Artificial Intelligence and Machine Learning in Sports Medicine: Mapping clinical tasks and assessing clinical maturity - a scoping review

Artificial Intelligence and Machine Learning in Sports Medicine: Mapping clinical tasks and assessing clinical maturity - a scoping review | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Artificial Intelligence and Machine Learning in Sports Medicine: Mapping clinical tasks and assessing clinical maturity - a scoping review Jakob Lindskog, Kristian Heder Ternell, Yinan Yu, Ida Lindman, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9259496/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 10 You are reading this latest preprint version Abstract Artificial intelligence (AI) and machine learning (ML) are rapidly transforming the medical field. The aim of this review was to outline the current scientific state of AI and ML application in sports medicine, evaluate the developmental and clinical maturity, and identify key priorities to guide future advancements and implementation. A scoping review was conducted with a literature search performed on February 5, 2026, using the MEDLINE, EMBASE and Web of Science databases which targeted AI or ML application on athletes within rehabilitation. Of 8,677 studies, 97 studies were included. Most research covered orthopaedics (70.1%) and neurology (18.6%), where AI was applied for injury prediction, diagnostic image analysis, and recovery estimation. Predictive and estimation models were the dominant application (57.7%). Reported discriminative performance was frequently high. However, the majority of studies relied on retrospective datasets and internal validation. Calibration reporting was uncommon, and prospective workflow integration was rare, with a single study attempting an interventional prevention strategy. Substantial heterogeneity in modelling approaches, data inputs, and outcomes definitions was observed. Although AI and ML applications in sports medicine frequently demonstrate strong within-sample performance, most remain in early-stage development. Currently, these tools should be viewed as supportive adjuncts rather than autonomous decision-making systems. AI predictive modeling diagnostic imaging rehabilitation deep learning return to sport Figures Figure 1 Figure 2 Introduction Artificial intelligence (AI) and machine learning (ML) are transforming healthcare by enabling machines to effectively analyze data, recognize patterns, and aid decision-making [ 1 ]. There is research that suggests that AI and ML might outperform humans within specific healthcare domains [ 2 – 4 ]. For example, ML models have, based on radiographic analysis, identified patients at risk for poor outcomes after unicompartmental knee replacement with greater accuracy than surgeons [ 2 ]. Similarly, chatbots powered by large language models (LLMs) have in one study surpassed physicians in diagnostic accuracy [ 3 ]. Furthermore, AI has reduced the miss rate for colorectal neoplasia detection by half [ 4 ]. These examples highlight the potential and increasing role of AI and ML in improving healthcare outcomes. Within sports medicine, AI and ML applications have attracted considerable interest. For example, Hu et al. [ 5 ] demonstrated that the use of a convolutional neural network (CNN) could detect anterior cruciate ligament (ACL) injury through magnetic resonance imaging (MRI) with an accuracy of 96.5%. Furthermore, Allen et al. [ 6 ] reported that a decision tree model could discriminate between early, typical and delayed recovery after sports-related concussion (SRC). Moreover, an extreme gradient boosting (XGBoost) model was used to predict level of match participation in football athletes after Achilles tendon rupture [ 7 ]. These studies showcase the potential of AI and ML in sports medicine. However, the literature remains fragmented, with limited understanding of how applications vary across fields and whether current work has progressed beyond retrospective analyses toward prospective or interventional use. Furthermore, it remains unclear whether existing AI and ML applications have reached sufficient developmental and clinical maturity to inform decision-making in sports medicine. The aim of this review was to outline the current scientific state of AI and ML application in sports medicine, evaluate the developmental and clinical maturity, and identify key priorities to guide future advancements and implementation. Method Protocol and registration As this was conducted as a scoping review with the purpose to map a rapidly growing field a formal review protocol was not considered needed. Eligibility criteria To be included in this review, papers needed to be written in English, published year 2000 or later, and were required to report on the use of AI or ML within the context of sports medicine. Peer-reviewed papers on all levels of evidence in accordance with the Oxford classification were included. All empirical study designs, including quantitative, qualitative, mixed-methods, case studies, and pilot studies, were considered with no restrictions with regards to cohort size or patient characteristics. Reviews, conference abstracts, commentaries (editorials, opinion pieces), system proposals (frameworks, protocols, datasets), articles without full-text availability, and pre-prints were excluded. System proposals were excluded, as the scope of this review was limited to studies that investigated the application of AI/ML within sports medicine. Information sources This study was conducted and presented in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR) checklist [ 8 ]. A scoping review approach was performed due to the heterogeneity of AI methods, outcomes, and study designs, which made a quantitative synthesis and detailed risk of bias assessment less feasible. A literature search was planned in collaboration with and was executed out on 2026-02-05 by medical university librarians, with expertise in electronic database searching. The search strategies were peer reviewed by another senior medical university librarian prior to execution in accordance with the PRESS Checklist [ 9 ]. No additional manual searching of references list or grey literature was conducted after the primary database search. The literature search included the MEDLINE, EMBASE, and Web of Science databases, to provide comprehensive coverage of sports medicine research relevant to the clinical scope of this study. Search The initial search strategy was developed to identify studies which involved the use of AI or ML technologies in the context of sports medicine. The search targeted two core elements. First, the population: Athletes who undergo rehabilitation. Second, the concept: Utilization of AI- or ML-based technologies, tools, or platforms within the treatment process. The broad search strategy was adopted to comprehensively map the diversity of AI and ML applications in sports medicine. The complete search strategy can be found in the Supplementary information. Selection of sources of evidence The screening process was performed with the Rayyan reference management platform (rayyan.ai) [ 10 ]. Screening of studies was performed by two independent reviewers (XX and YY) starting with title and abstract screening followed by full-text evaluation. At all stages, any differences were resolved by mutual agreement. For title and abstract screening, agreement between the authors was assessed with Cohen’s Kappa coefficient, calculated to 0.877, which suggests near perfect agreement. Data charting process Draft data charting tables were developed in Microsoft Excel (Version 16, Microsoft Corporation, Remond, WA, USA) to record extracted data from the included articles, guided by the scoping review research statement. The first two authors (XX and YY) performed the data charting process. Data items Study characteristics extracted included: bibliographic details (author(s), year of publication, and scientific journal), study characteristics (medical field, and country of origin), field of population (sport, sample size, age, study participant sex), AI-/ML application, data sources and input variables, output variables (outcomes), AI-/ML model(s) used, and key findings. Medical field classification was based on the primary clinical focus of each study. Studies were categorized as orthopaedics when the AI or ML application addressed musculoskeletal pathology, surgical outcomes, or rehabilitation related to orthopaedic conditions. The AI applications were categorized into four mutually exclusive application groups based on the primary aim of the AI component for each study. This categorization was not based on a single established or universally accepted classification framework, however, was pragmatically developed for the purpose of synthesizing the heterogeneous literature. Categories were defined a priori as follows: 1) Predictive and estimation models, in which algorithms were primarily used to predict outcomes, risks, or clinical parameters; 2) classification and pattern and recognition models, which focused on classification, clustering, feature extraction, or anomaly detection; 3) diagnostic and detection models, which aimed to identify diseases, conditions, or abnormalities; and 4) reasoning and summarization assistance models, where LLMs were central. When a study could plausibly fit more than one category, it was assigned to the group that best reflected the dominant role of the AI component. Critical appraisal of individual sources of evidence Due to the exploratory and descriptive nature of scoping reviews, and the heterogeneity of included studies, risk of bias and study quality assessments were not feasible and did not influence scoping review outcomes. Synthesis of results The results from the included studies were synthesized descriptively with a narrative approach, supported by tables and figures where appropriate [ 8 ]. Data charted from each study was grouped and summarized in accordance with key themes. These included: medical fields studied, AI-/ML applications, years of publication, study populations, AI-/ML models used in general, with more detailed subgroup analyses performed for orthopaedics and neurology due to the higher number of included studies in these fields, and lastly, the overall model development stage. No meta-analysis or quantitative pooling was conducted due to the heterogeneity of study designs, AI/ML approaches, and reported outcomes. Instead, findings were mapped to highlight the breadth of research activity, common areas of application, and gaps in the literature. Results In total, 8,677 records were identified, of which 97 were included (Fig. 1 ). Of the included studies, the medical fields represented were as follows: orthopaedics (n = 68, 70.1%), neurology (n = 18, 18.6%), radiology (n = 3, 3.1%), cardiology and cardiopulmonary (n = 2, 2.1%), nephrology (n = 1, 1.0%), odontology (n = 1, 1.0%), endocrinology (n = 1, 1.0%) and various (self-reported participation-restricting injuries [non-diagnosis-specific]; sports rehabilitation and digital health) (n = 3, 3.1%) (Table 1). Within orthopaedics, AI was primarily applied for injury prediction, outcome estimation, and rehabilitation monitoring, particularly concerning lower-extremity and ACL-related injuries. In neurology, models predominantly focused on SRC management, including classification of SRC severity and prediction of recovery duration. Radiology studies used AI for automated image optimization, detection of ligament injuries and bone marrow lesions, while the remaining medical fields involved isolated applications in injury-risk estimation (cardiopulmonary and cardiology), acute physiological responses (nephrology), dental injury prediction (odontology), and low bone mineral density (endocrinology). AI applications The AI application categories of the included studies were as follows: predictive and estimation models (n = 56, 57.7%), classification and pattern recognition models (n = 20, 20.6%), diagnostic and detection models (n = 11, 11.3%), and reasoning and summarization assistance models (n = 10, 10.3%) (Table 1). Within orthopaedics, predictive models were most common (43/68, 63.2%), whereas classification models were most common within neurology (9/18, 50.0%). Across AI applications, predictive and estimation models were mainly employed to forecast injury risk (n = 34), or recovery-related outcomes (n = 15), including return to sport (RTS) probability and functional improvement after orthopaedic injury/surgery. Classification and pattern-recognition models (n = 17) were primarily used to distinguish between injured and uninjured states, classify SRC or gait patterns, and identify biomechanical risk clusters. Diagnostic and detection models (n = 8) were mainly applied for image- or video-based injury identification, such as ACL or lumbar spine pathology. Reasoning and summarization assistance studies (n = 10) exclusively investigated LLM models (ChatGPT, Gemini, Bard, DeepSeek) for patient education and information quality assessment. Annual distribution of published studies Only two studies were identified before 2018, while the number increased thereafter, and peaked in 2025 (20 publications, 20.6%) (Fig. 2 and Table 1). Of all included studies, 86.6% were published between 2020 and 2026. Fields of population The most common specific fields of population were football (n = 25), followed by basketball (n = 6), rugby (n = 4), handball (n = 4), and runner-related populations (n = 4). Studies which included mixed athlete populations (n = 22) and a combination of athletes and non-athletes (n = 10) were also common. Data environments differed by sport: Football and running studies predominantly analyzed global positioning system (GPS)-based workload and accelerometry, whereas basketball, handball, and volleyball more often used laboratory biomechanical tests, balance/fatigue assessments, or physical performance analysis. Rugby studies included video-derived tackle characteristics. Sample sizes ranged from small elite squads to large youth/registry cohorts, with prospective designs typical for load-monitoring studies and cross-sectional designs were common for imaging/electroencephalogram (EEG) tasks. Across sports, female and para-sport cohorts were rarely represented, and only a minority integrated multimodal inputs that combined load, wellness/psychological, and clinical variables. AI models The five most included models used overall were random forest (RF) (n = 29), support vector machine (SVM) (n = 27), decision tree (DT) (n = 20), neural network (NN) (n = 15), and XGBoost (n = 12) (Table 2 ). Among the three most common population groups, RF models were most frequently used in studies which involved general athlete populations (9/20, 45.0%) and mixed populations (4/7, 57.1%). In studies focused on football, SVM and XGBoost models were the most commonly used, each applied in 10 out of 25 studies (40.0%). Beyond these core algorithms, categorical boosting (CatBoost), adaptive boosting (AdaBoost), Light gradient boosting machine, and elastic-net penalized regression were frequent ensemble or regularized variations, and 14 studies explored newer architectures such as deep-learning models (TabNet, ConcNet, CNNs, feedforward NNs, recurrent NNs [RNNs], Faster region-based CNN [Faster R-CNN]) for imaging or signal-based classification. Model selection generally reflected data type: tree-based ensembles and SVMs dominated structured tabular datasets (e.g., sensor, GPS, clinical, or performance data), while CNNs and RNNs were used for imaging and video, and task-specific networks such as ConcNet for EEG. Unsupervised clustering (umap, k-means, subgroup discovery) appeared occasionally for identifying biomechanical or risk profiles. In total, 42 studies incorporated explainable AI methods (feature importance or Shapley additive explanation values). Ten studies investigated LLMs (ChatGPT, Gemini, Bard, DeepSeek) for patient education rather than prediction. Although internal cross-validation was common, external/temporal validation and reporting of calibration metrics were rare, which underscores that while AI model performance was often strong, methodological maturity and reproducibility remain limited across sports medicine applications. Studies in orthopaedics Within orthopaedics (n = 68), AI was applied to three main areas: injury prediction, diagnostic imaging/video analysis, and outcome estimation after ligament reconstruction (Table 1). Common inputs included isokinetic knee strength, hop and balance tests, jump biomechanics, GPS-derived loads, clinical/radiographic fields, and MRI/computer tomography (CT) or match-video frames. Most studies (43/68, 63,2%) implemented predictive/estimation models, which typically used preseason screening (neuromuscular tests and anthropometrics), training-load/GPS and wellness logs, or clinical/surgical registry data to forecast ACL injury/reinjury, muscle strain, or RTS and functional recovery. Discrimination was generally poor to excellent (AUC 0.61–0.97, accuracy 65–98%), with tree-based ensembles (RF, XGBoost, gradient boosting) frequently achieved AUC ≥ 0.80 [ 7 , 11 – 16 ] and, in a few ACL-specific outcome models, approached 0.90–0.95 [ 17 , 18 ]. Diagnostic/detection studies (9%) focused on imaging and video, for example, CNN or RNN models to identify ACL injury from online match footage or to distinguish lumbar spondylolysis from non-specific low-back pain, reported accuracies of 73–96%. Beyond imaging, several works modeled post-operative trajectories (e.g., graft rupture risk, subjective function, and psychological readiness), drawing on isokinetic strength, hop tests, y-balance tests and patient reported outcomes. A small subset evaluated LLMs for orthopaedic patient education (e.g., ACL reconstruction and sports surgery information quality), which represented methodological exploration rather than prediction. Taken together, the orthopaedic literature reports strong within-sample performance on structured, tabular data and promising results for image/video-based detection, however, external/temporal validation and diverse cohorts (including female athletes) remain limited, which constrained generalizability. Studies in neurology In neurology-focused research (n = 18), nearly all studies (17/18, 94.4%) examined SRC, that used models to predict recovery time or classify concussion presence/severity (Table 1). Inputs were predominantly clinical and neurocognitive assessments (e.g., sport concussion assessment tool 3/5, vestibular ocular motor screening, symptom inventories, prior SRC, and time-to-clinic), sensor-based biomechanics (head-impact kinematics, and dual-task gait/behavioral performance), and physiological signals including EEG (resting-state and task-based) and radiomics from MRI/diffusion tensor imaging, where several studies combined these into multimodal feature sets. Reported performance was moderate to excellent, with AUC 0.70–0.96 and accuracy 75–96%. For recovery-time prediction, decision-tree and boosting approaches achieved AUC ~ 0.80 and sensitivity > 0.90 for early-recovery classification in pediatric and youth cohorts [ 6 , 19 ]. For SRC classification, SVM/RF/boosting models commonly reached AUC ≥ 0.80 [ 20 – 22 ], while deep-learning on EEG (e.g., ConcNet) reported the highest accuracy (94%) [ 23 ]. Overall, neurology applications show strong within-sample discrimination across both predictive and classification use-cases and growing interest in multimodal modeling. However, external/temporal validation, standardized feature sets, and explainability remain limited, which constrained generalizability beyond single-site cohorts. Model validation and translational stage Across all included studies, the majority relied on retrospective datasets and internal validation procedures, most commonly cross-validation or train-test splits. Only three studies employed external datasets to assess generalizability, and reporting of calibration metrics was uncommon [ 24 – 26 ]. Prospective implementation within preventive or decision-making workflows was rare, with only one study attempting a feedback-based interventional approach [ 27 ]. Two studies evaluated AI-integrated rehabilitation systems within structured training programs, which included one randomized controlled trial in postoperative ACL rehabilitation [ 28 ] and one application which combined AI and virtual reality for athlete rehabilitation training [ 29 ]. Table 2 Heatmap of AI-/ML model(s) used in each included study* Table 1: Overview of included studies. Author Year Journal Country Medical field Field of population Sample size, n Age, mean years or range Sex, males % AI application AI outcome Model(s) Key findings Data used Abasi et al.[ 30 ] 2025 BioData Minin Iran Cardiopulmonary Elite football 256 NR NR Predictive & Estimation models Prediction of reinjury risk SVM, CatBoost, RF, XGBoost CatBoost; Acc: 0.9138, F1: 0.9148; SVM: AUC: 0.9725 Cardiopulmonary data Allen et al.[ 6 ] 2023 Journal of Neurosurgery: Pediatrics. USA Neurology Pediatric athletes 493 15.7 68 Predictive & Estimation models Prediction of early (≤ 14), typical (15–27), delayed (≥ 28) recovery time (days) from SRC DT AUC: 0.80, Youden: 0.44. Sen: >0.90 (Classified early recovery) Demographics, post-SRC symptom scales, time-to-clinic presentation, concussion history, presence of defined symptom clusters Aoyag et al.[ 31 ] 2021 Spine Japan Orthopaedics Junior high-school athletes 223 13.5 72 Diagnostic & Detection models Distinguish lumbar spondylolysis from non-specific low back pain CART Sen: 0.64, Spec: 0.92, AUC: 0.79 Demographics, school grades, symptom onset time, history of lower-back pain, pre-existing conditions and anthropometry Ayala et al.[ 32 ] 2019 International Journal of Sports Medicine Spain Orthopaedics Professional football 96 NR 100 Predictive & Estimation models Prediction of risk factors of hamstring injury DT AUC: 0.837, Sen: 0.778, Spec: 0.838 Preseason: psychological, neuromuscular, and demographical data Bazarian et al.[ 33 ] 2021 JAMA Network Open USA Neurology Athletes 580 19.5 54 Classification & Pattern recognition Classification of SRC based on EEG Genetic algorithm Sen: 0.860, Spec 0.708, NPV: 0.901, PPV: 0.620, AUC: 0.89 EEG, cognitive tests, symptom inventories Bergeron et al.[ 34 ] 2019 Medicine & Science in Sports & Exercise USA Neurology High-school football 2004 NR NR Predictive & Estimation models Estimation of symptom resolvment after SRC NB, SVM, 5-nearest neighbours, DT, RF, MLP, radial basis function network NB and RF with 100 or 500 trees: AUC: 0.656–0.742 Symptom and recovery data Briand et al.[ 35 ] 2022 Frontiers in Sports & Active Living Canada Various (orthopaedics and neurology) Short-track speed skaters 11 21 0 Predictive & Estimation models Prediction of injury RF Sen: 0.5, Spec 0.7 Longitudinal: training load, physiological, neuromuscular, psychological well-being, heart rate variability and injury history data Calderon-Diaz et al.[ 36 ] 2023 Sensors Chile Orthopaedics Professional football 110 NR 100 Predictive & Estimation models Prediction of muscle injury DT, discriminant methods, NB, SVM, KNN, NN, XGBoost XGBoost: Prec: 78%. Biomechanical and muscle performance data Cao et al.[ 37 ] 2008 IEEE Transactions on Neural Systems & Rehabilitation Engineering USA Neurology Rugby and American football 61 20 44 Classification & Pattern recognition Classification of residual functional deficit SVM Acc: 77.1%, Sen: 80.0%, Spec: 75.0% EEG Castellanos et al.[ 38 ] 2021 Sports Medicine USA Neurology US Military cadettes 15682 19 65 Predictive & Estimation models Prediction of SRC risk SVM AUC: 0.73 Baseline demographic, clinical, cognitive and behavioral data Chen et al.[ 39 ] 2022 Computational & Mathematical Methods in Medicine China Orthopaedics Basketball 935 20 76 Classification & Pattern recognition Classification of thoracolumbar vertebral fractures (ABC) Deeplearning: Faster RCNN Acc: 86.4%, Cohen's kappa: 0.850 CT images Chu et al.[ 19 ] 2022 Annals of Physical & Rehabilitation Medicine USA Neurology Youth athletes 655 13.7 (male), 14.0 (female) 55 Predictive & Estimation models Prediction of SRC recovery CatBoost, DT, elastic net, RF, XGBoost, TabNet CatBoost: AUC: 0.8 (males), and 0.78 (females) Preinjury risk factors, injury severity measures, post-SRC functional and symptom data Dandrieux et al.[ 27 ] 2025 BMJ Open Sport & Exercise Medicine France Various Track and field 112 34 62 Predictive & Estimation models Investigate association between injury risk estimation and injury burden Negative binomial regression AUC: 0.63 Longitudinal: training activity, psychological state, sleep quality, and self-reported injury status De la Fuente et al.[ 40 ] 2023 Science & Medicine in Football Chile Orthopaedics Football 21 22.5 0 Classification & Pattern recognition Clustering to determine risk profiles based on biomechanical properties umap 3 clusters of biomechanical properties Biomechanical data de Leeuw et al.[ 41 ] 2022 European Journal of Sport Science Netherlands Orthopaedics Volleyball 10 27 100 Predictive & Estimation models Prediction of overuse injuries Subgroup discovery Jump load was an important predictor for 70% of players Longitudinal: training load, subjective wellness reports and overuse symptom questionnaires DiCesare et al.[ 42 ] 2020 Annals of Biomedical Engineering USA Neurology Football 20 16 0 Classification & Pattern recognition Classification of sub-SRC impact exposure XGBoost Acc: 83.5% Wearable sensor data, video-verified head impact recordings and MRIs Diniz et al.[ 7 ] 2022 Knee Surgery, Sports Traumatology, Arthroscopy Various Orthopaedics Football 209 28.3 100 Predictive & Estimation models Prediction of level of match participation Clustering, XGBoost XGBoost: AUC: 0.81 Match participation and performance data Diniz et al.[ 43 ] 2024 Knee Surgery, Sports Traumatology, Arthroscopy Various Orthopaedics Football 236 26.6 100 Predictive & Estimation models Cross-validation of identified ACL injury mentions OpenAI’s GPT-4o mini Sen: 88.4%, Spec: 99.3% Publicly available textual and database data Elkin et al.[ 44 ] 2018 Applied Clinical Informatics USA Orthopaedics Mixed 469 44 50 Diagnostic & Detection models Diagnosis of knee injury Bayesian and heuristic model Specificity-based Bayesian model significantly outperformed heuristic model Patient-reported questionnaire Eskofier et al.[ 45 ] 2012 Computer Methods in Biomechanics & Biomedical Engineering Canada Orthopaedics Runners 80 41.1 (male), 36.0 (female) 50 Classification & Pattern recognition Classification of participants with or without patellofemoral pain syndrome AdaBoost Acc: 100%. Biomechanical data Evans et al.[ 46 ] 2024 PLoS ONE UK Orthopaedics Rugby 36 20.7 100 Classification & Pattern recognition Classification of non-contact lower limb injuries risk factors Bayesian pattern recognition and assessed by means of: NB, J48 DT, SVM, KNN AUC 0.76 (severe non-contact lower limb), 0.70 (non-contact lower limb), and 0.71 (non-contact ankle) Longitudinal: training load, performance test results, musculoskeletal screening metrics and injury history Farhadian et al.[ 47 ] 2020 BMC Sports Science, Medicine and Rehabilitation Iran Odontology Pediatric athletes 356 11.3 (injured), 10.6 (uninjured) 54 Predictive & Estimation models Prediction of dental injury RF Acc: 89.3% Demographic and behavioral data Ferris et al.[ 20 ] 2021 American Journal of Sports Medicine USA Neurology Collegiate athletes 388 19.9 63 Diagnostic & Detection models Diagnosis of SRC AdaBoost Increased diagnostic accuracy by 4.4% to AUC: 0.848, and increased Sen by 9% Multimodal concussion assessment data Freitas et al.[ 48 ] 2025 PLoS ONE Portugal Orthopaedics Professional football 34 26.3 100 Predictive & Estimation models Prediction of non-contact injuries in footballers SVM, Feedforward NN, AdaBoost SVM: Acc: 74%, Sen: 71%, Spec: 74% Wearable GPS data Garcia et al.[ 49 ] 2019 Journal of Neurotrauma USA Neurology Athletes and military 24561 19.3 58 Predictive & Estimation models Prediction of SRC levels CART Sen: 91.07% to 97.40% Concussion assessment and demographic data Gaudet et al.[ 50 ] 2019 Journal of Science & Medicine in Sport Canada Orthopaedics Swimmers and handball 34 21.7 0 Classification & Pattern recognition Clustering to determine shoulder injury based on subjective outcomes K-mean clustering Sen: 86%, Spec: 100%, diagnostic OR: 229.67 (KJOC). Sen: 86%, Spec: 37%, diagnostic OR: 3.53 (CKQUEST) Functional performance and self-reported clinical assessment data Giorgino et al.[ 51 ] 2024 Diagnostics Italy Orthopaedics NA NA NA NA Reasoning & summarization assistance Use of an LLM for patient education Google Bard & ChatGPT-3.5 Both models show good promise in patient education Text-based conversation responses Girard et al.[ 52 ] 2025 Knee Surgery, Sports Traumatology, Arthroscopy Canada Orthopaedics Adolescents with and without ACL injury 134 15.3 (ACL injured) 13.8 (controls) 30 (ACL injured) 44 (controls) Classification & Pattern recognition Classification of ACL injury status DT Entire group: Acc 0.675, Sen 0.70, Spec 0.65, F1 0.684; Females: Acc 0.769; Males: Acc 0.533 Biomechanical data Goggins et al.[ 53 ] 2022 International Journal of Sports Medicine United Kingdom Orthopaedics Elite pathway cricket 17 18.2 0 Predictive & Estimation models Prediction of injury DT, RF DT: AUC: 0.66. RF: AUC: 0.72 Longitudinal: training load and performance monitoring data Gultekin et al.[ 54 ] 2025 Knee Surgery, Sports Traumatology, Arthroscopy Turkey Orthopaedics NA NA NA NA Reasoning & Summarization models Evaluation of LLM-generated ACL surgery patient education responses ChatGPT-4o, DeepSeek R1 Both high accuracy (3.9/4) and consistency (4/4); ChatGPT more comprehensive (4.0 vs 3.2, p < 0.001); DeepSeek clearer (3.9 vs 3.0, p < 0.001) and more readable (FKGL 8.9 vs 14.2; FRES 61.3 vs 32.7) Text-based conversation responses Guo et al.[ 16 ] 2025 PeerJ China Orthopaedics Collegiate basketball 104 20.4 100 Predictive & Estimation models Prediction of ACL injury incidence RF, SVM, XGBoost, LR RF: AUC 0.80; Accuracy 0.962; XGBoost AUC 0.79; Logistic regression AUC 0.76; SVM AUC 0.66 Demographic, injury history, biomechanical and EMG data Hecksteden et al.[ 55 ] 2023 Science and Medicine in Football Germany Orthopaedics Professional football players 88 24.6 100 Predictive & Estimation models Forecasting non-contact time-loss injuries GBoost, LR GBoost: CV AUC 0.61; Test AUC 0.62; without screening data AUC 0.56; without upsampling AUC 0.48 Physical performance, clinical, injury history and daily training, recovery and exposure data Henriquez et al.[ 56 ] 2020 Frontiers in Sports & Active Living USA Orthopaedics Student athletes 122 19.6 59 Predictive & Estimation models Prediction of musculoskeletal injury RF Acc: 79% Biomechanical, physical performance, demographic and injury history data Hopkingson et al.[ 11 ] 2022 European Journal of Sport Science Various European Orthopaedics Rugby 246 NR NR Classification & Pattern recognition Classification of injurious or no-injurious tackles RF Acc: 0.919, Sen: 0.995, Spec: 0.525 Video-derived tackle characteristics Hsu et al.[ 57 ] 2022 Journal of Human Kinetics Various Nephrology Ultramarathon runners 22 44 95 Predictive & Estimation models Prediction of acute kidney injury SVM Sen: 90%, Spec 100% Baseline psychological, biochemical, and body composition data Hu et al.[ 5 ] 2025 Scientific Reports Croatia Radiology Mixed 3064 NR NR Diagnostic & Detection models Detection of ACL injury CNN + modified political optimizer Acc: 96.496%, Sen: 99.767%, Spec: 98.557% MRI Huang et al.[ 58 ] 2022 Frontiers in Physiology China Orthopaedics Youth basketball 16 16.6 0 Predictive & Estimation models Prediction of lower extremity non-contact injury Fusion model, XGBoost, RF Fusion model: Prec: 0.9932, recall: 0.9976, F2: 0.9967 (non-injured). Prec: 0.9317, recall: 0.9167, F2: 0.9171 (minimal LE NC). Prec: 0.9000, recall: 0.9000, F2: 0.9000 (mild LE NC) Longitudinal: training load, perceived well-being, psychological responses, physical performance metrics, and injury history Huang et al.[ 59 ] 2023 Frontiers in Physiology China Orthopaedics Youth basketball 17 15 0 Predictive & Estimation models Prediction of lower limb non-contact injury Cost-sensitive NN AUC: 0.8590, Prec: 0.6360, recall: 0.8700, F2: 0.7980, Brier: 0.1020 Physical fitness, physiological data: performance metrics, biochemical markers, physiological responses, and perceived exertion Hwang et al.[ 12 ] 2025 Orthopaedic Journal of Sports Medicine South Korea Orthopaedics Athletes 113 27 67 Predictive & Estimation models Prediction of subjective function, symptoms, and psychological readiness GBoost, SVM, LR, DT, RF GBoost: AUC: 0.844, F1: 0.889 (Successful recovery of PASS, IKCD). RF: AUC: 0.835, F1:0.732 (PASS ACL-RSI) Isokinetic muscle strength and y-balance test results and patient reported outcomes Hwang et al.[ 17 ] 2024 Digital Health South Korea Orthopaedics Athletes 102 30 74 Predictive & Estimation models Prediction of return to sport after ACL reconstruction RF, GBoost RF: AUC: 0.952 (single leg hop), and 0.949 (Tegner activity scale). GBoost: AUC: 0.868 (single leg vertical hop) Physical performance data: balance, and isokinetic muscle strength Jacob et al.[ 21 ] 2022 Scientific Reports Iceland Neurology Elite athletes 54 38.4 0 Classification & Pattern recognition Classification of SRC RF, GBoost, AdaBoost, SVM, MLP SVM: Acc: 95.5% EEG, EMG; heart rate, and center of pressure and concussion assessment scale (SCAT5) Jauhiainen et al.[ 60 ] 2022 American Journal of Sports Medicine Various Orthopaedics Elite football and handball 791 21 0 Predictive & Estimation models Prediction of ACL injury SVM linear and with imbalance handling, RF, L2-regularized LR Linear SVM: AUC: 0.63 Preseason biomechanical and physical performance data Jauhiainen et al.[ 61 ] 2020 International Journal of Sports Medicine Finland Orthopaedics Youth basketball and floorball 314 16.0 (male), 15.4 (female) 45 Predictive & Estimation models Prediction of injury risk RF AUC: 0.63 Baseline biomechanical and physical performance data and anthropometrics Jia et al.[ 62 ] 2022 Computational Intelligence & Neuroscience China Orthopaedics Gymnasts 126 15.3 0 Classification & Pattern recognition Identification of injury through images Fuzzy pattern recognition. NN. Identified injury situation through images Image data and biomechanical force analysis Karbalaie et al.[ 63 ] 2026 Journal of Sports Sciences Sweden Orthopaedics Mixed: Patients with ACL-R 107 25.2 (ACLR); 22.4 (controls) 36 Classification & Pattern recognition Classification of high versus low fear of re-injury CNN, LR CNN: Acc 75.6%, F1 0.6, MCC 0.52; 8.6% higher Acc compared to LR Biomechanical data Kolodziej et al.[ 64 ] 2023 Scandinavian Journal of Medicine & Science in Sports Germany Orthopaedics Youth elite football 56 17.2 100 Predictive & Estimation models Prediction of lower extremity injury risk LASSO. Leave-One-Out LASSO: AUC: 0.63, Sen: 35%, Spec: 79% Biomechanical, neuromuscular and postural control data Kunze et al.[ 65 ] 2021 Journal of Bone & Joint Surgery USA Orthopaedics Athletes 1118 30 32 Predictive & Estimation models Prediction of functional Improvement ENPLR, stochastic GBoost, RF, AdaBoost, NN, SVM ENPLR: AUC: 0.77, intercept: 0.7, slope: 1.22, Brier: 0.14 Clinical, demographic and radiographic registry data Kunze et al.[ 66 ] 2021 Orthopaedic Journal of Sports Medicine USA Orthopaedics Mixed: Patients with ACL-R 442 29 52 Predictive & Estimation models Prediction of clinically meaningful improvement after ACL reconstruction Stochastic GBoost, RF, NN, SVM, AdaBoost, ENPLR ENPLR: AUC: 0.82, intercept: 0.10, slope: 1.15, Brier: 0.068 Clinical and surgical registry data Lipps Lene et al.[ 67 ] 2024 Journal of Experimental Orthopaedics France Orthopaedics Athletes 96 21.9 (male), 21.1 (female) 64 Diagnostic & Detection models Identification of participants with earlier knee injury DT, MLP, XGBoost DT and MPL: AUC: 0.94, Acc: 0.95, Prec: 1.0, Recall: 0.88, F1: 0.93 Biomechanical and psychological data López-Valenciano et al.[ 68 ] 2018 Medicine & Science in Sports & Exercise Spain Orthopaedics Professional football and handball 132 NR 100 Predictive & Estimation models Prediction of muscle injury C4.5 DT, SimpleCart, ADTree, RandomTree ADTree: AUC: 0.747, Sen: 65.9%, Spec: 79.1% Preseason demographic, psychological and neuromuscular data Lövdal et al.[ 69 ] 2021 International Journal of Sports Physiology & Performance Netherlands Orthopaedics High-level middle- and long-distance runners 74 NR 64 Predictive & Estimation models Prediction of injury XGBoost AUC: 0.724 (day), and 0.678 (week) Longitudinal training load data (GPS and subjective training feedback) Lu et al.[ 13 ] 2022 Orthopaedic Journal of Sports Medicine USA Orthopaedics Elite basketball 2103 26 100 Predictive & Estimation models Prediction of lower extremity muscle strain/injury XGBoost, RF, NN, SVM, elastic net penalized LR, generalized LR XGBoost AUC: 0.840 Longitudinal player performance and historical injury data Martínez-Gramage et al.[ 14 ] 2020 Sensors Spain Orthopaedics Triathletes 19 14.6 53 Predictive & Estimation models Prediction of running injury RF AUC: 0.8, Sen: 0.6, Spec: 0.8, NPV 0.7, Matthews correlation coefficient 0.4 Biomechanical, neuromuscular, and injury incidence data Maxin et al.[ 22 ] 2024 Diagnostics USA Neurology Collegiate football 93 20 100 Diagnostics & Detection models Diagnosis of acute SRC RF, KNN, SVM, LR (SMOTE) Post-SMOTE RF: Acc 91%, Sen 98%, Spec 86%, AUC 0.91, F1 0.92 Smartphone-based quantitative pupillometry McBee et al.[ 70 ] 2024 JMIR medical education USA Various NA NA NA NA Reasoning & summarization assistance LLM for interdisciplinary panel discussion on sports medicine ChatGPT-4 Reasonably pointed to various benefits such as 24/7 support, personalized advice, automated tracking, and reminders Text-based conversation data Murray et al.[ 71 ] 2024 Sports & Health USA Neurology Student athletes 409 20 56 Classification & Pattern recognition Classification participants with or without SRC LR Single-task tests were slower in patients with SRC Biomechanical and behavioral performance data including cognitive task response rates Nechita et al.[ 72 ] 2025 Diagnostics Romania Cardiology Youth athletes 312 7 to 17 NR Diagnostic & Detection models Detection of cardiovascular injury risk RF, CNN RF: Acc: 97.87%, Sen: 75%, Spec: 98.3%, Prec: 98% Physiological ECG data Nolte et al.[ 18 ] 2025 Journal of Sports Sciences Germany Orthopaedics Mixed: Patients with/without ACL injury 549 22.2 (male), 23.0 (female) 67 Predictive & Estimation models Prediction of participants being ACL-injured or not RF AUC: 0.90 (male), AUC: 0.92 (female) Isokinetic strength test data Nonnenmacher et al.[ 73 ] 2025 Bone & Joint Open Germany Orthopaedics Athletes with periacetabular osteotomy 235 31.9 17 Predictive & Estimation models Prediction of early RTS at 3 and 6 months after surgery LR, Conditional inference tree Early RTS associated with surgical approach, sport frequency, psychological factors, and pain; delayed RTS with male sex and older age. Preoperative demographic and patient-reported questionnaire data Nose-Ogura et al.[ 26 ] 2025 Physician and Sportsmedicine Japan Endocrinology Athletes 614 20.9 (development), 19.6 (validation) 0 Predictive & Estimation models Prediction of low bone mineral density LASSO Development AUC 0.89; Validation AUC 0.74; Sensitivity 0.83; NPV 0.85 Preoperative questionnaire and dual-energy X-ray absorptiometry data Ohlsen et al.[ 74 ] 2025 Cureus USA Orthopaedics NA NA NA NA Reasoning & Summarization assistance models Agreement of LLM recommendations with clinical guidelines for ACL and meniscal injuries ChatGPT-4o, Gemini 2.5 Pro ChatGPT: 82% agreement, Gemini: 73% agreement; no significant difference between models Text-based conversation data Oliver et al.[ 75 ] 2020 Journal of Science & Medicine in Sport England Orthopaedics Youth elite football 355 14.3 100 Predictive & Estimation models Prediction of non-contact lower extremity injury Multivariate LR, supervised learning DT DT: AUC: 0.663, Sen: 55.6%, Spec: 74.2% Preseason neuromuscular screening data and anthropometric measures Ozbek et al.[ 76 ] 2025 Arthroscopy Turkey / USA Orthopaedics NA NA NA NA Reasoning & Summarization assistance models Quality assessment of LLM responses to hip arthroscopy patient questions ChatGPT 4.0 20/25 rated "excellent"; 5/25 "satisfactory" Text-based conversation data Pérez-Contreras et al.[ 77 ] 2025 Applied Sciences-Basel Chile Orthopaedics Professional football 41 22.3 56 Predictive & Estimation models Prediction of non-contact muscle injury risk LR, DT, KNN, RF, GBoost, NN KNN: Acc 87%, AUC 0.87; Gradient Boosting: Acc 84%, AUC 0.90; Logistic Regression AUC 0.50 Preseason biomechanical and training load data Piłka et al.[ 78 ] 2023 Sensors Poland Orthopaedics Football 36 24 100 Predictive & Estimation models Prediction of football injury XGBoost Prec: 92.4%, recall: 96.5%, F1: 94.4% Training and match load data Quinn et al.[ 79 ] 2024 Arthroscopy USA Orthopaedics NA NA NA NA Reasoning & summarization assistance LLM to test quality of information with regard to ACL reconstruction ChatGPT-4, Gemini ChatGPT-4 and Gemini: Overall good ability to generate accurate and relevant responses Text-based conversation data Rossi et al.[ 80 ] 2023 Sport Sciences for Health Italy Orthopaedics Elite football 18 24.7 100 Predictive & Estimation models Prediction of non-contact injury risk DT, GBoost, k-mean cluster Acc increased to 63% (15% improvement) after blood profile was added to workload-only models GPS-derived external workload and blood biomarker data Richter et al.[ 24 ] 2023 Sports Biomechanics Norway Orthopaedics Elite football and handball 822 21 0 Predictive & Estimation models Prediction of participants with previous-/future-/no ACL injury DT, RF, discriminant analysis, NB, KNN, SVM, LR, NN Cluster of models: Average AUC 0.62, Sen: 0.59, Spec: 0.58 Biomechanical data Robinson et al.[ 81 ] 2022 American Journal of Physical Medicine & Rehabilitation USA Neurology Athletes 273 21 52 Predictive & Estimation models Prediction of prolonged recovery after SRC DT Acc: 0.7636, Sen: 0.6429, Spec: 0.8889, PPV: 0.8571, NPV: 0.7059 Symptom evaluation data (SCAT5) Rommers et al.[ 15 ] 2020 Medicine & Science in Sports & Exercise Belgium Orthopaedics Youth elite football 734 11.7 100 Predictive & Estimation models Prediction of musculoskeletal injury XGBoost Acc: 85%, Prec: 85%, recall: 85% Preseason anthropometric, motor coordination and physical performance data Ruddy et al.[ 82 ] 2018 Medicine & Science in Sports & Exercise Australia Orthopaedics Australian football 362 23.2 (2103), 25.0 (2015) 10 Predictive & Estimation models Prediction of hamstring injury NB, LR, RF, SVM, NN Median of all 5 models: AUC: 0.58 (2013 season), 0.57 (2015 season) Preseason demographic, injury history and strength test data Ruiz-Pérez et al.[ 83 ] 2021 Frontiers in Psychology Spain Orthopaedics Elite Futsal 139 22.5 52 Predictive & Estimation models Prediction of soft tissue injury C4.5, Alternating DT, SVM with SMO, KNN, Instance-Based Learning Various models: AUC: 0.701 to 0.767 Preseason psychological and neuromuscular data Saghafi et al.[ 84 ] 2018 Proceedings of SPIE USA Neurology Youth and high-school football 122 9 to 18 N/A Classification & Pattern recognition Classification of white matter changes after head impact exposure CNN AUC: 85.71%, F1: 83.33% Neuroimaging and biomechanical data Saglam et al.[ 85 ] 2025 BMC Medical Informatics & Decision Making Turkey Orthopaedics NA NA NA NA Reasoning & Summarization assistance models Comparison of GPT's in clinical decision-making GPT-4, GPT-3.5 GPT-4 significantly outperformed GPT-3.5 (p < 0.001; Cohen’s d = 1.42); higher treatment and rehabilitation suitability (p < 0.001) Text-based conversation data Schulc et al.[ 86 ] 2024 Orthopaedic Journal of Sports Medicine USA Orthopaedics Professional athletes with ACL injury 129 NR NR Diagnostic & Detection models Identification of ACL injury through video analysis Recurrent NN AUC: 0.88, F1: 0.63 Video-derived biomechanical data Shibata et al.[ 87 ] 2019 Journal of Orthopaedic Science Japan Orthopaedics Patients with ACL-R 386 23.7 53 Predictive & Estimation models Prediction of quadriceps strength recovery 6 months after ACL-R DT, Stepwise multiple linear regression Preoperative QSI, age, and pre-injury Tegner score predicted 6-month QSI; decision tree correctly classified 46.8% of cases Preoperative isokinetic quadriceps strength, demographic, clinical and intraoperative finding data Song et al.[ 29 ] 2022 Wireless Communications & Mobile Computing China Orthopaedics Track and field 12 19.5 N/A Predictive & Estimation models Evaluation of rehabilitation effectiveness using AI and virtual reality-assisted training Probabilistic NN, SVM AI+virtual reality group achieved > 96% physical function recovery; overall rehabilitation score 93.79 vs 82.38 (control) Physiological blood measures, functional, strength and speed assessment data Sparks et al.[ 88 ] 2024 JB & JS Open Access USA Orthopaedics NA NA NA NA Reasoning & summarization assistance LLM to investigate accuracy of patient education with regard to orthopaedic conditions ChatGPT-3.5 Moderately accurate outputs for general inquiries. Lack in the quantity of information for risk factors and treatment options. Text-based conversation data Stirling et al.[ 89 ] 2025 Journal of Orthopaedic Research Canada Radiology Patients with ACL injury 100 33.6 32 Classification & Pattern recognition Automated quantification of bone marrow lesion volume and association with pain outcomes CNN Bone marrow lesions present in 95%; 96.1% volume reduction at 1 year (p < 0.001); baseline BML volume modestly associated with symptoms MRI and patient-reported questionnaire data Tamez-Peña et al.[ 90 ] 2021 Frontiers in Neurology Unknown Neurology Student athletes 122 18.8 53 Classification & Pattern recognition Classification of SRC SVM Sen: 0.80, Spec: 0.74 Neuroimaging radiomic data Tedesco et al.[ 91 ] 2020 Sensors Ireland Orthopaedics Non-elite rugby 12 26 100 Diagnostic & Detection models Identification of gait patterns in participants with or without ACL injury KNN, NB, SVM, GBoost, MLP, stacking MLP: Acc: 73.07; GBoost: Sen: 81.8% Inertial sensor data Thanjavur et al.[ 23 ] 2021 Frontiers in Human Neuroscience Canada Neurology Adolescent athletes 58 13.4 (injured), 14.7 (uninjured) 100 Classification & Pattern recognition Classification of SRC ConcNet 2 and 3 Acc: 94% EEG data Tsilimigkras et al.[ 92 ] 2024 Journal of Sports Science & Medicine Greece Orthopaedics Professional football 25 N/A 100 Predictive & Estimation models Prediction of muscle injury risk SVM Acc: 0.78, Sen: 0.73, Spec: 0.85 Physiological and mechanical workload data Usami et al.[ 93 ] 2024 Knee Surgery, Sports Traumatology, Arthroscopy Japan Orthopaedics Mixed: Patients with ACL-R 386 25.1 49 Diagnostic & Detection models Detection of graft rupture and contralateral ACL injury NN AUC: 0.81 (graft rupture), 0.74 (contralateral ACL injury) Clinical, demographic, and surgical medical record data Vallance et al.[ 94 ] 2020 Applied Sciences-Basel France Orthopaedics Elite football 40 29.4 100 Predictive & Estimation models Prediction of non-contact injury risk KNN, DT, RF, XGBoost, SVM, MLP, Linear discriminant analysis, LR, Ridge regression, NB 1-month prediction: XGBoost AUC 0.97; 1-week prediction: questionnaires outperformed GPS data; internal load strongest short-term predictor GPS-derived external load, rating of perceived exertion and well-being questionnaire data Valle et al.[ 95 ] 2022 Sports Medicine Spain Orthopaedics Elite football 76 24.2 100 Predictive & Estimation models Prediction of recovery Linear regression, RF, XGBoost XGBoost (days to recovery): Mean absolute error: 9.78884, Root mean squared error: 12.1450, R-squared: 0.4847 Clinical and MRI data Villarreal-Espinosa et al.[ 96 ] 2024 Knee USA Orthopaedics NA NA NA NA Reasoning & summarization assistance LLM for patient education with regard to ACL surgery ChatGPT-4 5/10 responses completely accurate (by two reviewers), and 3/10 completely accurate (by at least one reviewer). Inter-rater reliability: weighted kappa: 0.57. 80% of responses were reproducible over time Text-based conversation data Wang et al.[ 25 ] 2026 Scientific Reports Various Orthopaedics Professional football 312 24.7 100 Predictive & Estimation models Prediction of non-contact lower extremity injuries RF, SVM, GBoost, DNN, Ensemble model Ensemble AUC 0.759 Isokinetic strength, training load, injury history and biomechanical data Weng et al.[ 97 ] 2025 Journal of Sports Sciences Taiwan Orthopaedics Various level baseball 98 18.0 (injured), 17.5 (uninjured) 100 Predictive & Estimation models Prediction of upper extremity injury GIRD, LR, RF, CatBoost, SVM CatBoost: AUC: 0.66, Acc: 0.70 Clinical and musculoskeletal data Yates et al.[ 98 ] 2025 BMJ Open Sport & Exercise Medicine England Neurology Contact sport athletes 375 24.2 78 Predictive & Estimation models Prediction of SRC recovery RF Acc: 94.6%, Sen: 100%, Spec: 93.8%, PPV: 71.4%, NPV: 96.3% Clinical and MRI data Ye et al.[ 99 ] 2023 Frontiers in Physiology Netherlands Orthopaedics Elite runners 64 N/A 65 Predictive & Estimation models Prediction of running injury GASF-DCAE-DNN AUC 0.985, Gmean: 0.930, Sen: 0.997, Spec: 0.868. Test: AUC: 0.891, Gmean: 0.830, Sen: 0.816, Spec: 0.845 Longitudinal training load, and physiological performance data Yüce et al.[ 100 ] 2024 Cureus Turkey Orthopaedics NA NA NA NA Reasoning & summarization assistance LLM for patient education with regard to sports surgery ChatGPT-4 DISCERN: 44.75 points. Sports surgery-specific scoring: 13.3 points Text-based conversation data Zhan et al.[ 101 ] 2025 Arthroscopy China Orthopaedics Mixed: Patients with MPFL-R 218 NR NR Predictive & Estimation models Prediction of clinical outcomes in patients with medial patello-femoral ligament reconstruction RF, LR, SVM, DT, implemented MLP, KNN Various models: AUC: 0.760 to 0.969, and Acc: 76.8% to 95.2% (Subjective outcomes); AUC: 0.952, and Acc. 95.2% (Return to pre-injury sport); AUC: 0.756, and Acc: 75.4% (Return to pivoting sports); AUC: 0.943, and Acc: 94.9 (Recurrent instability) Clinical, demographic and radiographic data Zhan et al.[ 102 ] 2023 Journal of Sport & Health Science USA Neurology Mixed: Lab, MMA, American football, automobile, NASCAR 3262 NR NR Classification & Pattern recognition Classification of head impact subtypes RF Acc: 96% Biomechanical data from head impact recordings Zhang et al.[ 103 ] 2022 Contrast Media & Molecular Imaging China Radiology Mixed: Patients with ACL injury 90 39 60 Diagnostic & Detection models Image optimization to assess ACL integrity iDose4 Iterative Reconstruction Algorithm. Improved image quality Clinical CT data Zhu et al.[ 104 ] 2026 BMC Sports Science, Medicine and Rehabilitation China Orthopaedics Patients with ACL-R 30 31.9 (RTS group), 36.9 (no-RTS group) 73% (RTS group), 60% (no RTS group) Classification & Pattern recognition Identification of urinary proteomic biomarkers associated with RTS LASSO AUC range 0.827–0.876 Urinary proteomic, isokinetic strength, hop test, thigh circumference and patient-reported questionnaire data Zhu et al.[ 28 ] 2026 Journal of Clinical Medicine China Orthopaedics Patients with ACL-R 79 30.9 89 Predictive & Estimation models Evaluate effectiveness of a rehabilitation protocol incorporating an AI-based assessment and correction system on functional recovery Intelligent Functional Movement and Physical Fitness Assessment System (ZD-200S-JG) Trial group showed significantly greater improvements in patient-reported outcomes and range of motion and rehabilitation adherence Non-wearable three-dimensional motion capture, clinical and patient-reported questionnaire data ACL-RSI = Anterior cruciate ligament-return to sport after injury, Acc = Accuracy, AdaBoost = Adaptive boosting, AI = Artificial intelligence, AUC = Area under the receiver operating curve, CART = Regression tree analysis, CatBoost = Categorical boosting, CNN = convolutional neural networks, DT = Decision tree, CT = Computer tomography, ECG = electrocardiogram, EEG = electrocochleography, EMO = Electromyography, ENPLR = Elastic-net penalized logistic regression, F1 = F1-Score, F2 = F2-Score, GASF-DCAE-DNN = Gramian Angular Summation Field-Deep Convolutional Auto-Encoder-Deep Neural Network, GBoost = Gradient boosting, GPS = Global positioning system, GPT = Generative pre-trained transformer, IKCD = International Knee Documentation Committee, KNN = K-nearest neighbor, LASSO = Least Absolute Shrinkage and Selection Operator, LE = Lower extremity, LR = Logistic regression, MLP = Multilayer perceptron, MRI = Magnetic resonance imaging, NA = Not applicable, NB = Naïve Bayes, NN = Neural networks, NPV = Negative predictive value, NR = Not reported, OR = Odds ratio, PASS = Patient acceptable symptom state, PPV = Positive predictive value, Prec = Precision, RF = Random forest, RTS = Return to sport, Sen = Sensitivity, Spec = Specificity, SRC = Sports-related concussion, SVM = Support Vector Machine, Youden = Youden index Table 2: Heatmap of AI-/ML model(s) used in each included study* AI-/ML model used Prediction and estimation, n = 56 Classification and pattern recognition, n = 20 Diagnosis and detection, n = 11 Reasoning and summarization, n = 10 RF 45% 15% 9% 0% SVM 36% 20% 18% 0% CatBoost 7% 0% 0% 0% XGBoost 20% 5% 9% 0% GBoost 13% 5% 9% 0% DT 30% 10% 9% 0% CART 2% 0% 9% 0% NB 9% 5% 9% 0% KNN 13% 5% 18% 0% MLP 5% 5% 18% 0% NN 18% 5% 18% 0% AdaBoost 4% 10% 9% 0% LR 27% 5% 9% 0% CNN 0% 15% 9% 0% LASSO 4% 5% 0% 0% K-mean cluster 0% 0% 0% 0% ChatGPT 2% 0% 0% 80% Bard 0% 0% 0% 10% Gemini 0% 0% 0% 20% DeepSeek 0% 0% 0% 10% Undefined GPT 0% 0% 0% 10% Other 25% 25% 18% 0% * = Within each task category, proportions were calculated as the number of studies using a specific model divided by the total number of studies in that category. AdaBoost = Adaptive boosting, CART = Regression tree analysis, CatBoost = Categorical boosting, CNN = convolutional neural networks, DT = Decision tree, GBoost = Gradient boosting, GPT = Generative pre-trained transformer, KNN = K-nearest neighbour, LASSO = Least Absolute Shrinkage and Selection Operator, LR = Logistic regression, MLP = Multilayer perceptron, NB = Naïve Bayes, NN = Neural networks, RF = Random forest, SVM = Support Vector Machine Discussion This scoping review provides a synthesis of AI applications across sports medicine, and demonstrates that, although methodological development has accelerated in recent years, most studies remain in an early developmental stage. Artificial intelligence has been widely applied for injury prediction, diagnostic imaging, and recovery estimation across diverse athletic and clinical populations, mostly within orthopaedics and neurology. Despite frequently high reported performance metrics, the literature is characterized by substantial heterogeneity in model selection, data modalities, outcome definitions, and validation procedures. Most studies relied on retrospective or observational prospective datasets and internal validation methods, whereas external or temporal validation and prospective prevention or intervention frameworks were rare. Consequently, the current evidence base does not yet support routine clinical integration of AI-driven decision tools in sports medicine. Although many models demonstrated strong discriminative performance, which often achieved AUC values ≥ 0.80, these findings must be interpreted in the context of important methodological limitations. High within-sample accuracy suggests that AI can effectively identify patterns associated with injury risk, recovery trajectories, or RTS potential. However, the vast majority of studies performed validation within the same dataset, typically through internal cross-validation or train-test splits. Only three studies employed external datasets to assess generalizability [ 24 – 26 ]. This represents a critical methodological limitation, as internal validation tends to overestimate model performance and fails to account for differences in population characteristics, data collection methods, or sporting environments [ 105 ]. Without robust external or temporal validation, the true predictive value and clinical reliability of these models remain uncertain. Accordingly, the literature reflects predominantly early-stage model development, with limited progression toward external validation, prospective integration, or demonstrated impact on clinical decision-making. Future studies should prioritize multi-center external validation across teams, seasons, and demographic groups, to evaluate whether reported performance translates into meaningful clinical utility. While AI-driven prediction models have been reported with strong retrospective accuracy, only Dandriex et al. [ 27 ] attempted to integrate predictions into a prospective, feedback-based prevention strategy, in which daily individualized feedback was provided to track-and-field athletes based on self-reported wellness data. However, adherence was low (average daily response rate of 37%), and no significant association with injury burden was observed, although a modest protective effect was suggested among participants with at least 9% response rate [ 27 ]. In addition to predictive frameworks, a small number of studies have integrated AI directly into structured rehabilitation programs. For example, one randomized controlled trial evaluated an AI-based assessment and correction system after ACL reconstruction [ 28 ], which demonstrated improvements in functional outcomes and rehabilitation adherence, while another study applied AI and virtual reality technology within athlete rehabilitation training [ 29 ]. These findings illustrate both the potential and the current limitations of AI-supported frameworks, namely, information alone does not yield benefit unless it is coupled with consistent athlete engagement, integration into clinical or training workflows, and actionable feedback mechanisms capable of influencing real-word decision-making. Sports injuries are inherently multifactorial, which arise from complex interactions between training load, biomechanics, physical fitness, psychological status, and contextual factors such as playing surface and competition demands [ 106 , 107 ]. Consequently, models that rely solely on single wellness or workload metrics are unlikely to capture the full spectrum of injury risk. This highlights the need for multimodal data integration that combines these factors to better reflect the complexity of athletic performance and health [ 108 ]. In the context of sports medicine, models intended to inform RTS decisions or reinjury risk estimation must also be interpretable, to allow stakeholders to understand which variables drive predictions and how they align with established clinical reasoning [ 108 ]. The growing use of high-performing yet opaque black-box models, such as DNNs, poses a barrier to practical implementation, as limited explainability can erode user confidence and hinder clinical decision-making [ 109 ]. Accordingly, development of AI frameworks that balance predictive strength with transparency will be crucial to support actionable and trustworthy decision support. Future research should extend beyond prediction to design and evaluate controlled, prospective, decision-driven systems that integrate real-time recommendations and test whether AI-supported interventions can meaningfully reduce injury incidence or improve recovery outcomes [ 110 ]. Overall, studies that evaluate the capabilities of LLMs in sports medicine suggest that these tools can generate generally accurate and informative responses, particularly for patient education. However, two key concerns were identified. Firstly, Sparks et al. [ 88 ] reported that LLM outputs often lacked sufficient detail with regard to risk factors and treatment options. Secondly, Villarreal-Espinosa et al. [ 96 ] found that two of ten responses about ACL surgery did not reach a very accurate rating, and that 80% responses were reproducible over time. In addition, LLMs are inherently susceptible to hallucinations, distribution shifts between training data and real-world use, and potential instability of output, all of which may further undermine their reliability in clinical athletic contexts [ 111 – 113 ]. These findings highlight the potential risk that patients may receive incomplete, inaccurate, or inconsistent information. Taken together, LLMs have serve as accessible adjunct educational tools, but current evidence does not support unsupervised clinical deployment. At present, their use should remain supervised by clinicians, particularly when addressing diagnosis, surgical decision-making, or RTS guidance. Future research should focus on benchmarking LLM performance against verified clinical standards and explore how these tools can be safely embedded into patient communication and rehabilitation pathways without compromission information accuracy. Image and diagnostic AI applications showed promise in accuracy for identification of ligament injuries, bone fractures, and concussion-related imaging patterns. These approaches leverage automated feature extraction from radiological or video data, which reduces reliance on manual interpretation [ 114 ]. However, most studies were limited by small sample size, and lack of external or multi-center validation, thus restricting clinical applicability [ 115 ]. Furthermore, image-based models often function as black boxes, with limited explainability of which image features drive decisions, which underscores the need for interpretable visualization methods to support clinical implementation. Across studies in which ML models were used alongside traditional regression approaches, ML algorithms demonstrated higher discriminative performance. However, these studies were limited to within-sample or internally validated analyses, and formal benchmarking with strict comparisons between methods was rare. Consequently, although ML models may offer incremental gains in discrimination, it remains unclear whether these improvements translate into superior calibration, generalizability, or meaningful enhancement of clinical decision-making. Future research should therefore include structured comparative evaluations that assess not only discrimination but also calibration, interpretability, and net clinical benefit to determine whether increased algorithmic complexity provides practical advantages over established biostatistical methods. Across studies, substantial model heterogeneity was observed, with each investigation employing diverse algorithms, feature sets, and outcome definitions. This diversity underscores the exploratory nature and limits consensus on optimal model families or architectures for specific sports or data types [ 116 ]. In parallel, the generalizability of existing models remains uncertain, as most datasets were small, single-site, and male-dominant, with minimal inclusion of female, youth, or para-sport athletes and limited representation outside Europe and North America leagues[ 105 ]. These sampling biases restrict the broader applicability of reported findings. Furthermore, the validity of any AI model ultimately depends on the quality of data input [ 117 ]. Inconsistent data collection methods, and missing contextual variables can all undermine predictive accuracy, regardless of algorithmic sophistication [ 117 ]. Collectively, this methodological variability reinforces that the field remains in developmental phase, in which foundational issues of data standardization, and reporting transparency must be addressed before reliable large-scale implementation can be achieved. Addressing these foundational issues through standardized data handling, and transparent reporting will be essential to build robust, and trustworthy AI systems in sports medicine. This review indicates that most current applications of AI and ML in sports medicine remain in an early developmental exploratory stage and should be interpreted cautiously in clinical settings. Consequently, these models should not yet be relied upon to independently guide clinical decision‑making, diagnosis, prognosis, or RTS recommendations. At present, many models rely on retrospective datasets, lack external validation, and have not undergone evaluation in real‑world clinical workflows, which limits their immediate clinical reliability and generalizability. Furthermore, the majority of the included studies focused on orthopaedics or neurology, hence the generalizability to other specialties remains low. The main contribution of this review was to provide clinicians and researchers with a clearer understanding of the current maturity and limitations of AI and ML technologies within the field. By synthesizing the available evidence, this work aims to support more informed, critical appraisal of algorithm‑generated outputs and to help clinicians recognize when such tools may complement rather than replace clinical reasoning. Furthermore, the review outlines priority areas in which rigorous model validation, prospective study designs, bias assessment, and implementation research are essential. Addressing these gaps will be crucial to ensure that future AI‑ and ML‑based tools can transition safely and effectively from experimental settings to practical, patient‑centered clinical application. This study has several limitations. The included studies varied widely in sport, level of play, sample size, data modality, outcomes, and performance metrics which did not allow for a quantitative synthesis and limits comparison across models. Therefore, it was determined to synthesize narratively to emphasize patterns rather than pool effects. In addition, due to the heterogeneity of included studies, no risk of bias or quality assessment was performed. Moreover, the predominance of internal validation limits the generalizability of findings. Thus, results must be interpreted cautiously. Furthermore, publication bias might skew the picture of the accurate results of included studies, and true performance of AI models might not be captured. Given the rapid growth of this field, relevant studies may have been published after our search and were therefore not captured. Engineering-led studies focused solely on algorithmic development were excluded; therefore, the technical foundation of AI methods may be underrepresented. To organize this heterogeneous literature, AI applications were pragmatically grouped into four mutually exclusive categories. While this approach facilitates synthesis, it simplifies the inherently multidimensional nature of AI systems, which often vary substantially in data sources, modelling approaches, and validation strategies within the same clinical task. Accordingly, the categories should be interpreted as heuristic groupings to support interpretation rather than rigid distinctions between fundamentally different AI methodologies. Conclusion The use of AI applications in sports medicine demonstrate strong within-sample discriminative performance for injury risk, recovery, and diagnostic imaging, yet most remain limited to retrospective analysis with limited external validation and minimal evidence of clinical workflow integration. This review shows that the field is characterized by substantial methodological heterogeneity and limited progression toward prospective implementation. For clinicians within sports medicine, current AI tools should therefore be regarded as exploratory decision-support adjuncts rather than implementation-ready systems. Declarations Competing Interests Author Kristian Samuelsson reports a relationship with Getinge AB that includes: board membership. No other competing interests to declare. Conflict of interest disclosure Author Kristian Samuelsson reports a relationship with Getinge AB that includes: board membership. No other competing interests to declare. Ethics statement Ethical approval was not required for this study as it involved the analysis of previously published literature Funding statement This research received no specific grant from any funding agency in the public, commercial, or not-for-profit sectors. Author Contribution Jakob Lindskog drafted the initial version of the manuscript, performed screening and synthesis of data, has approved the final work for publication, and has agreed to be accountable for all aspects of the work.Kristian Heder Ternell has contributed majorly during the drafting of the manuscript, performed screening and synthesis of data, has approved the final work for publication, and has agreed to be accountable for all aspects of the work.Yinan Yu, Ida Lindman and Kristian Samuelsson have contributed during the interpretation of data, made meaningful contributions during the final stages of manuscript drafting, has approved the final work, and has agreed to be accountable for all aspects of the work.Eric Hamrin Senorski has contributed majorly during the drafting of the manuscript, analysis and interpretation of data, is responsible for the design concept, has approved the final work, and has agreed to be accountable for all aspects of the work. Acknowledgement The authors thank librarians Kajsa Magnusson and Ann Liljegren for valuable advice and performing of the literature searches. The authors also thank librarian Ida Stadig for her assistance in developing the AI-related search strategy. All librarians are affiliated with the Medical Library, Sahlgrenska University Hospital. Data Availability This scoping review is based on previously published studies. The data-charting spreadsheet generated during the review is available from the corresponding author on reasonable request. References Aung YYM, Wong DCS, Ting DSW. The promise of artificial intelligence: a review of the opportunities and challenges of artificial intelligence in healthcare. Br Med Bull. 2021;139:4–15. https://doi.org/10.1093/bmb/ldab016 . Tu SJ, et al. Machine learning is better than surgeons at assessing unicompartmental knee replacement radiographs. Knee. 2024;52:212–9. https://doi.org/10.1016/j.knee.2024.11.007 . Goh E et al. Large Language Model Influence on Diagnostic Reasoning: A Randomized Clinical Trial. JAMA Netw Open 7, e2440969 (2024) https://doi.org/10.1001/jamanetworkopen.2024.40969 Wallace MB, et al. Impact of Artificial Intelligence on Miss Rate of Colorectal Neoplasia. Gastroenterology. 2022;163:295–304. https://doi.org/10.1053/j.gastro.2022.03.007 . .e295. Hu W, Razmjooy S. Combining an improved political optimizer with convolutional neural networks for accurate anterior cruciate ligament tear detection in sports injuries. Sci Rep. 2025;15:6862. https://doi.org/10.1038/s41598-025-91242-2 . Allen JH, et al. Predicting early versus late recovery from sport-related concussion using decision tree analysis. J Neurosurg Pediatr. 2023;32:9–18. https://doi.org/10.3171/2023.2.Peds2330 . Diniz P, et al. Pre-injury performance is most important for predicting the level of match participation after Achilles tendon ruptures in elite soccer players: a study using a machine learning classifier. Knee Surg Sports Traumatol Arthrosc. 2022;30:4225–37. https://doi.org/10.1007/s00167-022-07082-4 . Tricco AC, et al. PRISMA Extension for Scoping Reviews (PRISMA-ScR): Checklist and Explanation. Ann Intern Med. 2018;169:467–73. https://doi.org/10.7326/m18-0850 . McGowan J, PRESS Peer Review of Electronic Search Strategies, et al. 2015 Guideline Statement. J Clin Epidemiol. 2016;75:40–6. 10.1016/j.jclinepi.2016.01.021 . https://doi.org/https://doi.org/ . Ouzzani M, Hammady H, Fedorowicz Z, Elmagarmid A. Rayyan-a web and mobile app for systematic reviews. Syst Rev. 2016;5:210. https://doi.org/10.1186/s13643-016-0384-4 . Hopkinson M, et al. Rugby league ball carrier injuries: The relative importance of tackle characteristics during the European Super League. Eur J Sport Sci. 2022;22:269–78. https://doi.org/10.1080/17461391.2020.1853817 . Hwang UJ, Kim JS, Chung KS. Machine Learning Predictions of Subjective Function, Symptoms, and Psychological Readiness at 12 Months After ACL Reconstruction Based on Physical Performance in the Early Rehabilitation Stage: Retrospective Cohort Study. Orthop J Sports Med. 2025;13:23259671251319512. https://doi.org/10.1177/23259671251319512 . Lu Y, et al. Machine Learning for Predicting Lower Extremity Muscle Strain in National Basketball Association Athletes. Orthop J Sports Med. 2022;10:23259671221111742. https://doi.org/10.1177/23259671221111742 . Martínez-Gramage J, et al. A Random Forest Machine Learning Framework to Reduce Running Injuries in Young Triathletes. Sens (Basel). 2020;20. https://doi.org/10.3390/s20216388 . Rommers N, et al. A Machine Learning Approach to Assess Injury Risk in Elite Youth Football Players. Med Sci Sports Exerc. 2020;52:1745–51. https://doi.org/10.1249/mss.0000000000002305 . Guo L, Cui Z, Loh WP, Shaharudin S. Prediction of ACL injury incidence and analysis of key features in basketball players based on multi-algorithm models. Peerj 13, e20141 (2025) https://doi.org/https://doi.org/10.7717/peerj.20141 Hwang UJ, Kim JS, Kim KY, Chung KS. Machine learning models for predicting return to sports after anterior cruciate ligament reconstruction: Physical performance in early rehabilitation. Digit Health. 2024;10:20552076241299065. https://doi.org/10.1177/20552076241299065 . Nolte K, Gerharz A, Jaitner T, Knicker AJ, Alt T. Finding the needle in the haystack of isokinetic knee data: Random Forest modelling improves information about ACLR-related deficiencies. J Sports Sci. 2025;43:173–81. https://doi.org/10.1080/02640414.2024.2435729 . Chu Y, et al. Machine learning to predict sports-related concussion recovery using clinical data. Ann Phys Rehabil Med. 2022;65:101626. https://doi.org/10.1016/j.rehab.2021.101626 . Ferris LM et al. Predictive Accuracy of the Sport Concussion Assessment Tool 3 and Vestibular/Ocular-Motor Screening, Individually and In Combination: A National Collegiate Athletic Association-Department of Defense Concussion Assessment, Research and Education Consortium Analysis. Am J Sports Med 49, 1040–1048 (2021) https://doi.org/10.1177/0363546520988098 Jacob D, et al. Towards defining biomarkers to evaluate concussions using virtual reality and a moving platform (BioVRSea). Sci Rep. 2022;12:8996. https://doi.org/10.1038/s41598-022-12822-0 . Maxin AJ, Whelan BM, Levitt MR, McGrath LB, Harmon KG. Smartphone-Based Pupillometry Using Machine Learning for the Diagnosis of Sports-Related Concussion. Diagnostics (Basel). 2024;14(23):2723. https://doi.org/https://doi.org/10.3390/diagnostics14232723 . (no pagination). Thanjavur K, Hristopulos DT, Babul A, Yi KM, Virji-Babul ND. Learning Recurrent Neural Network for Concussion Classification in Adolescents Using Raw Electroencephalography Signals: Toward a Minimal Number of Sensors. Front Hum Neurosci. 2021;15:734501. https://doi.org/10.3389/fnhum.2021.734501 . Richter C, et al. Cross-validation of a machine learning algorithm that determines anterior cruciate ligament rehabilitation status and evaluation of its ability to predict future injury. Sports Biomech. 2023;22:91–101. https://doi.org/10.1080/14763141.2021.1947358 . Wang Y, Lee S. Development and validation of a machine learning model for non-contact injury prediction based on lower limb strength asymmetry in professional football. Sci. 2026;16:4456. https://doi.org/10.1038/s41598-025-34468-4 . https://doi.org/. Nose-Ogura S, et al. Development and validation of a pre-screening tool for early detection of low bone mineral density in female athletes (PreST-LBMD). Phys Sports Med. 2025. https://doi.org/https://doi.org/10.1080/00913847.2025.2586448 . Dandrieux PE, et al. Association between the use of daily injury risk estimation feedback (I-REF) based on machine learning techniques and injuries in athletics (track and field): results of a prospective cohort study over an athletics season. BMJ Open Sport Exerc Med. 2025;11:e002331. https://doi.org/10.1136/bmjsem-2024-002331 . Zhu T, et al. Evaluation of the Efficacy of an Artificial Intelligence-Based Assessment and Correction System in the Rehabilitation of Patients Following Anterior Cruciate Ligament Reconstruction Surgery. J. 2026;15:10. https://doi.org/https://doi.org/10.3390/jcm15020575 . Song B, Tuo PX. Application of Artificial Intelligence and Virtual Reality Technology in the Rehabilitation Training of Track and Field Athletes. Wirel Commun Mob Comput 2022, (2022) https://doi.org/https://doi.org/10.1155/2022/9828199 Abasi A, Nazari A, Moezy A, Fatemi Aghda. SA Machine learning models for reinjury risk prediction using cardiopulmonary exercise testing (CPET) data: optimizing athlete recovery. BioData Min. 2025;18:16. https://doi.org/10.1186/s13040-025-00431-2 . Aoyagi M et al. Identifying Acute Lumbar Spondylolysis in Young Athletes with Low Back Pain: Retrospective Classification and Regression Tree Analysis. Spine (Phila Pa 1976) 46, 1026–1032 (2021) https://doi.org/10.1097/brs.0000000000003922 Ayala F, et al. A Preventive Model for Hamstring Injuries in Professional Soccer: Learning Algorithms. Int J Sports Med. 2019;40:344–53. https://doi.org/10.1055/a-0826-1955 . Bazarian JJ et al. Validation of a Machine Learning Brain Electrical Activity-Based Index to Aid in Diagnosing Concussion Among Athletes. JAMA Netw Open 4, e2037349 (2021) https://doi.org/10.1001/jamanetworkopen.2020.37349 Bergeron MF, et al. Machine Learning in Modeling High School Sport Concussion Symptom Resolve. Med Sci Sports Exerc. 2019;51:1362–71. https://doi.org/10.1249/mss.0000000000001903 . Briand J, Deguire S, Gaudet S, Bieuzen F. Monitoring Variables Influence on Random Forest Models to Forecast Injuries in Short-Track Speed Skating. Front Sports Act Living. 2022;4:896828. https://doi.org/10.3389/fspor.2022.896828 . Calderón-Díaz M, et al. Explainable Machine Learning Techniques to Predict Muscle Injuries in Professional Soccer Players through Biomechanical Analysis. Sens (Basel). 2023;24. https://doi.org/10.3390/s24010119 . Cao C, Tutwiler RL, Slobounov S. Automatic classification of athletes with residual functional deficits following concussion by means of EEG signal using support vector machine. IEEE Trans Neural Syst Rehabil Eng. 2008;16:327–35. https://doi.org/10.1109/tnsre.2008.918422 . Castellanos J, et al. Predicting Risk of Sport-Related Concussion in Collegiate Athletes and Military Cadets: A Machine Learning Approach Using Baseline Data from the CARE Consortium Study. Sports Med. 2021;51:567–79. https://doi.org/10.1007/s40279-020-01390-w . Chen X, Liu YA, Classification. Method for Thoracolumbar Vertebral Fractures due to Basketball Sports Injury Based on Deep Learning. Comput Math Methods Med 2022, 8747487 (2022) https://doi.org/10.1155/2022/8747487 De la Fuente C, et al. Preseason multiple biomechanics testing and dimension reduction for injury risk surveillance in elite female soccer athletes: short-communication. Sci Med Footb. 2023;7:183–8. https://doi.org/10.1080/24733938.2022.2075558 . de Leeuw AW, van der Zwaard S, van Baar R. Knobbe A Personalized machine learning approach to injury monitoring in elite volleyball players. Eur J Sport Sci. 2022;22:511–20. https://doi.org/10.1080/17461391.2021.1887369 . DiCesare CA, et al. Machine Learning Classification of Verified Head Impact Exposure Strengthens Associations with Brain Changes. Ann Biomed Eng. 2020;48:2772–82. https://doi.org/10.1007/s10439-020-02662-2 . Diniz P, et al. High specificity of an AI-powered framework in cross-checking male professional football anterior cruciate ligament tear reports in public databases. Knee Surg Sports Traumatol Arthrosc. 2025;33:3478–88. https://doi.org/10.1002/ksa.12571 . Elkin PL, et al. Artificial Intelligence: Bayesian versus Heuristic Method for Diagnostic Decision Support. Appl Clin Inf. 2018;9:432–9. /https://doi.org/10.1055/s-0038-1656547 . https://doi.org. Eskofier BM, Kraus M, Worobets JT, Stefanyshyn DJ, Nigg BM. Pattern classification of kinematic and kinetic running data to distinguish gender, shod/barefoot and injury groups with feature ranking. Comput Methods Biomech Biomed Engin. 2012;15:467–74. https://doi.org/10.1080/10255842.2010.542153 . Evans SL, et al. Non-contact lower limb injuries in Rugby Union: A two-year pattern recognition analysis of injury risk factors. PLoS ONE. 2024;19:e0307287. https://doi.org/10.1371/journal.pone.0307287 . Farhadian M, Torkaman S, Mojarad F. Random forest algorithm to identify factors associated with sports-related dental injuries in 6 to 13-year-old athlete children in Hamadan, Iran-2018 -a cross-sectional study. BMC Sports Sci Med Rehabil. 2020;12:69. https://doi.org/10.1186/s13102-020-00217-5 . Freitas DN, et al. Predicting noncontact injuries of professional football players using machine learning. PLoS ONE. 2025;20:e0315481. https://doi.org/10.1371/journal.pone.0315481 . Garcia GP, et al. A Data-Driven Approach to Unlikely, Possible, Probable, and Definite Acute Concussion Assessment. J Neurotrauma. 2019;36:1571–83. https://doi.org/10.1089/neu.2018.6098 . Gaudet S, Begon M, Tremblay J. Cluster analysis using physical performance and self-report measures to identify shoulder injury in overhead female athletes. J Sci Med Sport. 2019;22:269–74. https://doi.org/10.1016/j.jsams.2018.09.224 . Giorgino R, et al. Google Bard and ChatGPT in Orthopedics: Which Is the Better Doctor in Sports Medicine and Pediatric Orthopedics? The Role of AI in Patient Education. Diagnostics (Basel). 2024;14. https://doi.org/10.3390/diagnostics14121253 . Girard CI, et al. Classifiers of anterior cruciate ligament status in female and male adolescents using return-to-activity criteria. Knee Surg Sports Traumatol Arthrosc. 2025;33:1633–44. https://doi.org/https://doi.org/10.1002/ksa.12462 . Goggins L, et al. Detecting Injury Risk Factors with Algorithmic Models in Elite Women's Pathway Cricket. Int J Sports Med. 2022;43:344–9. https://doi.org/10.1055/a-1502-6824 . Gultekin O, et al. Evaluating DeepResearch and DeepThink in anterior cruciate ligament surgery patient education: ChatGPT-4o excels in comprehensiveness, DeepSeek R1 leads in clarity and readability of orthopaedic information. Knee Surg Sports Traumatol Arthrosc. 2025;33:3025–31. https://doi.org/https://doi.org/10.1002/ksa.12711 . Hecksteden A, et al. Forecasting football injuries by combining screening, monitoring and machine learning. Sci Med Footb. 2023;7:214–28. /https://doi.org/10.1080/24733938.2022.2095006 . https://doi.org. Henriquez M, Sumner J, Faherty M, Sell T, Bent B. Machine Learning to Predict Lower Extremity Musculoskeletal Injury Risk in Student Athletes. Front Sports Act Living. 2020;2:576655. https://doi.org/10.3389/fspor.2020.576655 . Hsu PY, Hsu YC, Liu HL, Fong Kao W, Lin KY. An Acute Kidney Injury Prediction Model for 24-hour Ultramarathon Runners. J Hum Kinet. 2022;84:103–11. https://doi.org/10.2478/hukin-2022-0070 . Huang Y, et al. A novel lower extremity non-contact injury risk prediction model based on multimodal fusion and interpretable machine learning. Front Physiol. 2022;13:937546. https://doi.org/10.3389/fphys.2022.937546 . Huang Y, et al. The impact of sport-specific physical fitness change patterns on lower limb non-contact injury risk in youth female basketball players: a pilot study based on field testing and machine learning. Front Physiol. 2023;14:1182755. https://doi.org/10.3389/fphys.2023.1182755 . Jauhiainen S, et al. Predicting ACL Injury Using Machine Learning on Data From an Extensive Screening Test Battery of 880 Female Elite Athletes. Am J Sports Med. 2022;50:2917–24. https://doi.org/10.1177/03635465221112095 . Jauhiainen S, et al. New Machine Learning Approach for Detection of Injury Risk Factors in Young Team Sport Athletes. Int J Sports Med. 2021;42:175–82. https://doi.org/10.1055/a-1231-5304 . Jia P, Xu Y, Research on Image Recognition of Gymnastics Sports Injuries Based on Deep Learning. Comput Intell Neurosci 2022, 8987006 (2022) https://doi.org/10.1155/2022/8987006 Karbalaie A, et al. Beyond self-reports after anterior cruciate ligament injury - machine learning methods for classifying and identifying movement patterns related to fear of re-injury. J Sports Sci. 2026;44:342–56. https://doi.org/https://doi.org/10.1080/02640414.2025.2578584 . Kolodziej M, et al. Predictive modeling of lower extremity injury risk in male elite youth soccer players using least absolute shrinkage and selection operator regression. Scand J Med Sci Sports. 2023;33:1021–33. https://doi.org/10.1111/sms.14322 . Kunze KN, et al. Machine Learning Algorithms Predict Functional Improvement After Hip Arthroscopy for Femoroacetabular Impingement Syndrome in Athletes. J Bone Joint Surg Am. 2021;103:1055–62. https://doi.org/10.2106/jbjs.20.01640 . Kunze KN, et al. Application of Machine Learning Algorithms to Predict Clinically Meaningful Improvement After Arthroscopic Anterior Cruciate Ligament Reconstruction. Orthop J Sports Med. 2021;9:23259671211046575. https://doi.org/10.1177/23259671211046575 . Lipps Lene C, Frere J, Weissland T. Machine learning in knee injury sequelae detection: Unravelling the role of psychological factors and preventing long-term sequelae. J Exp Orthop. 2024;11:e70081. https://doi.org/10.1002/jeo2.70081 . López-Valenciano A, et al. A Preventive Model for Muscle Injuries: A Novel Approach based on Learning Algorithms. Med Sci Sports Exerc. 2018;50:915–27. https://doi.org/10.1249/mss.0000000000001535 . Lövdal SS, Den Hartigh RJR, Azzopardi G. Injury Prediction in Competitive Runners With Machine Learning. Int J Sports Physiol Perform. 2021;16:1522–31. https://doi.org/10.1123/ijspp.2020-0518 . McBee JC, et al. Assessing ChatGPT's Competency in Addressing Interdisciplinary Inquiries on Chatbot Uses in Sports Rehabilitation: Simulation Study. JMIR Med Educ. 2024;10:e51157. https://doi.org/10.2196/51157 . Murray NG, et al. Single-Task and Dual-Task Gait Performance After Sport-Related Concussion: A Machine Learning Statistical Approach. Sports Health. 2025;17:666–77. https://doi.org/10.1177/19417381241264289 . Nechita LC, et al. A Resting ECG Screening Protocol Improved with Artificial Intelligence for the Early Detection of Cardiovascular Risk in Athletes. Diagnostics (Basel). 2025;15. https://doi.org/10.3390/diagnostics15040477 . Nonnenmacher L, Fischer M, Kaderali L, Wassilew GI. Predicting early return to sport after periacetabular osteotomy: a machine-learning approach. Bone Jt Open. 2025;6:33–42. https://doi.org/10.1302/2633-1462.66.bjo-2024-0257.r1 . https://doi.org/. Ohlsen SM, Pirkle SB, Yang J, Gee AO. Do ChatGPT and Gemini Provide Appropriate Recommendations for Anterior Cruciate Ligament and Isolated Meniscal Injuries? Cureus 17, e94315 (2025) https://doi.org/https://doi.org/10.7759/cureus.94315 Oliver JL, et al. Using machine learning to improve our understanding of injury risk and prediction in elite male youth football players. J Sci Med Sport. 2020;23:1044–8. https://doi.org/10.1016/j.jsams.2020.04.021 . Ozbek EA, et al. ChatGPT Can Offer At Least Satisfactory Responses to Common Patient Questions Regarding Hip Arthroscopy. Arthroscopy. 2025;41:1806–27. 10.1016/j.arthro.2024.08.036 . https://doi.org/https://doi.org/ . Pérez-Contreras J, et al. Are Countermovement Jump Variables Indicators of Injury Risk in Professional Soccer Players? A Machine Learning Approach. Appl Sci-Basel. 2025;15. https://doi.org/https://doi.org/10.3390/app152312721 . Piłka T, Grzelak B, Sadurska A, Górecki T, Dyczkowski K. Predicting Injuries in Football Based on Data Collected from GPS-Based Wearable Sensors. Sens (Basel). 2023;23. https://doi.org/10.3390/s23031227 . Quinn M et al. Artificial Intelligence Large Language Models Address Anterior Cruciate Ligament Reconstruction: Superior Clarity and Completeness by Gemini Compared With ChatGPT-4 in Response to American Academy of Orthopaedic Surgeons Clinical Practice Guidelines. Arthroscopy 41, 2002–2008 (2025) https://doi.org/10.1016/j.arthro.2024.09.020 Rossi A, Pappalardo L, Filetti C, Cintia P. Blood sample profile helps to injury forecasting in elite soccer players. Sport Sci Health. 2023;19:285–96. https://doi.org/10.1007/s11332-022-00932-1 . https://doi.org/. Robinson M, Johnson AM, Fischer LK. MacKenzie HM Two Symptoms to Triage Acute Concussions: Using Decision Tree Modeling to Predict Prolonged Recovery After a Concussion. Am J Phys Med Rehabil. 2022;101:135–8. https://doi.org/10.1097/phm.0000000000001754 . Ruddy JD, et al. Predictive Modeling of Hamstring Strain Injuries in Elite Australian Footballers. Med Sci Sports Exerc. 2018;50:906–14. https://doi.org/10.1249/mss.0000000000001527 . Ruiz-Pérez I, et al. A Field-Based Approach to Determine Soft Tissue Injury Risk in Elite Futsal Using Novel Machine Learning Techniques. Front Psychol. 2021;12:610210. https://doi.org/10.3389/fpsyg.2021.610210 . Saghafi B, et al. Quantifying the Association between White Matter Integrity Changes and Subconcussive Head Impact Exposure from a Single Season of Youth and High School Football using 3D Convolutional Neural Networks. Proc SPIE Int Soc Opt Eng. 2018;10575. https://doi.org/10.1117/12.2293023 . Saglam S, et al. Comparative evaluation of artificial intelligence models GPT-4 and GPT-3.5 in clinical decision-making in sports surgery and physiotherapy: a cross-sectional study. BMC Med Inf Decis Mak. 2025;25:163. https://doi.org/https://doi.org/10.1186/s12911-025-02996-8 . Schulc A, et al. Identifying Anterior Cruciate Ligament Injuries Through Automated Video Analysis of In-Game Motion Patterns. Orthop J Sports Med. 2024;12:23259671231221579. https://doi.org/10.1177/23259671231221579 . Shibata Y, et al. Prediction of quadriceps strength recovery after anterior cruciate ligament reconstruction with a hamstring autograft: Decision tree analysis. J Orthop Sci. 2019;24:301–5. https://doi.org/10.1016/j.jos.2018.10.007 . https://doi.org/. Sparks CA, et al. ChatGPT Is Moderately Accurate in Providing a General Overview of Orthopaedic Conditions. JB JS Open Access. 2024;9. https://doi.org/10.2106/jbjs.Oa.23.00129 . Stirling CE, Pavlovic N, Manske SL, Walker REA, Boyd SK. Longitudinal Progression of Traumatic Bone Marrow Lesions Following Anterior Cruciate Ligament Injury: Associations With Knee Pain and Concomitant Injuries. J Orthop Res. 2025;43:2178–87. https://doi.org/https://doi.org/10.1002/jor.70067 . Tamez-Peña J, et al. Post-concussive mTBI in Student Athletes: MRI Features and Machine Learning. Front Neurol. 2021;12:734329. https://doi.org/10.3389/fneur.2021.734329 . Tedesco S, et al. Motion Sensors-Based Machine Learning Approach for the Identification of Anterior Cruciate Ligament Gait Patterns in On-the-Field Activities in Rugby Players. Sens (Basel). 2020;20. https://doi.org/10.3390/s20113029 . Tsilimigkras T, Kakkos I, Matsopoulos GK, Bogdanis GC. Enhancing Sports Injury Risk Assessment in Soccer Through Machine Learning and Training Load Analysis. J Sports Sci Med. 2024;23:537–47. https://doi.org/10.52082/jssm.2024.537 . Usami S, et al. A new neural network model that detects graft ruptures and contralateral anterior cruciate ligament injuries. Knee Surg Sports Traumatol Arthrosc. 2024;32:872–80. https://doi.org/10.1002/ksa.12123 . Vallance E, Sutton-Charani N, Imoussaten A, Montmain J, Perrey S. Combining Internal- and External-Training-Loads to Predict Non-Contact Injuries in Soccer. Appl Sci-Basel. 2020;10. https://doi.org/https://doi.org/10.3390/app10155261 . Valle X, et al. Return to Play Prediction Accuracy of the MLG-R Classification System for Hamstring Injuries in Football Players: A Machine Learning Approach. Sports Med. 2022;52:2271–82. https://doi.org/10.1007/s40279-022-01672-5 . Villarreal-Espinosa JB, et al. Accuracy assessment of ChatGPT responses to frequently asked questions regarding anterior cruciate ligament surgery. Knee. 2024;51:84–92. https://doi.org/10.1016/j.knee.2024.08.014 . Weng YH, Chang PH, Wu KP, Lin JJ, Huang TS. Enhanced personalized prediction of baseball-related upper extremity injuries through novel features and explainable artificial intelligence. J Sports Sci. 2025;43:719–27. https://doi.org/10.1080/02640414.2025.2474328 . Yates LC, et al. Developing a multivariate model for the prediction of concussion recovery in sportspeople: a machine learning approach. BMJ Open Sport Exerc Med. 2025;11:e002090. https://doi.org/10.1136/bmjsem-2024-002090 . Ye X, Huang Y, Bai Z, Wang Y. A novel approach for sports injury risk prediction: based on time-series image encoding and deep learning. Front Physiol. 2023;14:1174525. https://doi.org/10.3389/fphys.2023.1174525 . Yüce A, Erkurt N, Yerli M, Misir A. The Potential of ChatGPT for High-Quality Information in Patient Education for Sports Surgery. Cureus 16, e58874 (2024) https://doi.org/10.7759/cureus.58874 Zhan H et al. Machine-Learning Models Reliably Predict Clinical Outcomes in Medial Patellofemoral Ligament Reconstruction. Arthroscopy 41, 1896–1908.e1892 (2025) https://doi.org/10.1016/j.arthro.2024.07.028 Zhan X, et al. Machine-learning-based head impact subtyping based on the spectral densities of the measurable head kinematics. J Sport Health Sci. 2023;12:619–29. https://doi.org/10.1016/j.jshs.2023.03.003 . Zhang H, Zheng H, Deng R, Luo K, Duan S. Computed Tomography Imaging under Artificial Intelligence Reconstruction Algorithm Used in Recovery of Sports Injury of the Knee Anterior Cruciate Ligament. Contrast Media Mol Imaging 2022, 1199841 (2022) https://doi.org/10.1155/2022/1199841 Zhu T, et al. Alterations of urinary proteomic profiles are correlated with return to sport after anterior cruciate ligament reconstruction. BMC Sports Sci Med Rehabil. 2026;10. https://doi.org/10.1186/s13102-025-01527-2 . https://doi.org/. Moons KGM et al. PROBAST + AI: an updated quality, risk of bias, and applicability assessment tool for prediction models using regression or artificial intelligence methods. Bmj 388, e082505 (2025) https://doi.org/10.1136/bmj-2024-082505 Bahr R, Krosshaug T. Understanding injury mechanisms: a key component of preventing injuries in sport. Br J Sports Med. 2005;39:324–9. https://doi.org/10.1136/bjsm.2005.018341 . Bittencourt NFN, et al. Complex systems approach for sports injuries: moving from risk factor identification to injury pattern recognition-narrative review and new concept. Br J Sports Med. 2016;50:1309–14. https://doi.org/10.1136/bjsports-2015-095850 . Tonekaboni S, Joshi S, McCradden MD, Goldenberg A, editors. What clinicians want: contextualizing explainable machine learning for clinical end use. Machine learning for healthcare conference; 2019: PMLR. Ghassemi M, Oakden-Rayner L, Beam AL. The false hope of current approaches to explainable artificial intelligence in health care. Lancet Digit Health. 2021;3:e745–50. https://doi.org/10.1016/s2589-7500(21)00208-9 . Van Tiggelen D, Wickes S, Stevens V, Roosen P, Witvrouw E. Effective prevention of sports injuries: a model integrating efficacy, efficiency, compliance and risk-taking behaviour. Br J Sports Med. 2008;42:648–52. https://doi.org/10.1136/bjsm.2008.046441 . Guo Z, et al. Large Language Models for Mental Health Applications: Systematic Review. JMIR Ment Health. 2024;11:e57400. https://doi.org/10.2196/57400 . Farhat F, ChatGPT as a Complementary Mental Health Resource. A Boon or a Bane. Ann Biomed Eng. 2024;52:1111–4. https://doi.org/10.1007/s10439-023-03326-7 . Zech JR, et al. Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: A cross-sectional study. PLoS Med. 2018;15:e1002683. https://doi.org/10.1371/journal.pmed.1002683 . Litjens G, et al. A survey on deep learning in medical image analysis. Med Image Anal. 2017;42:60–88. https://doi.org/10.1016/j.media.2017.07.005 . Moassefi M, et al. Reproducibility of Deep Learning Algorithms Developed for Medical Imaging Analysis: A Systematic Review. J Digit Imaging. 2023;36:2306–12. https://doi.org/10.1007/s10278-023-00870-5 . Wolpert DH, Macready WG. No free lunch theorems for optimization. IEEE Trans Evol Comput. 1997;1:67–82. https://doi.org/10.1109/4235.585893 . D'Amour A, et al. Underspecification presents challenges for credibility in modern machine learning. J Mach Learn Res. 2022;23:1–61. Additional Declarations Competing interest reported. Author Kristian Samuelsson reports a relationship with Getinge AB that includes: board membership. No other competing interests to declare. Supplementary Files Supplimentaryinformation.docx Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 20 Apr, 2026 Reviews received at journal 20 Apr, 2026 Reviews received at journal 15 Apr, 2026 Reviewers agreed at journal 05 Apr, 2026 Reviewers agreed at journal 04 Apr, 2026 Reviewers invited by journal 04 Apr, 2026 Editor invited by journal 03 Apr, 2026 Editor assigned by journal 31 Mar, 2026 Submission checks completed at journal 31 Mar, 2026 First submitted to journal 29 Mar, 2026 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-9259496","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":620702806,"identity":"e22c01fb-c26d-4477-81a4-0264998d864f","order_by":0,"name":"Jakob Lindskog","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8ElEQVRIie3QPQrCMBiA4a8U2iU6VxS8QkrAH5D2Ki2BdnFwdOxkl2LX9hYeIVDQRXQVuigBXRw6ijgY0Q4u0VEw75CQ4SFfAqBS/WBaZIAOMEAAnthh9DWxahJ8c8+TwIsUn4EeL30+AavTN0OOq+vWWTDzsJcOlgQFycRgw+RM/Hxe0gVDBMvfEs7aSBC8G+tFIykpZsiwpCQ91STkgmwEMU8XKcmC5Yt4hKILczCDnkwIcqQkw4Ksz8TOI+q1CkSkg9lpYPPJdOTiVcit6ua4zVV8qKQkeqz1D2kz8CNdOhZA9/14A/cDUKlUqj/sDqUoSB6m+uroAAAAAElFTkSuQmCC","orcid":"","institution":"University of Gothenburg","correspondingAuthor":true,"prefix":"","firstName":"Jakob","middleName":"","lastName":"Lindskog","suffix":""},{"id":620702807,"identity":"5dba887c-dc60-4a90-8aee-b46a4abfe874","order_by":1,"name":"Kristian Heder Ternell","email":"","orcid":"","institution":"University of Gothenburg","correspondingAuthor":false,"prefix":"","firstName":"Kristian","middleName":"Heder","lastName":"Ternell","suffix":""},{"id":620702808,"identity":"7d96ba6e-4cc5-43ba-98c7-42aed225650d","order_by":2,"name":"Yinan Yu","email":"","orcid":"","institution":"Chalmers University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Yinan","middleName":"","lastName":"Yu","suffix":""},{"id":620702810,"identity":"32dc36c3-4927-4f1d-960d-097d4d3be280","order_by":3,"name":"Ida Lindman","email":"","orcid":"","institution":"University of Gothenburg","correspondingAuthor":false,"prefix":"","firstName":"Ida","middleName":"","lastName":"Lindman","suffix":""},{"id":620702812,"identity":"3fd401c9-3381-4d6e-b685-733954be503c","order_by":4,"name":"Kristian Samuelsson","email":"","orcid":"","institution":"University of Gothenburg","correspondingAuthor":false,"prefix":"","firstName":"Kristian","middleName":"","lastName":"Samuelsson","suffix":""},{"id":620702813,"identity":"83cb052d-c21f-4ae2-837d-76604338fb8f","order_by":5,"name":"Eric Hamrin Senorski","email":"","orcid":"","institution":"University of Gothenburg","correspondingAuthor":false,"prefix":"","firstName":"Eric","middleName":"Hamrin","lastName":"Senorski","suffix":""}],"badges":[],"createdAt":"2026-03-29 14:38:32","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9259496/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9259496/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106836212,"identity":"42ba0a3c-1aa9-4d16-afdc-c76717132aac","added_by":"auto","created_at":"2026-04-14 02:07:05","extension":"jpg","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":114676,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cem\u003ePRISMA flowchart for the inclusion process. AI = Artificial intelligence, ML = Machine learning, n = number\u003c/em\u003e\u003c/p\u003e","description":"","filename":"Figure1PRISMAFlowchart.jpg","url":"https://assets-eu.researchsquare.com/files/rs-9259496/v1/197c4e39f73b1c7a15dc84ee.jpg"},{"id":106836214,"identity":"50a253d8-49a7-45e9-acf4-75b420f148f4","added_by":"auto","created_at":"2026-04-14 02:07:06","extension":"jpg","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":31755,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cem\u003eAnnual distribution of published studies. For year 2026, only publications up until 5 of February were included.\u003c/em\u003e\u003c/p\u003e","description":"","filename":"Figure2Yearsofpublication.jpg","url":"https://assets-eu.researchsquare.com/files/rs-9259496/v1/9a00bc1b7da553996adc895e.jpg"},{"id":106963108,"identity":"88606c6b-264d-4f7d-987c-206b0c239662","added_by":"auto","created_at":"2026-04-15 09:42:10","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2281227,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9259496/v1/f1ee1847-cbe1-4d88-a1a4-719814b3bdff.pdf"},{"id":106960813,"identity":"dcaf6542-77b0-49c2-a6c1-27716c24364c","added_by":"auto","created_at":"2026-04-15 09:23:14","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":52664,"visible":true,"origin":"","legend":"","description":"","filename":"Supplimentaryinformation.docx","url":"https://assets-eu.researchsquare.com/files/rs-9259496/v1/c7fe8844b98e1d8d9b75278c.docx"}],"financialInterests":"Competing interest reported. Author Kristian Samuelsson reports a relationship with Getinge AB that includes: board membership. No other competing interests to declare.","formattedTitle":"Artificial Intelligence and Machine Learning in Sports Medicine: Mapping clinical tasks and assessing clinical maturity - a scoping review","fulltext":[{"header":"Introduction","content":"\u003cp\u003eArtificial intelligence (AI) and machine learning (ML) are transforming healthcare by enabling machines to effectively analyze data, recognize patterns, and aid decision-making [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. There is research that suggests that AI and ML might outperform humans within specific healthcare domains [\u003cspan additionalcitationids=\"CR3\" citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]. For example, ML models have, based on radiographic analysis, identified patients at risk for poor outcomes after unicompartmental knee replacement with greater accuracy than surgeons [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. Similarly, chatbots powered by large language models (LLMs) have in one study surpassed physicians in diagnostic accuracy [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]. Furthermore, AI has reduced the miss rate for colorectal neoplasia detection by half [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]. These examples highlight the potential and increasing role of AI and ML in improving healthcare outcomes.\u003c/p\u003e \u003cp\u003eWithin sports medicine, AI and ML applications have attracted considerable interest. For example, Hu et al. [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e] demonstrated that the use of a convolutional neural network (CNN) could detect anterior cruciate ligament (ACL) injury through magnetic resonance imaging (MRI) with an accuracy of 96.5%. Furthermore, Allen et al. [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e] reported that a decision tree model could discriminate between early, typical and delayed recovery after sports-related concussion (SRC). Moreover, an extreme gradient boosting (XGBoost) model was used to predict level of match participation in football athletes after Achilles tendon rupture [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e]. These studies showcase the potential of AI and ML in sports medicine. However, the literature remains fragmented, with limited understanding of how applications vary across fields and whether current work has progressed beyond retrospective analyses toward prospective or interventional use. Furthermore, it remains unclear whether existing AI and ML applications have reached sufficient developmental and clinical maturity to inform decision-making in sports medicine.\u003c/p\u003e \u003cp\u003eThe aim of this review was to outline the current scientific state of AI and ML application in sports medicine, evaluate the developmental and clinical maturity, and identify key priorities to guide future advancements and implementation.\u003c/p\u003e"},{"header":"Method","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003eProtocol and registration\u003c/h2\u003e \u003cp\u003eAs this was conducted as a scoping review with the purpose to map a rapidly growing field a formal review protocol was not considered needed.\u003c/p\u003e \u003c/div\u003e\n\u003ch3\u003eEligibility criteria\u003c/h3\u003e\n\u003cp\u003eTo be included in this review, papers needed to be written in English, published year 2000 or later, and were required to report on the use of AI or ML within the context of sports medicine. Peer-reviewed papers on all levels of evidence in accordance with the Oxford classification were included. All empirical study designs, including quantitative, qualitative, mixed-methods, case studies, and pilot studies, were considered with no restrictions with regards to cohort size or patient characteristics. Reviews, conference abstracts, commentaries (editorials, opinion pieces), system proposals (frameworks, protocols, datasets), articles without full-text availability, and pre-prints were excluded. System proposals were excluded, as the scope of this review was limited to studies that investigated the application of AI/ML within sports medicine.\u003c/p\u003e\n\u003ch3\u003eInformation sources\u003c/h3\u003e\n\u003cp\u003eThis study was conducted and presented in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR) checklist [\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]. A scoping review approach was performed due to the heterogeneity of AI methods, outcomes, and study designs, which made a quantitative synthesis and detailed risk of bias assessment less feasible. A literature search was planned in collaboration with and was executed out on 2026-02-05 by medical university librarians, with expertise in electronic database searching. The search strategies were peer reviewed by another senior medical university librarian prior to execution in accordance with the PRESS Checklist [\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]. No additional manual searching of references list or grey literature was conducted after the primary database search. The literature search included the MEDLINE, EMBASE, and Web of Science databases, to provide comprehensive coverage of sports medicine research relevant to the clinical scope of this study.\u003c/p\u003e\n\u003ch3\u003eSearch\u003c/h3\u003e\n\u003cp\u003eThe initial search strategy was developed to identify studies which involved the use of AI or ML technologies in the context of sports medicine. The search targeted two core elements. First, the population: Athletes who undergo rehabilitation. Second, the concept: Utilization of AI- or ML-based technologies, tools, or platforms within the treatment process. The broad search strategy was adopted to comprehensively map the diversity of AI and ML applications in sports medicine. The complete search strategy can be found in the Supplementary information.\u003c/p\u003e\n\u003ch3\u003eSelection of sources of evidence\u003c/h3\u003e\n\u003cp\u003eThe screening process was performed with the Rayyan reference management platform (rayyan.ai) [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e]. Screening of studies was performed by two independent reviewers (XX and YY) starting with title and abstract screening followed by full-text evaluation. At all stages, any differences were resolved by mutual agreement. For title and abstract screening, agreement between the authors was assessed with Cohen\u0026rsquo;s Kappa coefficient, calculated to 0.877, which suggests near perfect agreement.\u003c/p\u003e \u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003eData charting process\u003c/h2\u003e \u003cp\u003eDraft data charting tables were developed in Microsoft Excel (Version 16, Microsoft Corporation, Remond, WA, USA) to record extracted data from the included articles, guided by the scoping review research statement. The first two authors (XX and YY) performed the data charting process.\u003c/p\u003e \u003c/div\u003e\n\u003ch3\u003eData items\u003c/h3\u003e\n\u003cp\u003eStudy characteristics extracted included: bibliographic details (author(s), year of publication, and scientific journal), study characteristics (medical field, and country of origin), field of population (sport, sample size, age, study participant sex), AI-/ML application, data sources and input variables, output variables (outcomes), AI-/ML model(s) used, and key findings. Medical field classification was based on the primary clinical focus of each study. Studies were categorized as orthopaedics when the AI or ML application addressed musculoskeletal pathology, surgical outcomes, or rehabilitation related to orthopaedic conditions.\u003c/p\u003e \u003cp\u003eThe AI applications were categorized into four mutually exclusive application groups based on the primary aim of the AI component for each study. This categorization was not based on a single established or universally accepted classification framework, however, was pragmatically developed for the purpose of synthesizing the heterogeneous literature. Categories were defined a priori as follows: 1) Predictive and estimation models, in which algorithms were primarily used to predict outcomes, risks, or clinical parameters; 2) classification and pattern and recognition models, which focused on classification, clustering, feature extraction, or anomaly detection; 3) diagnostic and detection models, which aimed to identify diseases, conditions, or abnormalities; and 4) reasoning and summarization assistance models, where LLMs were central. When a study could plausibly fit more than one category, it was assigned to the group that best reflected the dominant role of the AI component.\u003c/p\u003e\n\u003ch3\u003eCritical appraisal of individual sources of evidence\u003c/h3\u003e\n\u003cp\u003eDue to the exploratory and descriptive nature of scoping reviews, and the heterogeneity of included studies, risk of bias and study quality assessments were not feasible and did not influence scoping review outcomes.\u003c/p\u003e \u003cdiv id=\"Sec11\" class=\"Section2\"\u003e \u003ch2\u003eSynthesis of results\u003c/h2\u003e \u003cp\u003eThe results from the included studies were synthesized descriptively with a narrative approach, supported by tables and figures where appropriate [\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]. Data charted from each study was grouped and summarized in accordance with key themes. These included: medical fields studied, AI-/ML applications, years of publication, study populations, AI-/ML models used in general, with more detailed subgroup analyses performed for orthopaedics and neurology due to the higher number of included studies in these fields, and lastly, the overall model development stage.\u003c/p\u003e \u003cp\u003eNo meta-analysis or quantitative pooling was conducted due to the heterogeneity of study designs, AI/ML approaches, and reported outcomes. Instead, findings were mapped to highlight the breadth of research activity, common areas of application, and gaps in the literature.\u003c/p\u003e \u003c/div\u003e"},{"header":"Results","content":"\u003cp\u003eIn total, 8,677 records were identified, of which 97 were included (Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e). Of the included studies, the medical fields represented were as follows: orthopaedics (n\u0026thinsp;=\u0026thinsp;68, 70.1%), neurology (n\u0026thinsp;=\u0026thinsp;18, 18.6%), radiology (n\u0026thinsp;=\u0026thinsp;3, 3.1%), cardiology and cardiopulmonary (n\u0026thinsp;=\u0026thinsp;2, 2.1%), nephrology (n\u0026thinsp;=\u0026thinsp;1, 1.0%), odontology (n\u0026thinsp;=\u0026thinsp;1, 1.0%), endocrinology (n\u0026thinsp;=\u0026thinsp;1, 1.0%) and various (self-reported participation-restricting injuries [non-diagnosis-specific]; sports rehabilitation and digital health) (n\u0026thinsp;=\u0026thinsp;3, 3.1%) (Table\u0026nbsp;1). Within orthopaedics, AI was primarily applied for injury prediction, outcome estimation, and rehabilitation monitoring, particularly concerning lower-extremity and ACL-related injuries. In neurology, models predominantly focused on SRC management, including classification of SRC severity and prediction of recovery duration. Radiology studies used AI for automated image optimization, detection of ligament injuries and bone marrow lesions, while the remaining medical fields involved isolated applications in injury-risk estimation (cardiopulmonary and cardiology), acute physiological responses (nephrology), dental injury prediction (odontology), and low bone mineral density (endocrinology).\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cdiv id=\"Sec13\" class=\"Section2\"\u003e \u003ch2\u003eAI applications\u003c/h2\u003e \u003cp\u003eThe AI application categories of the included studies were as follows: predictive and estimation models (n\u0026thinsp;=\u0026thinsp;56, 57.7%), classification and pattern recognition models (n\u0026thinsp;=\u0026thinsp;20, 20.6%), diagnostic and detection models (n\u0026thinsp;=\u0026thinsp;11, 11.3%), and reasoning and summarization assistance models (n\u0026thinsp;=\u0026thinsp;10, 10.3%) (Table\u0026nbsp;1). Within orthopaedics, predictive models were most common (43/68, 63.2%), whereas classification models were most common within neurology (9/18, 50.0%). Across AI applications, predictive and estimation models were mainly employed to forecast injury risk (n\u0026thinsp;=\u0026thinsp;34), or recovery-related outcomes (n\u0026thinsp;=\u0026thinsp;15), including return to sport (RTS) probability and functional improvement after orthopaedic injury/surgery. Classification and pattern-recognition models (n\u0026thinsp;=\u0026thinsp;17) were primarily used to distinguish between injured and uninjured states, classify SRC or gait patterns, and identify biomechanical risk clusters. Diagnostic and detection models (n\u0026thinsp;=\u0026thinsp;8) were mainly applied for image- or video-based injury identification, such as ACL or lumbar spine pathology. Reasoning and summarization assistance studies (n\u0026thinsp;=\u0026thinsp;10) exclusively investigated LLM models (ChatGPT, Gemini, Bard, DeepSeek) for patient education and information quality assessment.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec14\" class=\"Section2\"\u003e \u003ch2\u003eAnnual distribution of published studies\u003c/h2\u003e \u003cp\u003eOnly two studies were identified before 2018, while the number increased thereafter, and peaked in 2025 (20 publications, 20.6%) (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e2\u003c/span\u003e and Table\u0026nbsp;1). Of all included studies, 86.6% were published between 2020 and 2026.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec15\" class=\"Section2\"\u003e \u003ch2\u003eFields of population\u003c/h2\u003e \u003cp\u003eThe most common specific fields of population were football (n\u0026thinsp;=\u0026thinsp;25), followed by basketball (n\u0026thinsp;=\u0026thinsp;6), rugby (n\u0026thinsp;=\u0026thinsp;4), handball (n\u0026thinsp;=\u0026thinsp;4), and runner-related populations (n\u0026thinsp;=\u0026thinsp;4). Studies which included mixed athlete populations (n\u0026thinsp;=\u0026thinsp;22) and a combination of athletes and non-athletes (n\u0026thinsp;=\u0026thinsp;10) were also common. Data environments differed by sport: Football and running studies predominantly analyzed global positioning system (GPS)-based workload and accelerometry, whereas basketball, handball, and volleyball more often used laboratory biomechanical tests, balance/fatigue assessments, or physical performance analysis. Rugby studies included video-derived tackle characteristics. Sample sizes ranged from small elite squads to large youth/registry cohorts, with prospective designs typical for load-monitoring studies and cross-sectional designs were common for imaging/electroencephalogram (EEG) tasks. Across sports, female and para-sport cohorts were rarely represented, and only a minority integrated multimodal inputs that combined load, wellness/psychological, and clinical variables.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec16\" class=\"Section2\"\u003e \u003ch2\u003eAI models\u003c/h2\u003e \u003cp\u003eThe five most included models used overall were random forest (RF) (n\u0026thinsp;=\u0026thinsp;29), support vector machine (SVM) (n\u0026thinsp;=\u0026thinsp;27), decision tree (DT) (n\u0026thinsp;=\u0026thinsp;20), neural network (NN) (n\u0026thinsp;=\u0026thinsp;15), and XGBoost (n\u0026thinsp;=\u0026thinsp;12) (Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e2\u003c/span\u003e). Among the three most common population groups, RF models were most frequently used in studies which involved general athlete populations (9/20, 45.0%) and mixed populations (4/7, 57.1%). In studies focused on football, SVM and XGBoost models were the most commonly used, each applied in 10 out of 25 studies (40.0%). Beyond these core algorithms, categorical boosting (CatBoost), adaptive boosting (AdaBoost), Light gradient boosting machine, and elastic-net penalized regression were frequent ensemble or regularized variations, and 14 studies explored newer architectures such as deep-learning models (TabNet, ConcNet, CNNs, feedforward NNs, recurrent NNs [RNNs], Faster region-based CNN [Faster R-CNN]) for imaging or signal-based classification. Model selection generally reflected data type: tree-based ensembles and SVMs dominated structured tabular datasets (e.g., sensor, GPS, clinical, or performance data), while CNNs and RNNs were used for imaging and video, and task-specific networks such as ConcNet for EEG. Unsupervised clustering (umap, k-means, subgroup discovery) appeared occasionally for identifying biomechanical or risk profiles. In total, 42 studies incorporated explainable AI methods (feature importance or Shapley additive explanation values). Ten studies investigated LLMs (ChatGPT, Gemini, Bard, DeepSeek) for patient education rather than prediction. Although internal cross-validation was common, external/temporal validation and reporting of calibration metrics were rare, which underscores that while AI model performance was often strong, methodological maturity and reproducibility remain limited across sports medicine applications.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec17\" class=\"Section2\"\u003e \u003ch2\u003eStudies in orthopaedics\u003c/h2\u003e \u003cp\u003eWithin orthopaedics (n\u0026thinsp;=\u0026thinsp;68), AI was applied to three main areas: injury prediction, diagnostic imaging/video analysis, and outcome estimation after ligament reconstruction (Table\u0026nbsp;1). Common inputs included isokinetic knee strength, hop and balance tests, jump biomechanics, GPS-derived loads, clinical/radiographic fields, and MRI/computer tomography (CT) or match-video frames. Most studies (43/68, 63,2%) implemented predictive/estimation models, which typically used preseason screening (neuromuscular tests and anthropometrics), training-load/GPS and wellness logs, or clinical/surgical registry data to forecast ACL injury/reinjury, muscle strain, or RTS and functional recovery. Discrimination was generally poor to excellent (AUC 0.61\u0026ndash;0.97, accuracy 65\u0026ndash;98%), with tree-based ensembles (RF, XGBoost, gradient boosting) frequently achieved AUC\u0026thinsp;\u0026ge;\u0026thinsp;0.80 [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e, \u003cspan additionalcitationids=\"CR12 CR13 CR14 CR15\" citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e] and, in a few ACL-specific outcome models, approached 0.90\u0026ndash;0.95 [\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e, \u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e]. Diagnostic/detection studies (9%) focused on imaging and video, for example, CNN or RNN models to identify ACL injury from online match footage or to distinguish lumbar spondylolysis from non-specific low-back pain, reported accuracies of 73\u0026ndash;96%. Beyond imaging, several works modeled post-operative trajectories (e.g., graft rupture risk, subjective function, and psychological readiness), drawing on isokinetic strength, hop tests, y-balance tests and patient reported outcomes. A small subset evaluated LLMs for orthopaedic patient education (e.g., ACL reconstruction and sports surgery information quality), which represented methodological exploration rather than prediction. Taken together, the orthopaedic literature reports strong within-sample performance on structured, tabular data and promising results for image/video-based detection, however, external/temporal validation and diverse cohorts (including female athletes) remain limited, which constrained generalizability.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec18\" class=\"Section2\"\u003e \u003ch2\u003eStudies in neurology\u003c/h2\u003e \u003cp\u003eIn neurology-focused research (n\u0026thinsp;=\u0026thinsp;18), nearly all studies (17/18, 94.4%) examined SRC, that used models to predict recovery time or classify concussion presence/severity (Table\u0026nbsp;1). Inputs were predominantly clinical and neurocognitive assessments (e.g., sport concussion assessment tool 3/5, vestibular ocular motor screening, symptom inventories, prior SRC, and time-to-clinic), sensor-based biomechanics (head-impact kinematics, and dual-task gait/behavioral performance), and physiological signals including EEG (resting-state and task-based) and radiomics from MRI/diffusion tensor imaging, where several studies combined these into multimodal feature sets. Reported performance was moderate to excellent, with AUC 0.70\u0026ndash;0.96 and accuracy 75\u0026ndash;96%. For recovery-time prediction, decision-tree and boosting approaches achieved AUC\u0026thinsp;~\u0026thinsp;0.80 and sensitivity\u0026thinsp;\u0026gt;\u0026thinsp;0.90 for early-recovery classification in pediatric and youth cohorts [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e, \u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e]. For SRC classification, SVM/RF/boosting models commonly reached AUC\u0026thinsp;\u0026ge;\u0026thinsp;0.80 [\u003cspan additionalcitationids=\"CR21\" citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e], while deep-learning on EEG (e.g., ConcNet) reported the highest accuracy (94%) [\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e]. Overall, neurology applications show strong within-sample discrimination across both predictive and classification use-cases and growing interest in multimodal modeling. However, external/temporal validation, standardized feature sets, and explainability remain limited, which constrained generalizability beyond single-site cohorts.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec19\" class=\"Section2\"\u003e \u003ch2\u003eModel validation and translational stage\u003c/h2\u003e \u003cp\u003eAcross all included studies, the majority relied on retrospective datasets and internal validation procedures, most commonly cross-validation or train-test splits. Only three studies employed external datasets to assess generalizability, and reporting of calibration metrics was uncommon [\u003cspan additionalcitationids=\"CR25\" citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e]. Prospective implementation within preventive or decision-making workflows was rare, with only one study attempting a feedback-based interventional approach [\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e]. Two studies evaluated AI-integrated rehabilitation systems within structured training programs, which included one randomized controlled trial in postoperative ACL rehabilitation [\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e] and one application which combined AI and virtual reality for athlete rehabilitation training [\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e].\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eHeatmap of AI-/ML model(s) used in each included study*\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"15\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c10\" colnum=\"10\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c11\" colnum=\"11\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c12\" colnum=\"12\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c13\" colnum=\"13\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c14\" colnum=\"14\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c15\" colnum=\"15\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colspan=\"14\" nameend=\"c14\" namest=\"c1\"\u003e \u003cp\u003eTable\u0026nbsp;1: Overview of included studies.\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colspan=\"1\" nameend=\"c15\" namest=\"c15\"\u003e\u0026nbsp;\u003c/th\u003e \u003c/tr\u003e \u003ctr\u003e \u003cth align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eAuthor\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eYear\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eJournal\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eCountry\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eMedical field\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e \u003cp\u003eField of population\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c8\"\u003e \u003cp\u003eSample size, n\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c9\"\u003e \u003cp\u003eAge, mean years or range\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c10\"\u003e \u003cp\u003eSex, males %\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c11\"\u003e \u003cp\u003eAI application\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c12\"\u003e \u003cp\u003eAI outcome\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c13\"\u003e \u003cp\u003eModel(s)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c14\"\u003e \u003cp\u003eKey findings\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c15\"\u003e \u003cp\u003eData used\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eAbasi et al.[\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2025\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eBioData Minin\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eIran\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eCardiopulmonary\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eElite football\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e256\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003eNR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003eNR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of reinjury risk\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eSVM, CatBoost, RF, XGBoost\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eCatBoost; Acc: 0.9138, F1: 0.9148; SVM: AUC: 0.9725\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eCardiopulmonary data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eAllen et al.[\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2023\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eJournal of Neurosurgery: Pediatrics.\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eUSA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eNeurology\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003ePediatric athletes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e493\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e15.7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e68\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of early (\u0026le;\u0026thinsp;14), typical (15\u0026ndash;27), delayed (\u0026ge;\u0026thinsp;28) recovery time (days) from SRC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eDT\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eAUC: 0.80, Youden: 0.44. Sen: \u0026gt;0.90 (Classified early recovery)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eDemographics, post-SRC symptom scales, time-to-clinic presentation, concussion history, presence of defined symptom clusters\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eAoyag et al.[\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2021\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eSpine\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eJapan\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eJunior high-school athletes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e223\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e13.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e72\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eDiagnostic \u0026amp; Detection models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eDistinguish lumbar spondylolysis from non-specific low back pain\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eCART\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eSen: 0.64, Spec: 0.92, AUC: 0.79\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eDemographics, school grades, symptom onset time, history of lower-back pain, pre-existing conditions and anthropometry\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eAyala et al.[\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2019\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eInternational Journal of Sports Medicine\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eSpain\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eProfessional football\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e96\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003eNR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of risk factors of hamstring injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eDT\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eAUC: 0.837, Sen: 0.778, Spec: 0.838\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003ePreseason: psychological, neuromuscular, and demographical data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eBazarian et al.[\u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2021\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eJAMA Network Open\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eUSA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eNeurology\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eAthletes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e580\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e19.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e54\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eClassification \u0026amp; Pattern recognition\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eClassification of SRC based on EEG\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eGenetic algorithm\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eSen: 0.860, Spec 0.708, NPV: 0.901, PPV: 0.620, AUC: 0.89\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eEEG, cognitive tests, symptom inventories\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eBergeron et al.[\u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2019\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eMedicine \u0026amp; Science in Sports \u0026amp; Exercise\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eUSA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eNeurology\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eHigh-school football\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e2004\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003eNR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003eNR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eEstimation of symptom resolvment after SRC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eNB, SVM, 5-nearest neighbours, DT, RF, MLP, radial basis function network\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eNB and RF with 100 or 500 trees: AUC: 0.656\u0026ndash;0.742\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eSymptom and recovery data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eBriand et al.[\u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e35\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2022\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eFrontiers in Sports \u0026amp; Active Living\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eCanada\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eVarious (orthopaedics and neurology)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eShort-track speed skaters\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e21\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eRF\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eSen: 0.5, Spec 0.7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eLongitudinal: training load, physiological, neuromuscular, psychological well-being, heart rate variability and injury history data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eCalderon-Diaz et al.[\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2023\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eSensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eChile\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eProfessional football\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e110\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003eNR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of muscle injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eDT, discriminant methods, NB, SVM, KNN, NN, XGBoost\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eXGBoost: Prec: 78%.\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eBiomechanical and muscle performance data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eCao et al.[\u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e37\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2008\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eIEEE Transactions on Neural Systems \u0026amp; Rehabilitation Engineering\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eUSA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eNeurology\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eRugby and American football\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e61\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e20\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e44\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eClassification \u0026amp; Pattern recognition\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eClassification of residual functional deficit\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eSVM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eAcc: 77.1%, Sen: 80.0%, Spec: 75.0%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eEEG\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eCastellanos et al.[\u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e38\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2021\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eSports Medicine\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eUSA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eNeurology\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eUS Military cadettes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e15682\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e19\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e65\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of SRC risk\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eSVM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eAUC: 0.73\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eBaseline demographic, clinical, cognitive and behavioral data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eChen et al.[\u003cspan citationid=\"CR39\" class=\"CitationRef\"\u003e39\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2022\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eComputational \u0026amp; Mathematical Methods in Medicine\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eChina\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eBasketball\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e935\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e20\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e76\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eClassification \u0026amp; Pattern recognition\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eClassification of thoracolumbar vertebral fractures (ABC)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eDeeplearning: Faster RCNN\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eAcc: 86.4%, Cohen's kappa: 0.850\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eCT images\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eChu et al.[\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2022\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eAnnals of Physical \u0026amp; Rehabilitation Medicine\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eUSA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eNeurology\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eYouth athletes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e655\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e13.7 (male), 14.0 (female)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e55\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of SRC recovery\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eCatBoost, DT, elastic net, RF, XGBoost, TabNet\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eCatBoost: AUC: 0.8 (males), and 0.78 (females)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003ePreinjury risk factors, injury severity measures, post-SRC functional and symptom data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eDandrieux et al.[\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2025\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eBMJ Open Sport \u0026amp; Exercise Medicine\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eFrance\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eVarious\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eTrack and field\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e112\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e34\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e62\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eInvestigate association between injury risk estimation and injury burden\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eNegative binomial regression\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eAUC: 0.63\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eLongitudinal: training activity, psychological state, sleep quality, and self-reported injury status\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eDe la Fuente et al.[\u003cspan citationid=\"CR40\" class=\"CitationRef\"\u003e40\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2023\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eScience \u0026amp; Medicine in Football\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eChile\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eFootball\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e21\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e22.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eClassification \u0026amp; Pattern recognition\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eClustering to determine risk profiles based on biomechanical properties\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eumap\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003e3 clusters of biomechanical properties\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eBiomechanical data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003ede Leeuw et al.[\u003cspan citationid=\"CR41\" class=\"CitationRef\"\u003e41\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2022\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eEuropean Journal of Sport Science\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eNetherlands\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eVolleyball\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e27\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of overuse injuries\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eSubgroup discovery\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eJump load was an important predictor for 70% of players\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eLongitudinal: training load, subjective wellness reports and overuse symptom questionnaires\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eDiCesare et al.[\u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e42\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2020\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eAnnals of Biomedical Engineering\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eUSA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eNeurology\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eFootball\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e20\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e16\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eClassification \u0026amp; Pattern recognition\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eClassification of sub-SRC impact exposure\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eXGBoost\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eAcc: 83.5%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eWearable sensor data, video-verified head impact recordings and MRIs\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eDiniz et al.[\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2022\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eKnee Surgery, Sports Traumatology, Arthroscopy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eVarious\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eFootball\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e209\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e28.3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of level of match participation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eClustering, XGBoost\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eXGBoost: AUC: 0.81\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eMatch participation and performance data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eDiniz et al.[\u003cspan citationid=\"CR43\" class=\"CitationRef\"\u003e43\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2024\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eKnee Surgery, Sports Traumatology, Arthroscopy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eVarious\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eFootball\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e236\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e26.6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eCross-validation of identified ACL injury mentions\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eOpenAI\u0026rsquo;s \u003c/p\u003e \u003cp\u003eGPT-4o mini\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eSen: 88.4%, Spec: 99.3%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003ePublicly available textual and database data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eElkin et al.[\u003cspan citationid=\"CR44\" class=\"CitationRef\"\u003e44\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2018\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eApplied Clinical Informatics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eUSA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eMixed\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e469\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e44\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e50\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eDiagnostic \u0026amp; Detection models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eDiagnosis of knee injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eBayesian and heuristic model\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eSpecificity-based Bayesian model significantly outperformed heuristic model\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003ePatient-reported questionnaire\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eEskofier et al.[\u003cspan citationid=\"CR45\" class=\"CitationRef\"\u003e45\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2012\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eComputer Methods in Biomechanics \u0026amp; Biomedical Engineering\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eCanada\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eRunners\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e80\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e41.1 (male), 36.0 (female)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e50\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eClassification \u0026amp; Pattern recognition\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eClassification of participants with or without patellofemoral pain syndrome\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eAdaBoost\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eAcc: 100%.\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eBiomechanical data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eEvans et al.[\u003cspan citationid=\"CR46\" class=\"CitationRef\"\u003e46\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2024\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003ePLoS ONE\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eUK\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eRugby\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e36\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e20.7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eClassification \u0026amp; Pattern recognition\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eClassification of non-contact lower limb injuries risk factors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eBayesian pattern recognition and assessed by means of: NB, J48 DT, SVM, KNN\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eAUC 0.76 (severe non-contact lower limb), 0.70 (non-contact lower limb), and 0.71 (non-contact ankle)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eLongitudinal: training load, performance test results, musculoskeletal screening metrics and injury history\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eFarhadian et al.[\u003cspan citationid=\"CR47\" class=\"CitationRef\"\u003e47\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2020\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eBMC Sports Science, Medicine and Rehabilitation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eIran\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOdontology\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003ePediatric athletes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e356\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e11.3 (injured), 10.6 (uninjured)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e54\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of dental injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eRF\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eAcc: 89.3%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eDemographic and behavioral data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eFerris et al.[\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2021\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eAmerican Journal of Sports Medicine\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eUSA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eNeurology\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eCollegiate athletes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e388\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e19.9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e63\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eDiagnostic \u0026amp; Detection models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eDiagnosis of SRC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eAdaBoost\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eIncreased diagnostic accuracy by 4.4% to AUC: 0.848, and increased Sen by 9%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eMultimodal concussion assessment data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eFreitas et al.[\u003cspan citationid=\"CR48\" class=\"CitationRef\"\u003e48\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2025\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003ePLoS ONE\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003ePortugal\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eProfessional football\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e34\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e26.3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of non-contact injuries in footballers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eSVM, Feedforward NN, AdaBoost\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eSVM: Acc: 74%, Sen: 71%, Spec: 74%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eWearable GPS data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eGarcia et al.[\u003cspan citationid=\"CR49\" class=\"CitationRef\"\u003e49\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2019\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eJournal of Neurotrauma\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eUSA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eNeurology\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eAthletes and military\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e24561\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e19.3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e58\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of SRC levels\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eCART\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eSen: 91.07% to 97.40%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eConcussion assessment and demographic data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eGaudet et al.[\u003cspan citationid=\"CR50\" class=\"CitationRef\"\u003e50\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2019\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eJournal of Science \u0026amp; Medicine in Sport\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eCanada\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eSwimmers and handball\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e34\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e21.7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eClassification \u0026amp; Pattern recognition\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eClustering to determine shoulder injury based on subjective outcomes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eK-mean clustering\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eSen: 86%, Spec: 100%, diagnostic OR: 229.67 (KJOC). Sen: 86%, Spec: 37%, diagnostic OR: 3.53 (CKQUEST)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eFunctional performance and self-reported clinical assessment data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eGiorgino et al.[\u003cspan citationid=\"CR51\" class=\"CitationRef\"\u003e51\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2024\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eDiagnostics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eItaly\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eReasoning \u0026amp; summarization assistance\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eUse of an LLM for patient education\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eGoogle Bard \u0026amp; ChatGPT-3.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eBoth models show good promise in patient education\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eText-based conversation responses\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eGirard et al.[\u003cspan citationid=\"CR52\" class=\"CitationRef\"\u003e52\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2025\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eKnee Surgery, Sports Traumatology, Arthroscopy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eCanada\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eAdolescents with and without ACL injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e134\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e15.3 (ACL injured)\u003c/p\u003e \u003cp\u003e13.8 (controls)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e30 (ACL injured)\u003c/p\u003e \u003cp\u003e44 (controls)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eClassification \u0026amp; Pattern recognition\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eClassification of ACL injury status\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eDT\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eEntire group: Acc 0.675, Sen 0.70, Spec 0.65, F1 0.684; Females: Acc 0.769; Males: Acc 0.533\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eBiomechanical data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eGoggins et al.[\u003cspan citationid=\"CR53\" class=\"CitationRef\"\u003e53\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2022\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eInternational Journal of Sports Medicine\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eUnited Kingdom\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eElite pathway cricket\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e17\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e18.2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eDT, RF\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eDT: AUC: 0.66. RF: AUC: 0.72\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eLongitudinal: training load and performance monitoring data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eGultekin et al.[\u003cspan citationid=\"CR54\" class=\"CitationRef\"\u003e54\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2025\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eKnee Surgery, Sports Traumatology, Arthroscopy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eTurkey\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eReasoning \u0026amp; Summarization models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eEvaluation of LLM-generated ACL surgery patient education responses\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eChatGPT-4o, DeepSeek R1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eBoth high accuracy (3.9/4) and consistency (4/4); ChatGPT more comprehensive (4.0 vs 3.2, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001); DeepSeek clearer (3.9 vs 3.0, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001) and more readable (FKGL 8.9 vs 14.2; FRES 61.3 vs 32.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eText-based conversation responses\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eGuo et al.[\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2025\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003ePeerJ\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eChina\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eCollegiate basketball\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e104\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e20.4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of ACL injury incidence\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eRF, SVM, XGBoost, LR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eRF: AUC 0.80; Accuracy 0.962; XGBoost AUC 0.79; Logistic regression AUC 0.76; SVM AUC 0.66\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eDemographic, injury history, biomechanical and EMG data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eHecksteden et al.[\u003cspan citationid=\"CR55\" class=\"CitationRef\"\u003e55\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2023\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eScience and Medicine in Football\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eGermany\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eProfessional football players\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e88\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e24.6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eForecasting non-contact time-loss injuries\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eGBoost, LR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eGBoost: CV AUC 0.61; Test AUC 0.62; without screening data AUC 0.56; without upsampling AUC 0.48\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003ePhysical performance, clinical, injury history and daily training, recovery and exposure data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eHenriquez et al.[\u003cspan citationid=\"CR56\" class=\"CitationRef\"\u003e56\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2020\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eFrontiers in Sports \u0026amp; Active Living\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eUSA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eStudent athletes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e122\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e19.6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e59\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of musculoskeletal injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eRF\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eAcc: 79%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eBiomechanical, physical performance, demographic and injury history data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eHopkingson et al.[\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2022\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eEuropean Journal of Sport Science\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eVarious European\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eRugby\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e246\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003eNR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003eNR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eClassification \u0026amp; Pattern recognition\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eClassification of injurious or no-injurious tackles\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eRF\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eAcc: 0.919, Sen: 0.995, Spec: 0.525\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eVideo-derived tackle characteristics\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eHsu et al.[\u003cspan citationid=\"CR57\" class=\"CitationRef\"\u003e57\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2022\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eJournal of Human Kinetics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eVarious\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eNephrology\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eUltramarathon runners\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e22\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e44\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e95\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of acute kidney injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eSVM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eSen: 90%, Spec 100%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eBaseline psychological, biochemical, and body composition data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eHu et al.[\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2025\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eScientific Reports\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eCroatia\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eRadiology\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eMixed\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e3064\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003eNR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003eNR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eDiagnostic \u0026amp; Detection models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eDetection of ACL injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eCNN\u0026thinsp;+\u0026thinsp;modified political optimizer\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eAcc: 96.496%, Sen: 99.767%, Spec: 98.557%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eMRI\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eHuang et al.[\u003cspan citationid=\"CR58\" class=\"CitationRef\"\u003e58\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2022\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eFrontiers in Physiology\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eChina\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eYouth basketball\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e16\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e16.6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of lower extremity non-contact injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eFusion model, XGBoost, RF\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eFusion model: Prec: 0.9932, recall: 0.9976, F2: 0.9967 (non-injured). Prec: 0.9317, recall: 0.9167, F2: 0.9171 (minimal LE NC). Prec: 0.9000, recall: 0.9000, F2: 0.9000 (mild LE NC)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eLongitudinal: training load, perceived well-being, psychological responses, physical performance metrics, and injury history\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eHuang et al.[\u003cspan citationid=\"CR59\" class=\"CitationRef\"\u003e59\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2023\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eFrontiers in Physiology\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eChina\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eYouth basketball\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e17\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e15\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of lower limb non-contact injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eCost-sensitive NN\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eAUC: 0.8590, Prec: 0.6360, recall: 0.8700, F2: 0.7980, Brier: 0.1020\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003ePhysical fitness, physiological data: performance metrics, biochemical markers, physiological responses, and perceived exertion\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eHwang et al.[\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2025\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eOrthopaedic Journal of Sports Medicine\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eSouth Korea\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eAthletes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e113\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e27\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e67\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of subjective function, symptoms, and psychological readiness\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eGBoost, SVM, LR, DT, RF\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eGBoost: AUC: 0.844, F1: 0.889 (Successful recovery of PASS, IKCD). RF: AUC: 0.835, F1:0.732 (PASS ACL-RSI)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eIsokinetic muscle strength and y-balance test results and patient reported outcomes\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eHwang et al.[\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2024\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eDigital Health\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eSouth Korea\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eAthletes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e102\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e30\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e74\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of return to sport after ACL reconstruction\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eRF, GBoost\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eRF: AUC: 0.952 (single leg hop), and 0.949 (Tegner activity scale). GBoost: AUC: 0.868 (single leg vertical hop)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003ePhysical performance data: balance, and isokinetic muscle strength\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eJacob et al.[\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2022\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eScientific Reports\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eIceland\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eNeurology\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eElite athletes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e54\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e38.4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eClassification \u0026amp; Pattern recognition\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eClassification of SRC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eRF, GBoost, AdaBoost, SVM, MLP\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eSVM: Acc: 95.5%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eEEG, EMG; heart rate, and center of pressure and concussion assessment scale (SCAT5)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eJauhiainen et al.[\u003cspan citationid=\"CR60\" class=\"CitationRef\"\u003e60\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2022\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eAmerican Journal of Sports Medicine\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eVarious\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eElite football and handball\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e791\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e21\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of ACL injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eSVM linear and with imbalance handling, RF, L2-regularized LR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eLinear SVM: AUC: 0.63\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003ePreseason biomechanical and physical performance data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eJauhiainen et al.[\u003cspan citationid=\"CR61\" class=\"CitationRef\"\u003e61\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2020\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eInternational Journal of Sports Medicine\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eFinland\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eYouth basketball and floorball\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e314\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e16.0 (male), 15.4 (female)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e45\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of injury risk\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eRF\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eAUC: 0.63\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eBaseline biomechanical and physical performance data and anthropometrics\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eJia et al.[\u003cspan citationid=\"CR62\" class=\"CitationRef\"\u003e62\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2022\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eComputational Intelligence \u0026amp; Neuroscience\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eChina\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eGymnasts\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e126\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e15.3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eClassification \u0026amp; Pattern recognition\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eIdentification of injury through images\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eFuzzy pattern recognition. NN.\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eIdentified injury situation through images\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eImage data and biomechanical force analysis\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eKarbalaie et al.[\u003cspan citationid=\"CR63\" class=\"CitationRef\"\u003e63\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2026\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eJournal of Sports Sciences\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eSweden\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eMixed: Patients with ACL-R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e107\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e25.2 (ACLR); 22.4 (controls)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e36\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eClassification \u0026amp; Pattern recognition\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eClassification of high versus low fear of re-injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eCNN, LR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eCNN: Acc 75.6%, F1 0.6, MCC 0.52; 8.6% higher Acc compared to LR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eBiomechanical data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eKolodziej et al.[\u003cspan citationid=\"CR64\" class=\"CitationRef\"\u003e64\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2023\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eScandinavian Journal of Medicine \u0026amp; Science in Sports\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eGermany\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eYouth elite football\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e56\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e17.2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of lower extremity injury risk\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eLASSO. Leave-One-Out\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eLASSO: AUC: 0.63, Sen: 35%, Spec: 79%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eBiomechanical, neuromuscular and postural control data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eKunze et al.[\u003cspan citationid=\"CR65\" class=\"CitationRef\"\u003e65\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2021\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eJournal of Bone \u0026amp; Joint Surgery\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eUSA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eAthletes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e1118\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e30\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e32\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of functional Improvement\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eENPLR, stochastic GBoost, RF, AdaBoost, NN, SVM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eENPLR: AUC: 0.77, intercept: 0.7, slope: 1.22, Brier: 0.14\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eClinical, demographic and radiographic registry data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eKunze et al.[\u003cspan citationid=\"CR66\" class=\"CitationRef\"\u003e66\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2021\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eOrthopaedic Journal of Sports Medicine\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eUSA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eMixed: Patients with ACL-R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e442\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e29\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e52\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of clinically meaningful improvement after ACL reconstruction\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eStochastic GBoost, RF, NN, SVM, AdaBoost, ENPLR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eENPLR: AUC: 0.82, intercept: 0.10, slope: 1.15, Brier: 0.068\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eClinical and surgical registry data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eLipps Lene et al.[\u003cspan citationid=\"CR67\" class=\"CitationRef\"\u003e67\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2024\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eJournal of Experimental Orthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eFrance\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eAthletes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e96\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e21.9 (male), 21.1 (female)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e64\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eDiagnostic \u0026amp; Detection models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eIdentification of participants with earlier knee injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eDT, MLP, XGBoost\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eDT and MPL: AUC: 0.94, Acc: 0.95, Prec: 1.0, Recall: 0.88, F1: 0.93\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eBiomechanical and psychological data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eL\u0026oacute;pez-Valenciano et al.[\u003cspan citationid=\"CR68\" class=\"CitationRef\"\u003e68\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2018\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eMedicine \u0026amp; Science in Sports \u0026amp; Exercise\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eSpain\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eProfessional football and handball\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e132\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003eNR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of muscle injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eC4.5 DT, SimpleCart, ADTree, RandomTree\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eADTree: AUC: 0.747, Sen: 65.9%, Spec: 79.1%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003ePreseason demographic, psychological and neuromuscular data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eL\u0026ouml;vdal et al.[\u003cspan citationid=\"CR69\" class=\"CitationRef\"\u003e69\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2021\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eInternational Journal of Sports Physiology \u0026amp; Performance\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eNetherlands\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eHigh-level middle- and long-distance runners\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e74\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003eNR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e64\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eXGBoost\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eAUC: 0.724 (day), and 0.678 (week)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eLongitudinal training load data (GPS and subjective training feedback)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eLu et al.[\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2022\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eOrthopaedic Journal of Sports Medicine\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eUSA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eElite basketball\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e2103\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e26\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of lower extremity muscle strain/injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eXGBoost, RF, NN, SVM, elastic net penalized LR, generalized LR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eXGBoost AUC: 0.840\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eLongitudinal player performance and historical injury data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eMart\u0026iacute;nez-Gramage et al.[\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2020\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eSensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eSpain\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eTriathletes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e19\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e14.6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e53\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of running injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eRF\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eAUC: 0.8, Sen: 0.6, Spec: 0.8, NPV 0.7, Matthews correlation coefficient 0.4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eBiomechanical, neuromuscular, and injury incidence data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eMaxin et al.[\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2024\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eDiagnostics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eUSA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eNeurology\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eCollegiate football\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e93\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e20\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eDiagnostics \u0026amp; Detection models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eDiagnosis of acute SRC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eRF, KNN, SVM, LR (SMOTE)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003ePost-SMOTE RF: Acc 91%, Sen 98%, Spec 86%, AUC 0.91, F1 0.92\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eSmartphone-based quantitative pupillometry\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eMcBee et al.[\u003cspan citationid=\"CR70\" class=\"CitationRef\"\u003e70\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2024\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eJMIR medical education\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eUSA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eVarious\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eReasoning \u0026amp; summarization assistance\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eLLM for interdisciplinary panel discussion on sports medicine\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eChatGPT-4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eReasonably pointed to various benefits such as 24/7 support, personalized advice, automated tracking, and reminders\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eText-based conversation data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eMurray et al.[\u003cspan citationid=\"CR71\" class=\"CitationRef\"\u003e71\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2024\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eSports \u0026amp; Health\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eUSA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eNeurology\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eStudent athletes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e409\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e20\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e56\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eClassification \u0026amp; Pattern recognition\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eClassification participants with or without SRC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eLR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eSingle-task tests were slower in patients with SRC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eBiomechanical and behavioral performance data including cognitive task response rates\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eNechita et al.[\u003cspan citationid=\"CR72\" class=\"CitationRef\"\u003e72\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2025\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eDiagnostics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eRomania\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eCardiology\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eYouth athletes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e312\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e7 to 17\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003eNR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eDiagnostic \u0026amp; Detection models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eDetection of cardiovascular injury risk\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eRF, CNN\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eRF: Acc: 97.87%, Sen: 75%, Spec: 98.3%, Prec: 98%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003ePhysiological ECG data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eNolte et al.[\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2025\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eJournal of Sports Sciences\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eGermany\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eMixed: Patients with/without ACL injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e549\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e22.2 (male), 23.0 (female)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e67\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of participants being ACL-injured or not\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eRF\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eAUC: 0.90 (male), AUC: 0.92 (female)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eIsokinetic strength test data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eNonnenmacher et al.[\u003cspan citationid=\"CR73\" class=\"CitationRef\"\u003e73\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2025\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eBone \u0026amp; Joint Open\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eGermany\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eAthletes with periacetabular osteotomy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e235\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e31.9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e17\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of early RTS at 3 and 6 months after surgery\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eLR, Conditional inference tree\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eEarly RTS associated with surgical approach, sport frequency, psychological factors, and pain; delayed RTS with male sex and older age.\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003ePreoperative demographic and patient-reported questionnaire data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eNose-Ogura et al.[\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2025\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003ePhysician and Sportsmedicine\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eJapan\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eEndocrinology\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eAthletes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e614\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e20.9 (development), 19.6 (validation)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of low bone mineral density\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eLASSO\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eDevelopment AUC 0.89; Validation AUC 0.74; Sensitivity 0.83; NPV 0.85\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003ePreoperative questionnaire and dual-energy X-ray absorptiometry data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eOhlsen et al.[\u003cspan citationid=\"CR74\" class=\"CitationRef\"\u003e74\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2025\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eCureus\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eUSA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eReasoning \u0026amp; Summarization assistance models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eAgreement of LLM recommendations with clinical guidelines for ACL and meniscal injuries\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eChatGPT-4o, Gemini 2.5 Pro\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eChatGPT: 82% agreement, Gemini: 73% agreement; no significant difference between models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eText-based conversation data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eOliver et al.[\u003cspan citationid=\"CR75\" class=\"CitationRef\"\u003e75\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2020\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eJournal of Science \u0026amp; Medicine in Sport\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eEngland\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eYouth elite football\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e355\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e14.3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of non-contact lower extremity injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eMultivariate LR, supervised learning DT\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eDT: AUC: 0.663, Sen: 55.6%, Spec: 74.2%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003ePreseason neuromuscular screening data and anthropometric measures\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eOzbek et al.[\u003cspan citationid=\"CR76\" class=\"CitationRef\"\u003e76\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2025\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eArthroscopy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eTurkey / USA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eReasoning \u0026amp; Summarization assistance models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eQuality assessment of LLM responses to hip arthroscopy patient questions\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eChatGPT 4.0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003e20/25 rated \"excellent\"; 5/25 \"satisfactory\"\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eText-based conversation data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eP\u0026eacute;rez-Contreras et al.[\u003cspan citationid=\"CR77\" class=\"CitationRef\"\u003e77\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2025\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eApplied Sciences-Basel\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eChile\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eProfessional football\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e41\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e22.3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e56\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of non-contact muscle injury risk\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eLR, DT, KNN, RF, GBoost, NN\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eKNN: Acc 87%, AUC 0.87; Gradient Boosting: Acc 84%, AUC 0.90; Logistic Regression AUC 0.50\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003ePreseason biomechanical and training load data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003ePiłka et al.[\u003cspan citationid=\"CR78\" class=\"CitationRef\"\u003e78\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2023\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eSensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003ePoland\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eFootball\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e36\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e24\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of football injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eXGBoost\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003ePrec: 92.4%, recall: 96.5%, F1: 94.4%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eTraining and match load data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eQuinn et al.[\u003cspan citationid=\"CR79\" class=\"CitationRef\"\u003e79\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2024\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eArthroscopy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eUSA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eReasoning \u0026amp; summarization assistance\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eLLM to test quality of information with regard to ACL reconstruction\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eChatGPT-4, Gemini\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eChatGPT-4 and Gemini: Overall good ability to generate accurate and relevant responses\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eText-based conversation data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eRossi et al.[\u003cspan citationid=\"CR80\" class=\"CitationRef\"\u003e80\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2023\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eSport Sciences for Health\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eItaly\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eElite football\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e18\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e24.7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of non-contact injury risk\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eDT, GBoost, k-mean cluster\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eAcc increased to 63% (15% improvement) after blood profile was added to workload-only models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eGPS-derived external workload and blood biomarker data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eRichter et al.[\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2023\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eSports Biomechanics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eNorway\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eElite football and handball\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e822\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e21\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of participants with previous-/future-/no ACL injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eDT, RF, discriminant analysis, NB, KNN, SVM, LR, NN\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eCluster of models: Average AUC 0.62, Sen: 0.59, Spec: 0.58\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eBiomechanical data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eRobinson et al.[\u003cspan citationid=\"CR81\" class=\"CitationRef\"\u003e81\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2022\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eAmerican Journal of Physical Medicine \u0026amp; Rehabilitation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eUSA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eNeurology\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eAthletes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e273\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e21\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e52\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of prolonged recovery after SRC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eDT\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eAcc: 0.7636, Sen: 0.6429, Spec: 0.8889, PPV: 0.8571, NPV: 0.7059\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eSymptom evaluation data (SCAT5)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eRommers et al.[\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2020\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eMedicine \u0026amp; Science in Sports \u0026amp; Exercise\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBelgium\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eYouth elite football\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e734\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e11.7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of musculoskeletal injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eXGBoost\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eAcc: 85%, Prec: 85%, recall: 85%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003ePreseason anthropometric, motor coordination and physical performance data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eRuddy et al.[\u003cspan citationid=\"CR82\" class=\"CitationRef\"\u003e82\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2018\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eMedicine \u0026amp; Science in Sports \u0026amp; Exercise\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eAustralia\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eAustralian football\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e362\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e23.2 (2103), 25.0 (2015)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of hamstring injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eNB, LR, RF, SVM, NN\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eMedian of all 5 models: AUC: 0.58 (2013 season), 0.57 (2015 season)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003ePreseason demographic, injury history and strength test data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eRuiz-P\u0026eacute;rez et al.[\u003cspan citationid=\"CR83\" class=\"CitationRef\"\u003e83\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2021\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eFrontiers in Psychology\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eSpain\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eElite Futsal\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e139\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e22.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e52\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of soft tissue injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eC4.5, Alternating DT, SVM with SMO, KNN, Instance-Based Learning\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eVarious models: AUC: 0.701 to 0.767\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003ePreseason psychological and neuromuscular data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eSaghafi et al.[\u003cspan citationid=\"CR84\" class=\"CitationRef\"\u003e84\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2018\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eProceedings of SPIE\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eUSA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eNeurology\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eYouth and high-school football\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e122\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e9 to 18\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003eN/A\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eClassification \u0026amp; Pattern recognition\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eClassification of white matter changes after head impact exposure\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eCNN\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eAUC: 85.71%, F1: 83.33%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eNeuroimaging and biomechanical data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eSaglam et al.[\u003cspan citationid=\"CR85\" class=\"CitationRef\"\u003e85\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2025\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eBMC Medical Informatics \u0026amp; Decision Making\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eTurkey\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eReasoning \u0026amp; Summarization assistance models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eComparison of GPT's in clinical decision-making\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eGPT-4, GPT-3.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eGPT-4 significantly outperformed GPT-3.5 (p\u0026thinsp;\u0026lt;\u0026thinsp;0.001; Cohen\u0026rsquo;s d\u0026thinsp;=\u0026thinsp;1.42); higher treatment and rehabilitation suitability (p\u0026thinsp;\u0026lt;\u0026thinsp;0.001)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eText-based conversation data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eSchulc et al.[\u003cspan citationid=\"CR86\" class=\"CitationRef\"\u003e86\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2024\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eOrthopaedic Journal of Sports Medicine\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eUSA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eProfessional athletes with ACL injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e129\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003eNR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003eNR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eDiagnostic \u0026amp; Detection models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eIdentification of ACL injury through video analysis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eRecurrent NN\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eAUC: 0.88, F1: 0.63\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eVideo-derived biomechanical data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eShibata et al.[\u003cspan citationid=\"CR87\" class=\"CitationRef\"\u003e87\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2019\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eJournal of Orthopaedic Science\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eJapan\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003ePatients with ACL-R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e386\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e23.7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e53\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of quadriceps strength recovery 6 months after ACL-R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eDT, Stepwise multiple linear regression\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003ePreoperative QSI, age, and pre-injury Tegner score predicted 6-month QSI; decision tree correctly classified 46.8% of cases\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003ePreoperative isokinetic quadriceps strength, demographic, clinical and intraoperative finding data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eSong et al.[\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2022\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eWireless Communications \u0026amp; Mobile Computing\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eChina\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eTrack and field\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e12\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e19.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003eN/A\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eEvaluation of rehabilitation effectiveness using AI and virtual reality-assisted training\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eProbabilistic NN, SVM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eAI+virtual reality group achieved\u0026thinsp;\u0026gt;\u0026thinsp;96% physical function recovery; overall rehabilitation score 93.79 vs 82.38 (control)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003ePhysiological blood measures, functional, strength and speed assessment data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eSparks et al.[\u003cspan citationid=\"CR88\" class=\"CitationRef\"\u003e88\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2024\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eJB \u0026amp; JS Open Access\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eUSA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eReasoning \u0026amp; summarization assistance\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eLLM to investigate accuracy of patient education with regard to orthopaedic conditions\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eChatGPT-3.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eModerately accurate outputs for general inquiries. Lack in the quantity of information for risk factors and treatment options.\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eText-based conversation data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eStirling et al.[\u003cspan citationid=\"CR89\" class=\"CitationRef\"\u003e89\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2025\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eJournal of Orthopaedic Research\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eCanada\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eRadiology\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003ePatients with ACL injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e33.6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e32\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eClassification \u0026amp; Pattern recognition\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eAutomated quantification of bone marrow lesion volume and association with pain outcomes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eCNN\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eBone marrow lesions present in 95%; 96.1% volume reduction at 1 year (p\u0026thinsp;\u0026lt;\u0026thinsp;0.001); baseline BML volume modestly associated with symptoms\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eMRI and patient-reported questionnaire data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eTamez-Pe\u0026ntilde;a et al.[\u003cspan citationid=\"CR90\" class=\"CitationRef\"\u003e90\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2021\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eFrontiers in Neurology\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eUnknown\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eNeurology\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eStudent athletes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e122\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e18.8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e53\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eClassification \u0026amp; Pattern recognition\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eClassification of SRC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eSVM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eSen: 0.80, Spec: 0.74\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eNeuroimaging radiomic data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eTedesco et al.[\u003cspan citationid=\"CR91\" class=\"CitationRef\"\u003e91\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2020\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eSensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eIreland\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eNon-elite rugby\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e12\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e26\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eDiagnostic \u0026amp; Detection models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eIdentification of gait patterns in participants with or without ACL injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eKNN, NB, SVM, GBoost, MLP, stacking\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eMLP: Acc: 73.07; GBoost: Sen: 81.8%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eInertial sensor data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eThanjavur et al.[\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2021\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eFrontiers in Human Neuroscience\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eCanada\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eNeurology\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eAdolescent athletes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e58\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e13.4 (injured), 14.7 (uninjured)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eClassification \u0026amp; Pattern recognition\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eClassification of SRC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eConcNet 2 and 3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eAcc: 94%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eEEG data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eTsilimigkras et al.[\u003cspan citationid=\"CR92\" class=\"CitationRef\"\u003e92\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2024\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eJournal of Sports Science \u0026amp; Medicine\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eGreece\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eProfessional football\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e25\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003eN/A\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of muscle injury risk\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eSVM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eAcc: 0.78, Sen: 0.73, Spec: 0.85\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003ePhysiological and mechanical workload data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eUsami et al.[\u003cspan citationid=\"CR93\" class=\"CitationRef\"\u003e93\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2024\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eKnee Surgery, Sports Traumatology, Arthroscopy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eJapan\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eMixed: Patients with ACL-R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e386\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e25.1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e49\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eDiagnostic \u0026amp; Detection models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eDetection of graft rupture and contralateral ACL injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eNN\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eAUC: 0.81 (graft rupture), 0.74 (contralateral ACL injury)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eClinical, demographic, and surgical medical record data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eVallance et al.[\u003cspan citationid=\"CR94\" class=\"CitationRef\"\u003e94\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2020\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eApplied Sciences-Basel\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eFrance\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eElite football\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e40\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e29.4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of non-contact injury risk\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eKNN, DT, RF, XGBoost, SVM, MLP, Linear discriminant analysis, LR, Ridge regression, NB\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003e1-month prediction: XGBoost AUC 0.97; 1-week prediction: questionnaires outperformed GPS data; internal load strongest short-term predictor\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eGPS-derived external load, rating of perceived exertion and well-being questionnaire data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eValle et al.[\u003cspan citationid=\"CR95\" class=\"CitationRef\"\u003e95\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2022\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eSports Medicine\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eSpain\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eElite football\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e76\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e24.2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of recovery\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eLinear regression, RF, XGBoost\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eXGBoost (days to recovery): Mean absolute error: 9.78884, Root mean squared error: 12.1450, R-squared: 0.4847\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eClinical and MRI data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eVillarreal-Espinosa et al.[\u003cspan citationid=\"CR96\" class=\"CitationRef\"\u003e96\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2024\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eKnee\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eUSA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eReasoning \u0026amp; summarization assistance\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eLLM for patient education with regard to ACL surgery\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eChatGPT-4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003e5/10 responses completely accurate (by two reviewers), and 3/10 completely accurate (by at least one reviewer). Inter-rater reliability: weighted kappa: 0.57. 80% of responses were reproducible over time\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eText-based conversation data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eWang et al.[\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2026\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eScientific Reports\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eVarious\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eProfessional football\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e312\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e24.7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of non-contact lower extremity injuries\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eRF, SVM, GBoost, DNN, Ensemble model\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eEnsemble AUC 0.759\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eIsokinetic strength, training load, injury history and biomechanical data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eWeng et al.[\u003cspan citationid=\"CR97\" class=\"CitationRef\"\u003e97\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2025\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eJournal of Sports Sciences\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eTaiwan\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eVarious level baseball\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e98\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e18.0 (injured), 17.5 (uninjured)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of upper extremity injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eGIRD, LR, RF, CatBoost, SVM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eCatBoost: AUC: 0.66, Acc: 0.70\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eClinical and musculoskeletal data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eYates et al.[\u003cspan citationid=\"CR98\" class=\"CitationRef\"\u003e98\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2025\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eBMJ Open Sport \u0026amp; Exercise Medicine\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eEngland\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eNeurology\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eContact sport athletes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e375\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e24.2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e78\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of SRC recovery\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eRF\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eAcc: 94.6%, Sen: 100%, Spec: 93.8%, PPV: 71.4%, NPV: 96.3%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eClinical and MRI data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eYe et al.[\u003cspan citationid=\"CR99\" class=\"CitationRef\"\u003e99\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2023\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eFrontiers in Physiology\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eNetherlands\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eElite runners\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e64\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003eN/A\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e65\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of running injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eGASF-DCAE-DNN\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eAUC 0.985, Gmean: 0.930, Sen: 0.997, Spec: 0.868. Test: AUC: 0.891, Gmean: 0.830, Sen: 0.816, Spec: 0.845\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eLongitudinal training load, and physiological performance data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eY\u0026uuml;ce et al.[\u003cspan citationid=\"CR100\" class=\"CitationRef\"\u003e100\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2024\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eCureus\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eTurkey\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eReasoning \u0026amp; summarization assistance\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eLLM for patient education with regard to sports surgery\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eChatGPT-4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eDISCERN: 44.75 points. Sports surgery-specific scoring: 13.3 points\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eText-based conversation data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eZhan et al.[\u003cspan citationid=\"CR101\" class=\"CitationRef\"\u003e101\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2025\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eArthroscopy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eChina\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eMixed: Patients with MPFL-R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e218\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003eNR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003eNR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePrediction of clinical outcomes in patients with medial patello-femoral ligament reconstruction\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eRF, LR, SVM, DT, implemented MLP, KNN\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eVarious models: AUC: 0.760 to 0.969, and Acc: 76.8% to 95.2% (Subjective outcomes); AUC: 0.952, and Acc. 95.2% (Return to pre-injury sport); AUC: 0.756, and Acc: 75.4% (Return to pivoting sports); AUC: 0.943, and Acc: 94.9 (Recurrent instability)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eClinical, demographic and radiographic data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eZhan et al.[\u003cspan citationid=\"CR102\" class=\"CitationRef\"\u003e102\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2023\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eJournal of Sport \u0026amp; Health Science\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eUSA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eNeurology\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eMixed: Lab, MMA, American football, automobile, NASCAR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e3262\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003eNR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003eNR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eClassification \u0026amp; Pattern recognition\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eClassification of head impact subtypes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eRF\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eAcc: 96%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eBiomechanical data from head impact recordings\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eZhang et al.[\u003cspan citationid=\"CR103\" class=\"CitationRef\"\u003e103\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2022\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eContrast Media \u0026amp; Molecular Imaging\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eChina\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eRadiology\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eMixed: Patients with ACL injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e90\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e39\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e60\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eDiagnostic \u0026amp; Detection models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eImage optimization to assess ACL integrity\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eiDose4 Iterative Reconstruction Algorithm.\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eImproved image quality\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eClinical CT data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eZhu et al.[\u003cspan citationid=\"CR104\" class=\"CitationRef\"\u003e104\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2026\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eBMC Sports Science, Medicine and Rehabilitation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eChina\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003ePatients with ACL-R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e30\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e31.9 (RTS group),\u003c/p\u003e \u003cp\u003e36.9 (no-RTS group)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e73% (RTS group),\u003c/p\u003e \u003cp\u003e60% (no RTS group)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003eClassification \u0026amp; Pattern recognition\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eIdentification of urinary proteomic biomarkers associated with RTS\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eLASSO\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eAUC range 0.827\u0026ndash;0.876\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eUrinary proteomic, isokinetic strength, hop test, thigh circumference and patient-reported questionnaire data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eZhu et al.[\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2026\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eJournal of Clinical Medicine\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eChina\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOrthopaedics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003ePatients with ACL-R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e79\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e30.9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e89\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePredictive \u0026amp; Estimation models\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003eEvaluate effectiveness of a rehabilitation protocol incorporating an AI-based assessment and correction system on functional recovery\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c13\"\u003e \u003cp\u003eIntelligent Functional Movement and Physical Fitness Assessment System (ZD-200S-JG)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c14\"\u003e \u003cp\u003eTrial group showed significantly greater improvements in patient-reported outcomes and range of motion and rehabilitation adherence\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c15\"\u003e \u003cp\u003eNon-wearable three-dimensional motion capture, clinical and patient-reported questionnaire data\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003ctfoot\u003e \u003ctr\u003e\u003ctd colspan=\"15\"\u003eACL-RSI\u0026thinsp;=\u0026thinsp;Anterior cruciate ligament-return to sport after injury, Acc\u0026thinsp;=\u0026thinsp;Accuracy, AdaBoost\u0026thinsp;=\u0026thinsp;Adaptive boosting, AI\u0026thinsp;=\u0026thinsp;Artificial intelligence, AUC\u0026thinsp;=\u0026thinsp;Area under the receiver operating curve, CART\u0026thinsp;=\u0026thinsp;Regression tree analysis, CatBoost\u0026thinsp;=\u0026thinsp;Categorical boosting, CNN\u0026thinsp;=\u0026thinsp;convolutional neural networks, DT\u0026thinsp;=\u0026thinsp;Decision tree, CT\u0026thinsp;=\u0026thinsp;Computer tomography, ECG\u0026thinsp;=\u0026thinsp;electrocardiogram, EEG\u0026thinsp;=\u0026thinsp;electrocochleography, EMO\u0026thinsp;=\u0026thinsp;Electromyography, ENPLR\u0026thinsp;=\u0026thinsp;Elastic-net penalized logistic regression, F1\u0026thinsp;=\u0026thinsp;F1-Score, F2\u0026thinsp;=\u0026thinsp;F2-Score, GASF-DCAE-DNN\u0026thinsp;=\u0026thinsp;Gramian Angular Summation Field-Deep Convolutional Auto-Encoder-Deep Neural Network, GBoost\u0026thinsp;=\u0026thinsp;Gradient boosting, GPS\u0026thinsp;=\u0026thinsp;Global positioning system, GPT\u0026thinsp;=\u0026thinsp;Generative pre-trained transformer, IKCD\u0026thinsp;=\u0026thinsp;International Knee Documentation Committee, KNN\u0026thinsp;=\u0026thinsp;K-nearest neighbor, LASSO\u0026thinsp;=\u0026thinsp;Least Absolute Shrinkage and Selection Operator, LE\u0026thinsp;=\u0026thinsp;Lower extremity, LR\u0026thinsp;=\u0026thinsp;Logistic regression, MLP\u0026thinsp;=\u0026thinsp;Multilayer perceptron, MRI\u0026thinsp;=\u0026thinsp;Magnetic resonance imaging, NA\u0026thinsp;=\u0026thinsp;Not applicable, NB\u0026thinsp;=\u0026thinsp;Na\u0026iuml;ve Bayes, NN\u0026thinsp;=\u0026thinsp;Neural networks, NPV\u0026thinsp;=\u0026thinsp;Negative predictive value, NR\u0026thinsp;=\u0026thinsp;Not reported, OR\u0026thinsp;=\u0026thinsp;Odds ratio, PASS\u0026thinsp;=\u0026thinsp;Patient acceptable symptom state, PPV\u0026thinsp;=\u0026thinsp;Positive predictive value, Prec\u0026thinsp;=\u0026thinsp;Precision, RF\u0026thinsp;=\u0026thinsp;Random forest, RTS\u0026thinsp;=\u0026thinsp;Return to sport, Sen\u0026thinsp;=\u0026thinsp;Sensitivity, Spec\u0026thinsp;=\u0026thinsp;Specificity, SRC\u0026thinsp;=\u0026thinsp;Sports-related concussion, SVM\u0026thinsp;=\u0026thinsp;Support Vector Machine, Youden\u0026thinsp;=\u0026thinsp;Youden index\u003c/td\u003e\u003c/tr\u003e \u003c/tfoot\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \n\u003ctable style=\"border: none;width:517.4pt;border-collapse:collapse;margin-left:6.75pt;margin-right: 6.75pt;\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd nowrap=\"\" colspan=\"5\" style=\"width: 517.4pt;border-width: medium medium 1pt;border-style: none none solid;border-color: currentcolor currentcolor windowtext;border-image: initial;padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003eTable 2: Heatmap of AI-/ML model(s) used in each included study*\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd nowrap=\"\" style=\"width: 113.45pt;border-width: medium medium 1pt;border-style: none none solid;border-color: currentcolor currentcolor windowtext;border-image: initial;padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003eAI-/ML model used\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 4cm;border-width: medium medium 1pt;border-style: none none solid;border-color: currentcolor currentcolor windowtext;border-image: initial;padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003ePrediction and estimation,\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003en = 56\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 99.2pt;border-width: medium medium 1pt;border-style: none none solid;border-color: currentcolor currentcolor windowtext;border-image: initial;padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003eClassification and pattern recognition,\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003en = 20\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 106.3pt;border-width: medium medium 1pt;border-style: none none solid;border-color: currentcolor currentcolor windowtext;border-image: initial;padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003eDiagnosis and detection,\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003en = 11\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 3cm;border-width: medium medium 1pt;border-style: none none solid;border-color: currentcolor currentcolor windowtext;border-image: initial;padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003eReasoning and summarization,\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003en = 10\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd nowrap=\"\" style=\"width: 113.45pt;border-width: medium;border-style: none;border-color: currentcolor;border-image: initial;padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003eRF\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 4cm;border-width: medium;border-style: none;border-color: currentcolor;border-image: initial;background: rgb(99, 190, 123);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e45%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 99.2pt;border-width: medium;border-style: none;border-color: currentcolor;border-image: initial;background: rgb(177, 213, 128);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e15%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 106.3pt;border-width: medium;border-style: none;border-color: currentcolor;border-image: initial;background: rgb(255, 235, 132);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e9%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 3cm;border-width: medium;border-style: none;border-color: currentcolor;border-image: initial;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd nowrap=\"\" style=\"width: 113.45pt;padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003eSVM\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 4cm;background: rgb(136, 201, 126);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e36%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 99.2pt;background: rgb(138, 202, 126);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e20%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 106.3pt;background: rgb(99, 190, 123);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e18%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 3cm;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd nowrap=\"\" style=\"width: 113.45pt;padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003eCatBoost\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 4cm;background: rgb(252, 234, 132);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e7%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 99.2pt;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 106.3pt;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 3cm;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd nowrap=\"\" style=\"width: 113.45pt;padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003eXGBoost\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 4cm;background: rgb(201, 220, 129);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e20%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 99.2pt;background: rgb(255, 235, 132);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e5%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 106.3pt;background: rgb(255, 235, 132);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e9%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 3cm;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd nowrap=\"\" style=\"width: 113.45pt;padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003eGBoost\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 4cm;background: rgb(230, 228, 131);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e13%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 99.2pt;background: rgb(255, 235, 132);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e5%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 106.3pt;background: rgb(255, 235, 132);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e9%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 3cm;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd nowrap=\"\" style=\"width: 113.45pt;padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003eDT\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 4cm;background: rgb(158, 207, 127);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e30%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 99.2pt;background: rgb(216, 224, 130);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e10%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 106.3pt;background: rgb(255, 235, 132);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e9%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 3cm;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd nowrap=\"\" style=\"width: 113.45pt;padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003eCART\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 4cm;background: rgb(250, 142, 114);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e2%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 99.2pt;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 106.3pt;background: rgb(255, 235, 132);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e9%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 3cm;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd nowrap=\"\" style=\"width: 113.45pt;padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003eNB\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 4cm;background: rgb(245, 232, 132);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e9%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 99.2pt;background: rgb(255, 235, 132);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e5%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 106.3pt;background: rgb(255, 235, 132);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e9%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 3cm;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd nowrap=\"\" style=\"width: 113.45pt;padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003eKNN\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 4cm;background: rgb(230, 228, 131);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e13%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 99.2pt;background: rgb(255, 235, 132);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e5%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 106.3pt;background: rgb(99, 190, 123);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e18%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 3cm;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd nowrap=\"\" style=\"width: 113.45pt;padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003eMLP\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 4cm;background: rgb(254, 216, 128);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e5%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 99.2pt;background: rgb(255, 235, 132);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e5%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 106.3pt;background: rgb(99, 190, 123);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e18%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 3cm;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd nowrap=\"\" style=\"width: 113.45pt;padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003eNN\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 4cm;background: rgb(208, 222, 130);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e18%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 99.2pt;background: rgb(255, 235, 132);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e5%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 106.3pt;background: rgb(99, 190, 123);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e18%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 3cm;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd nowrap=\"\" style=\"width: 113.45pt;padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003eAdaBoost\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 4cm;background: rgb(252, 179, 121);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e4%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 99.2pt;background: rgb(216, 224, 130);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e10%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 106.3pt;background: rgb(255, 235, 132);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e9%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 3cm;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd nowrap=\"\" style=\"width: 113.45pt;padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003eLR\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 4cm;background: rgb(187, 216, 129);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e27%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 99.2pt;background: rgb(255, 235, 132);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e5%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 106.3pt;background: rgb(255, 235, 132);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e9%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 3cm;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd nowrap=\"\" style=\"width: 113.45pt;padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003eCNN\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 4cm;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 99.2pt;background: rgb(177, 213, 128);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e15%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 106.3pt;background: rgb(255, 235, 132);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e9%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 3cm;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd nowrap=\"\" style=\"width: 113.45pt;padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003eLASSO\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 4cm;background: rgb(252, 179, 121);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e4%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 99.2pt;background: rgb(255, 235, 132);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e5%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 106.3pt;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 3cm;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd nowrap=\"\" style=\"width: 113.45pt;padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003eK-mean cluster\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 4cm;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 99.2pt;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 106.3pt;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 3cm;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd nowrap=\"\" style=\"width: 113.45pt;padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003eChatGPT\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 4cm;background: rgb(250, 142, 114);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e2%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 99.2pt;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 106.3pt;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 3cm;background: rgb(99, 190, 123);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e80%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd nowrap=\"\" style=\"width: 113.45pt;padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003eBard\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 4cm;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 99.2pt;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 106.3pt;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 3cm;background: rgb(236, 230, 131);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e10%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd nowrap=\"\" style=\"width: 113.45pt;padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003eGemini\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 4cm;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 99.2pt;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 106.3pt;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 3cm;background: rgb(216, 224, 130);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e20%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd nowrap=\"\" style=\"width: 113.45pt;padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003eDeepSeek\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 4cm;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 99.2pt;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 106.3pt;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 3cm;background: rgb(236, 230, 131);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e10%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd nowrap=\"\" style=\"width: 113.45pt;padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003eUndefined GPT\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 4cm;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 99.2pt;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 106.3pt;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 3cm;background: rgb(236, 230, 131);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e10%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd nowrap=\"\" style=\"width: 113.45pt;border-width: medium medium 1pt;border-style: none none solid;border-color: currentcolor currentcolor windowtext;border-image: initial;padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003eOther\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 4cm;border-width: medium medium 1pt;border-style: none none solid;border-color: currentcolor currentcolor windowtext;border-image: initial;background: rgb(165, 209, 127);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e25%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 99.2pt;border-width: medium medium 1pt;border-style: none none solid;border-color: currentcolor currentcolor windowtext;border-image: initial;background: rgb(99, 190, 123);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e25%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 106.3pt;border-width: medium medium 1pt;border-style: none none solid;border-color: currentcolor currentcolor windowtext;border-image: initial;background: rgb(99, 190, 123);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e18%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd nowrap=\"\" style=\"width: 3cm;border-width: medium medium 1pt;border-style: none none solid;border-color: currentcolor currentcolor windowtext;border-image: initial;background: rgb(248, 105, 107);padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;text-align:center;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e0%\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd nowrap=\"\" colspan=\"5\" style=\"width: 517.4pt;border-width: medium;border-style: none;border-color: currentcolor;border-image: initial;padding: 0cm 5.4pt;height: 15pt;vertical-align: bottom;\"\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e* =\u003c/span\u003e \u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003eWithin each task category, proportions were calculated as the number of studies using a specific model divided by the total number of studies in that category.\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eAdaBoost = Adaptive boosting, CART = Regression tree analysis, CatBoost = Categorical boosting, CNN = convolutional neural networks, DT = Decision tree, GBoost = Gradient boosting, GPT = Generative pre-trained transformer, KNN = K-nearest neighbour, LASSO = Least Absolute Shrinkage and Selection Operator, LR = Logistic regression, MLP = Multilayer perceptron, NB = Na\u0026iuml;ve Bayes, NN = Neural networks, RF = Random forest, SVM = Support Vector Machine\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:5.0pt;margin-right:0cm;margin-bottom:10.0pt;margin-left:0cm;line-height:normal;font-size:13px;font-family:\"Calibri\",sans-serif;margin:0cm;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e"},{"header":"Discussion","content":"\u003cp\u003eThis scoping review provides a synthesis of AI applications across sports medicine, and demonstrates that, although methodological development has accelerated in recent years, most studies remain in an early developmental stage. Artificial intelligence has been widely applied for injury prediction, diagnostic imaging, and recovery estimation across diverse athletic and clinical populations, mostly within orthopaedics and neurology. Despite frequently high reported performance metrics, the literature is characterized by substantial heterogeneity in model selection, data modalities, outcome definitions, and validation procedures. Most studies relied on retrospective or observational prospective datasets and internal validation methods, whereas external or temporal validation and prospective prevention or intervention frameworks were rare. Consequently, the current evidence base does not yet support routine clinical integration of AI-driven decision tools in sports medicine.\u003c/p\u003e \u003cp\u003eAlthough many models demonstrated strong discriminative performance, which often achieved AUC values\u0026thinsp;\u0026ge;\u0026thinsp;0.80, these findings must be interpreted in the context of important methodological limitations. High within-sample accuracy suggests that AI can effectively identify patterns associated with injury risk, recovery trajectories, or RTS potential. However, the vast majority of studies performed validation within the same dataset, typically through internal cross-validation or train-test splits. Only three studies employed external datasets to assess generalizability [\u003cspan additionalcitationids=\"CR25\" citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e]. This represents a critical methodological limitation, as internal validation tends to overestimate model performance and fails to account for differences in population characteristics, data collection methods, or sporting environments [\u003cspan citationid=\"CR105\" class=\"CitationRef\"\u003e105\u003c/span\u003e]. Without robust external or temporal validation, the true predictive value and clinical reliability of these models remain uncertain. Accordingly, the literature reflects predominantly early-stage model development, with limited progression toward external validation, prospective integration, or demonstrated impact on clinical decision-making. Future studies should prioritize multi-center external validation across teams, seasons, and demographic groups, to evaluate whether reported performance translates into meaningful clinical utility.\u003c/p\u003e \u003cp\u003eWhile AI-driven prediction models have been reported with strong retrospective accuracy, only Dandriex et al. [\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e] attempted to integrate predictions into a prospective, feedback-based prevention strategy, in which daily individualized feedback was provided to track-and-field athletes based on self-reported wellness data. However, adherence was low (average daily response rate of 37%), and no significant association with injury burden was observed, although a modest protective effect was suggested among participants with at least 9% response rate [\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e]. In addition to predictive frameworks, a small number of studies have integrated AI directly into structured rehabilitation programs. For example, one randomized controlled trial evaluated an AI-based assessment and correction system after ACL reconstruction [\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e], which demonstrated improvements in functional outcomes and rehabilitation adherence, while another study applied AI and virtual reality technology within athlete rehabilitation training [\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e]. These findings illustrate both the potential and the current limitations of AI-supported frameworks, namely, information alone does not yield benefit unless it is coupled with consistent athlete engagement, integration into clinical or training workflows, and actionable feedback mechanisms capable of influencing real-word decision-making.\u003c/p\u003e \u003cp\u003eSports injuries are inherently multifactorial, which arise from complex interactions between training load, biomechanics, physical fitness, psychological status, and contextual factors such as playing surface and competition demands [\u003cspan citationid=\"CR106\" class=\"CitationRef\"\u003e106\u003c/span\u003e, \u003cspan citationid=\"CR107\" class=\"CitationRef\"\u003e107\u003c/span\u003e]. Consequently, models that rely solely on single wellness or workload metrics are unlikely to capture the full spectrum of injury risk. This highlights the need for multimodal data integration that combines these factors to better reflect the complexity of athletic performance and health [\u003cspan citationid=\"CR108\" class=\"CitationRef\"\u003e108\u003c/span\u003e]. In the context of sports medicine, models intended to inform RTS decisions or reinjury risk estimation must also be interpretable, to allow stakeholders to understand which variables drive predictions and how they align with established clinical reasoning [\u003cspan citationid=\"CR108\" class=\"CitationRef\"\u003e108\u003c/span\u003e]. The growing use of high-performing yet opaque black-box models, such as DNNs, poses a barrier to practical implementation, as limited explainability can erode user confidence and hinder clinical decision-making [\u003cspan citationid=\"CR109\" class=\"CitationRef\"\u003e109\u003c/span\u003e]. Accordingly, development of AI frameworks that balance predictive strength with transparency will be crucial to support actionable and trustworthy decision support. Future research should extend beyond prediction to design and evaluate controlled, prospective, decision-driven systems that integrate real-time recommendations and test whether AI-supported interventions can meaningfully reduce injury incidence or improve recovery outcomes [\u003cspan citationid=\"CR110\" class=\"CitationRef\"\u003e110\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eOverall, studies that evaluate the capabilities of LLMs in sports medicine suggest that these tools can generate generally accurate and informative responses, particularly for patient education. However, two key concerns were identified. Firstly, Sparks et al. [\u003cspan citationid=\"CR88\" class=\"CitationRef\"\u003e88\u003c/span\u003e] reported that LLM outputs often lacked sufficient detail with regard to risk factors and treatment options. Secondly, Villarreal-Espinosa et al. [\u003cspan citationid=\"CR96\" class=\"CitationRef\"\u003e96\u003c/span\u003e] found that two of ten responses about ACL surgery did not reach a very accurate rating, and that 80% responses were reproducible over time. In addition, LLMs are inherently susceptible to hallucinations, distribution shifts between training data and real-world use, and potential instability of output, all of which may further undermine their reliability in clinical athletic contexts [\u003cspan additionalcitationids=\"CR112\" citationid=\"CR111\" class=\"CitationRef\"\u003e111\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR113\" class=\"CitationRef\"\u003e113\u003c/span\u003e]. These findings highlight the potential risk that patients may receive incomplete, inaccurate, or inconsistent information. Taken together, LLMs have serve as accessible adjunct educational tools, but current evidence does not support unsupervised clinical deployment. At present, their use should remain supervised by clinicians, particularly when addressing diagnosis, surgical decision-making, or RTS guidance. Future research should focus on benchmarking LLM performance against verified clinical standards and explore how these tools can be safely embedded into patient communication and rehabilitation pathways without compromission information accuracy.\u003c/p\u003e \u003cp\u003eImage and diagnostic AI applications showed promise in accuracy for identification of ligament injuries, bone fractures, and concussion-related imaging patterns. These approaches leverage automated feature extraction from radiological or video data, which reduces reliance on manual interpretation [\u003cspan citationid=\"CR114\" class=\"CitationRef\"\u003e114\u003c/span\u003e]. However, most studies were limited by small sample size, and lack of external or multi-center validation, thus restricting clinical applicability [\u003cspan citationid=\"CR115\" class=\"CitationRef\"\u003e115\u003c/span\u003e]. Furthermore, image-based models often function as black boxes, with limited explainability of which image features drive decisions, which underscores the need for interpretable visualization methods to support clinical implementation.\u003c/p\u003e \u003cp\u003eAcross studies in which ML models were used alongside traditional regression approaches, ML algorithms demonstrated higher discriminative performance. However, these studies were limited to within-sample or internally validated analyses, and formal benchmarking with strict comparisons between methods was rare. Consequently, although ML models may offer incremental gains in discrimination, it remains unclear whether these improvements translate into superior calibration, generalizability, or meaningful enhancement of clinical decision-making. Future research should therefore include structured comparative evaluations that assess not only discrimination but also calibration, interpretability, and net clinical benefit to determine whether increased algorithmic complexity provides practical advantages over established biostatistical methods.\u003c/p\u003e \u003cp\u003eAcross studies, substantial model heterogeneity was observed, with each investigation employing diverse algorithms, feature sets, and outcome definitions. This diversity underscores the exploratory nature and limits consensus on optimal model families or architectures for specific sports or data types [\u003cspan citationid=\"CR116\" class=\"CitationRef\"\u003e116\u003c/span\u003e]. In parallel, the generalizability of existing models remains uncertain, as most datasets were small, single-site, and male-dominant, with minimal inclusion of female, youth, or para-sport athletes and limited representation outside Europe and North America leagues[\u003cspan citationid=\"CR105\" class=\"CitationRef\"\u003e105\u003c/span\u003e]. These sampling biases restrict the broader applicability of reported findings. Furthermore, the validity of any AI model ultimately depends on the quality of data input [\u003cspan citationid=\"CR117\" class=\"CitationRef\"\u003e117\u003c/span\u003e]. Inconsistent data collection methods, and missing contextual variables can all undermine predictive accuracy, regardless of algorithmic sophistication [\u003cspan citationid=\"CR117\" class=\"CitationRef\"\u003e117\u003c/span\u003e]. Collectively, this methodological variability reinforces that the field remains in developmental phase, in which foundational issues of data standardization, and reporting transparency must be addressed before reliable large-scale implementation can be achieved. Addressing these foundational issues through standardized data handling, and transparent reporting will be essential to build robust, and trustworthy AI systems in sports medicine.\u003c/p\u003e \u003cp\u003eThis review indicates that most current applications of AI and ML in sports medicine remain in an early developmental exploratory stage and should be interpreted cautiously in clinical settings. Consequently, these models should not yet be relied upon to independently guide clinical decision‑making, diagnosis, prognosis, or RTS recommendations. At present, many models rely on retrospective datasets, lack external validation, and have not undergone evaluation in real‑world clinical workflows, which limits their immediate clinical reliability and generalizability. Furthermore, the majority of the included studies focused on orthopaedics or neurology, hence the generalizability to other specialties remains low. The main contribution of this review was to provide clinicians and researchers with a clearer understanding of the current maturity and limitations of AI and ML technologies within the field. By synthesizing the available evidence, this work aims to support more informed, critical appraisal of algorithm‑generated outputs and to help clinicians recognize when such tools may complement rather than replace clinical reasoning. Furthermore, the review outlines priority areas in which rigorous model validation, prospective study designs, bias assessment, and implementation research are essential. Addressing these gaps will be crucial to ensure that future AI‑ and ML‑based tools can transition safely and effectively from experimental settings to practical, patient‑centered clinical application.\u003c/p\u003e \u003cp\u003eThis study has several limitations. The included studies varied widely in sport, level of play, sample size, data modality, outcomes, and performance metrics which did not allow for a quantitative synthesis and limits comparison across models. Therefore, it was determined to synthesize narratively to emphasize patterns rather than pool effects. In addition, due to the heterogeneity of included studies, no risk of bias or quality assessment was performed. Moreover, the predominance of internal validation limits the generalizability of findings. Thus, results must be interpreted cautiously. Furthermore, publication bias might skew the picture of the accurate results of included studies, and true performance of AI models might not be captured. Given the rapid growth of this field, relevant studies may have been published after our search and were therefore not captured. Engineering-led studies focused solely on algorithmic development were excluded; therefore, the technical foundation of AI methods may be underrepresented. To organize this heterogeneous literature, AI applications were pragmatically grouped into four mutually exclusive categories. While this approach facilitates synthesis, it simplifies the inherently multidimensional nature of AI systems, which often vary substantially in data sources, modelling approaches, and validation strategies within the same clinical task. Accordingly, the categories should be interpreted as heuristic groupings to support interpretation rather than rigid distinctions between fundamentally different AI methodologies.\u003c/p\u003e"},{"header":"Conclusion","content":"\u003cp\u003eThe use of AI applications in sports medicine demonstrate strong within-sample discriminative performance for injury risk, recovery, and diagnostic imaging, yet most remain limited to retrospective analysis with limited external validation and minimal evidence of clinical workflow integration. This review shows that the field is characterized by substantial methodological heterogeneity and limited progression toward prospective implementation. For clinicians within sports medicine, current AI tools should therefore be regarded as exploratory decision-support adjuncts rather than implementation-ready systems.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eCompeting Interests\u003c/strong\u003e\u003cp\u003eAuthor Kristian Samuelsson reports a relationship with Getinge AB that includes: board membership. No other competing interests to declare.\u003c/p\u003e\u003c/p\u003e\u003cp\u003e \u003ch2\u003eConflict of interest disclosure\u003c/h2\u003e \u003cp\u003eAuthor Kristian Samuelsson reports a relationship with Getinge AB that includes: board membership. No other competing interests to declare.\u003c/p\u003e \u003c/p\u003e\u003ch2\u003e \u003cb\u003eEthics statement\u003c/b\u003e \u003c/h2\u003e \u003cp\u003e \u003cstrong\u003eEthical approval\u003c/strong\u003e \u003cp\u003ewas not required for this study as it involved the analysis of previously published literature\u003c/p\u003e \u003c/p\u003e\u003ch2\u003eFunding statement\u003c/h2\u003e \u003cp\u003eThis research received no specific grant from any funding agency in the public, commercial, or not-for-profit sectors.\u003c/p\u003e\u003ch2\u003eAuthor Contribution\u003c/h2\u003e\u003cp\u003eJakob Lindskog drafted the initial version of the manuscript, performed screening and synthesis of data, has approved the final work for publication, and has agreed to be accountable for all aspects of the work.Kristian Heder Ternell has contributed majorly during the drafting of the manuscript, performed screening and synthesis of data, has approved the final work for publication, and has agreed to be accountable for all aspects of the work.Yinan Yu, Ida Lindman and Kristian Samuelsson have contributed during the interpretation of data, made meaningful contributions during the final stages of manuscript drafting, has approved the final work, and has agreed to be accountable for all aspects of the work.Eric Hamrin Senorski has contributed majorly during the drafting of the manuscript, analysis and interpretation of data, is responsible for the design concept, has approved the final work, and has agreed to be accountable for all aspects of the work.\u003c/p\u003e\u003ch2\u003eAcknowledgement\u003c/h2\u003e\u003cp\u003eThe authors thank librarians Kajsa Magnusson and Ann Liljegren for valuable advice and performing of the literature searches. The authors also thank librarian Ida Stadig for her assistance in developing the AI-related search strategy. All librarians are affiliated with the Medical Library, Sahlgrenska University Hospital.\u003c/p\u003e\u003ch2\u003eData Availability\u003c/h2\u003e\u003cp\u003eThis scoping review is based on previously published studies. The data-charting spreadsheet generated during the review is available from the corresponding author on reasonable request.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eAung YYM, Wong DCS, Ting DSW. The promise of artificial intelligence: a review of the opportunities and challenges of artificial intelligence in healthcare. Br Med Bull. 2021;139:4\u0026ndash;15. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1093/bmb/ldab016\u003c/span\u003e\u003cspan address=\"10.1093/bmb/ldab016\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTu SJ, et al. Machine learning is better than surgeons at assessing unicompartmental knee replacement radiographs. Knee. 2024;52:212\u0026ndash;9. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.knee.2024.11.007\u003c/span\u003e\u003cspan address=\"10.1016/j.knee.2024.11.007\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGoh E et al. Large Language Model Influence on Diagnostic Reasoning: A Randomized Clinical Trial. \u003cem\u003eJAMA Netw Open\u003c/em\u003e 7, e2440969 (2024) \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1001/jamanetworkopen.2024.40969\u003c/span\u003e\u003cspan address=\"10.1001/jamanetworkopen.2024.40969\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWallace MB, et al. Impact of Artificial Intelligence on Miss Rate of Colorectal Neoplasia. Gastroenterology. 2022;163:295\u0026ndash;304. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1053/j.gastro.2022.03.007\u003c/span\u003e\u003cspan address=\"10.1053/j.gastro.2022.03.007\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. .e295.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHu W, Razmjooy S. Combining an improved political optimizer with convolutional neural networks for accurate anterior cruciate ligament tear detection in sports injuries. Sci Rep. 2025;15:6862. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1038/s41598-025-91242-2\u003c/span\u003e\u003cspan address=\"10.1038/s41598-025-91242-2\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAllen JH, et al. Predicting early versus late recovery from sport-related concussion using decision tree analysis. J Neurosurg Pediatr. 2023;32:9\u0026ndash;18. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3171/2023.2.Peds2330\u003c/span\u003e\u003cspan address=\"10.3171/2023.2.Peds2330\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDiniz P, et al. Pre-injury performance is most important for predicting the level of match participation after Achilles tendon ruptures in elite soccer players: a study using a machine learning classifier. Knee Surg Sports Traumatol Arthrosc. 2022;30:4225\u0026ndash;37. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s00167-022-07082-4\u003c/span\u003e\u003cspan address=\"10.1007/s00167-022-07082-4\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTricco AC, et al. PRISMA Extension for Scoping Reviews (PRISMA-ScR): Checklist and Explanation. Ann Intern Med. 2018;169:467\u0026ndash;73. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.7326/m18-0850\u003c/span\u003e\u003cspan address=\"10.7326/m18-0850\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMcGowan J, PRESS Peer Review of Electronic Search Strategies, et al. 2015 Guideline Statement. J Clin Epidemiol. 2016;75:40\u0026ndash;6. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.jclinepi.2016.01.021\u003c/span\u003e\u003cspan address=\"10.1016/j.jclinepi.2016.01.021\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/https://doi.org/\u003c/span\u003e\u003cspan address=\"https://doi.org/https://doi.org/\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eOuzzani M, Hammady H, Fedorowicz Z, Elmagarmid A. Rayyan-a web and mobile app for systematic reviews. Syst Rev. 2016;5:210. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1186/s13643-016-0384-4\u003c/span\u003e\u003cspan address=\"10.1186/s13643-016-0384-4\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHopkinson M, et al. Rugby league ball carrier injuries: The relative importance of tackle characteristics during the European Super League. Eur J Sport Sci. 2022;22:269\u0026ndash;78. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1080/17461391.2020.1853817\u003c/span\u003e\u003cspan address=\"10.1080/17461391.2020.1853817\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHwang UJ, Kim JS, Chung KS. Machine Learning Predictions of Subjective Function, Symptoms, and Psychological Readiness at 12 Months After ACL Reconstruction Based on Physical Performance in the Early Rehabilitation Stage: Retrospective Cohort Study. Orthop J Sports Med. 2025;13:23259671251319512. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1177/23259671251319512\u003c/span\u003e\u003cspan address=\"10.1177/23259671251319512\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLu Y, et al. Machine Learning for Predicting Lower Extremity Muscle Strain in National Basketball Association Athletes. Orthop J Sports Med. 2022;10:23259671221111742. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1177/23259671221111742\u003c/span\u003e\u003cspan address=\"10.1177/23259671221111742\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMart\u0026iacute;nez-Gramage J, et al. A Random Forest Machine Learning Framework to Reduce Running Injuries in Young Triathletes. Sens (Basel). 2020;20. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3390/s20216388\u003c/span\u003e\u003cspan address=\"10.3390/s20216388\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRommers N, et al. A Machine Learning Approach to Assess Injury Risk in Elite Youth Football Players. Med Sci Sports Exerc. 2020;52:1745\u0026ndash;51. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1249/mss.0000000000002305\u003c/span\u003e\u003cspan address=\"10.1249/mss.0000000000002305\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGuo L, Cui Z, Loh WP, Shaharudin S. Prediction of ACL injury incidence and analysis of key features in basketball players based on multi-algorithm models. \u003cem\u003ePeerj\u003c/em\u003e 13, e20141 (2025) \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/https://doi.org/10.7717/peerj.20141\u003c/span\u003e\u003cspan address=\"10.7717/peerj.20141\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHwang UJ, Kim JS, Kim KY, Chung KS. Machine learning models for predicting return to sports after anterior cruciate ligament reconstruction: Physical performance in early rehabilitation. Digit Health. 2024;10:20552076241299065. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1177/20552076241299065\u003c/span\u003e\u003cspan address=\"10.1177/20552076241299065\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eNolte K, Gerharz A, Jaitner T, Knicker AJ, Alt T. Finding the needle in the haystack of isokinetic knee data: Random Forest modelling improves information about ACLR-related deficiencies. J Sports Sci. 2025;43:173\u0026ndash;81. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1080/02640414.2024.2435729\u003c/span\u003e\u003cspan address=\"10.1080/02640414.2024.2435729\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChu Y, et al. Machine learning to predict sports-related concussion recovery using clinical data. Ann Phys Rehabil Med. 2022;65:101626. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.rehab.2021.101626\u003c/span\u003e\u003cspan address=\"10.1016/j.rehab.2021.101626\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFerris LM et al. Predictive Accuracy of the Sport Concussion Assessment Tool 3 and Vestibular/Ocular-Motor Screening, Individually and In Combination: A National Collegiate Athletic Association-Department of Defense Concussion Assessment, Research and Education Consortium Analysis. \u003cem\u003eAm J Sports Med\u003c/em\u003e 49, 1040\u0026ndash;1048 (2021) \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1177/0363546520988098\u003c/span\u003e\u003cspan address=\"10.1177/0363546520988098\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJacob D, et al. Towards defining biomarkers to evaluate concussions using virtual reality and a moving platform (BioVRSea). Sci Rep. 2022;12:8996. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1038/s41598-022-12822-0\u003c/span\u003e\u003cspan address=\"10.1038/s41598-022-12822-0\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMaxin AJ, Whelan BM, Levitt MR, McGrath LB, Harmon KG. Smartphone-Based Pupillometry Using Machine Learning for the Diagnosis of Sports-Related Concussion. Diagnostics (Basel). 2024;14(23):2723. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/https://doi.org/10.3390/diagnostics14232723\u003c/span\u003e\u003cspan address=\"10.3390/diagnostics14232723\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. (no pagination).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eThanjavur K, Hristopulos DT, Babul A, Yi KM, Virji-Babul ND. Learning Recurrent Neural Network for Concussion Classification in Adolescents Using Raw Electroencephalography Signals: Toward a Minimal Number of Sensors. Front Hum Neurosci. 2021;15:734501. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3389/fnhum.2021.734501\u003c/span\u003e\u003cspan address=\"10.3389/fnhum.2021.734501\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRichter C, et al. Cross-validation of a machine learning algorithm that determines anterior cruciate ligament rehabilitation status and evaluation of its ability to predict future injury. Sports Biomech. 2023;22:91\u0026ndash;101. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1080/14763141.2021.1947358\u003c/span\u003e\u003cspan address=\"10.1080/14763141.2021.1947358\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWang Y, Lee S. Development and validation of a machine learning model for non-contact injury prediction based on lower limb strength asymmetry in professional football. Sci. 2026;16:4456. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1038/s41598-025-34468-4\u003c/span\u003e\u003cspan address=\"10.1038/s41598-025-34468-4\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. https://doi.org/.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eNose-Ogura S, et al. Development and validation of a pre-screening tool for early detection of low bone mineral density in female athletes (PreST-LBMD). Phys Sports Med. 2025. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/https://doi.org/10.1080/00913847.2025.2586448\u003c/span\u003e\u003cspan address=\"10.1080/00913847.2025.2586448\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDandrieux PE, et al. Association between the use of daily injury risk estimation feedback (I-REF) based on machine learning techniques and injuries in athletics (track and field): results of a prospective cohort study over an athletics season. BMJ Open Sport Exerc Med. 2025;11:e002331. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1136/bmjsem-2024-002331\u003c/span\u003e\u003cspan address=\"10.1136/bmjsem-2024-002331\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhu T, et al. Evaluation of the Efficacy of an Artificial Intelligence-Based Assessment and Correction System in the Rehabilitation of Patients Following Anterior Cruciate Ligament Reconstruction Surgery. J. 2026;15:10. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/https://doi.org/10.3390/jcm15020575\u003c/span\u003e\u003cspan address=\"10.3390/jcm15020575\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSong B, Tuo PX. Application of Artificial Intelligence and Virtual Reality Technology in the Rehabilitation Training of Track and Field Athletes. \u003cem\u003eWirel Commun Mob Comput\u003c/em\u003e 2022, (2022) \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/https://doi.org/10.1155/2022/9828199\u003c/span\u003e\u003cspan address=\"10.1155/2022/9828199\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAbasi A, Nazari A, Moezy A, Fatemi Aghda. SA Machine learning models for reinjury risk prediction using cardiopulmonary exercise testing (CPET) data: optimizing athlete recovery. BioData Min. 2025;18:16. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1186/s13040-025-00431-2\u003c/span\u003e\u003cspan address=\"10.1186/s13040-025-00431-2\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAoyagi M et al. Identifying Acute Lumbar Spondylolysis in Young Athletes with Low Back Pain: Retrospective Classification and Regression Tree Analysis. \u003cem\u003eSpine (Phila Pa\u003c/em\u003e 1976) 46, 1026\u0026ndash;1032 (2021) \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1097/brs.0000000000003922\u003c/span\u003e\u003cspan address=\"10.1097/brs.0000000000003922\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAyala F, et al. A Preventive Model for Hamstring Injuries in Professional Soccer: Learning Algorithms. Int J Sports Med. 2019;40:344\u0026ndash;53. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1055/a-0826-1955\u003c/span\u003e\u003cspan address=\"10.1055/a-0826-1955\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBazarian JJ et al. Validation of a Machine Learning Brain Electrical Activity-Based Index to Aid in Diagnosing Concussion Among Athletes. \u003cem\u003eJAMA Netw Open\u003c/em\u003e 4, e2037349 (2021) \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1001/jamanetworkopen.2020.37349\u003c/span\u003e\u003cspan address=\"10.1001/jamanetworkopen.2020.37349\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBergeron MF, et al. Machine Learning in Modeling High School Sport Concussion Symptom Resolve. Med Sci Sports Exerc. 2019;51:1362\u0026ndash;71. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1249/mss.0000000000001903\u003c/span\u003e\u003cspan address=\"10.1249/mss.0000000000001903\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBriand J, Deguire S, Gaudet S, Bieuzen F. Monitoring Variables Influence on Random Forest Models to Forecast Injuries in Short-Track Speed Skating. Front Sports Act Living. 2022;4:896828. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3389/fspor.2022.896828\u003c/span\u003e\u003cspan address=\"10.3389/fspor.2022.896828\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCalder\u0026oacute;n-D\u0026iacute;az M, et al. Explainable Machine Learning Techniques to Predict Muscle Injuries in Professional Soccer Players through Biomechanical Analysis. Sens (Basel). 2023;24. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3390/s24010119\u003c/span\u003e\u003cspan address=\"10.3390/s24010119\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCao C, Tutwiler RL, Slobounov S. Automatic classification of athletes with residual functional deficits following concussion by means of EEG signal using support vector machine. IEEE Trans Neural Syst Rehabil Eng. 2008;16:327\u0026ndash;35. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1109/tnsre.2008.918422\u003c/span\u003e\u003cspan address=\"10.1109/tnsre.2008.918422\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCastellanos J, et al. Predicting Risk of Sport-Related Concussion in Collegiate Athletes and Military Cadets: A Machine Learning Approach Using Baseline Data from the CARE Consortium Study. Sports Med. 2021;51:567\u0026ndash;79. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s40279-020-01390-w\u003c/span\u003e\u003cspan address=\"10.1007/s40279-020-01390-w\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChen X, Liu YA, Classification. Method for Thoracolumbar Vertebral Fractures due to Basketball Sports Injury Based on Deep Learning. \u003cem\u003eComput Math Methods Med\u003c/em\u003e 2022, 8747487 (2022) \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1155/2022/8747487\u003c/span\u003e\u003cspan address=\"10.1155/2022/8747487\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDe la Fuente C, et al. Preseason multiple biomechanics testing and dimension reduction for injury risk surveillance in elite female soccer athletes: short-communication. Sci Med Footb. 2023;7:183\u0026ndash;8. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1080/24733938.2022.2075558\u003c/span\u003e\u003cspan address=\"10.1080/24733938.2022.2075558\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ede Leeuw AW, van der Zwaard S, van Baar R. Knobbe A Personalized machine learning approach to injury monitoring in elite volleyball players. Eur J Sport Sci. 2022;22:511\u0026ndash;20. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1080/17461391.2021.1887369\u003c/span\u003e\u003cspan address=\"10.1080/17461391.2021.1887369\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDiCesare CA, et al. Machine Learning Classification of Verified Head Impact Exposure Strengthens Associations with Brain Changes. Ann Biomed Eng. 2020;48:2772\u0026ndash;82. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s10439-020-02662-2\u003c/span\u003e\u003cspan address=\"10.1007/s10439-020-02662-2\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDiniz P, et al. High specificity of an AI-powered framework in cross-checking male professional football anterior cruciate ligament tear reports in public databases. Knee Surg Sports Traumatol Arthrosc. 2025;33:3478\u0026ndash;88. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1002/ksa.12571\u003c/span\u003e\u003cspan address=\"10.1002/ksa.12571\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eElkin PL, et al. Artificial Intelligence: Bayesian versus Heuristic Method for Diagnostic Decision Support. Appl Clin Inf. 2018;9:432\u0026ndash;9. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e/https://doi.org/10.1055/s-0038-1656547\u003c/span\u003e\u003cspan address=\"/10.1055/s-0038-1656547\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. https://doi.org.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eEskofier BM, Kraus M, Worobets JT, Stefanyshyn DJ, Nigg BM. Pattern classification of kinematic and kinetic running data to distinguish gender, shod/barefoot and injury groups with feature ranking. Comput Methods Biomech Biomed Engin. 2012;15:467\u0026ndash;74. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1080/10255842.2010.542153\u003c/span\u003e\u003cspan address=\"10.1080/10255842.2010.542153\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eEvans SL, et al. Non-contact lower limb injuries in Rugby Union: A two-year pattern recognition analysis of injury risk factors. PLoS ONE. 2024;19:e0307287. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1371/journal.pone.0307287\u003c/span\u003e\u003cspan address=\"10.1371/journal.pone.0307287\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFarhadian M, Torkaman S, Mojarad F. Random forest algorithm to identify factors associated with sports-related dental injuries in 6 to 13-year-old athlete children in Hamadan, Iran-2018 -a cross-sectional study. BMC Sports Sci Med Rehabil. 2020;12:69. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1186/s13102-020-00217-5\u003c/span\u003e\u003cspan address=\"10.1186/s13102-020-00217-5\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFreitas DN, et al. Predicting noncontact injuries of professional football players using machine learning. PLoS ONE. 2025;20:e0315481. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1371/journal.pone.0315481\u003c/span\u003e\u003cspan address=\"10.1371/journal.pone.0315481\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGarcia GP, et al. A Data-Driven Approach to Unlikely, Possible, Probable, and Definite Acute Concussion Assessment. J Neurotrauma. 2019;36:1571\u0026ndash;83. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1089/neu.2018.6098\u003c/span\u003e\u003cspan address=\"10.1089/neu.2018.6098\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGaudet S, Begon M, Tremblay J. Cluster analysis using physical performance and self-report measures to identify shoulder injury in overhead female athletes. J Sci Med Sport. 2019;22:269\u0026ndash;74. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.jsams.2018.09.224\u003c/span\u003e\u003cspan address=\"10.1016/j.jsams.2018.09.224\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGiorgino R, et al. Google Bard and ChatGPT in Orthopedics: Which Is the Better Doctor in Sports Medicine and Pediatric Orthopedics? The Role of AI in Patient Education. Diagnostics (Basel). 2024;14. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3390/diagnostics14121253\u003c/span\u003e\u003cspan address=\"10.3390/diagnostics14121253\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGirard CI, et al. Classifiers of anterior cruciate ligament status in female and male adolescents using return-to-activity criteria. Knee Surg Sports Traumatol Arthrosc. 2025;33:1633\u0026ndash;44. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/https://doi.org/10.1002/ksa.12462\u003c/span\u003e\u003cspan address=\"10.1002/ksa.12462\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGoggins L, et al. Detecting Injury Risk Factors with Algorithmic Models in Elite Women's Pathway Cricket. Int J Sports Med. 2022;43:344\u0026ndash;9. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1055/a-1502-6824\u003c/span\u003e\u003cspan address=\"10.1055/a-1502-6824\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGultekin O, et al. Evaluating DeepResearch and DeepThink in anterior cruciate ligament surgery patient education: ChatGPT-4o excels in comprehensiveness, DeepSeek R1 leads in clarity and readability of orthopaedic information. Knee Surg Sports Traumatol Arthrosc. 2025;33:3025\u0026ndash;31. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/https://doi.org/10.1002/ksa.12711\u003c/span\u003e\u003cspan address=\"10.1002/ksa.12711\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHecksteden A, et al. Forecasting football injuries by combining screening, monitoring and machine learning. Sci Med Footb. 2023;7:214\u0026ndash;28. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e/https://doi.org/10.1080/24733938.2022.2095006\u003c/span\u003e\u003cspan address=\"/10.1080/24733938.2022.2095006\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. https://doi.org.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHenriquez M, Sumner J, Faherty M, Sell T, Bent B. Machine Learning to Predict Lower Extremity Musculoskeletal Injury Risk in Student Athletes. Front Sports Act Living. 2020;2:576655. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3389/fspor.2020.576655\u003c/span\u003e\u003cspan address=\"10.3389/fspor.2020.576655\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHsu PY, Hsu YC, Liu HL, Fong Kao W, Lin KY. An Acute Kidney Injury Prediction Model for 24-hour Ultramarathon Runners. J Hum Kinet. 2022;84:103\u0026ndash;11. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.2478/hukin-2022-0070\u003c/span\u003e\u003cspan address=\"10.2478/hukin-2022-0070\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHuang Y, et al. A novel lower extremity non-contact injury risk prediction model based on multimodal fusion and interpretable machine learning. Front Physiol. 2022;13:937546. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3389/fphys.2022.937546\u003c/span\u003e\u003cspan address=\"10.3389/fphys.2022.937546\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHuang Y, et al. The impact of sport-specific physical fitness change patterns on lower limb non-contact injury risk in youth female basketball players: a pilot study based on field testing and machine learning. Front Physiol. 2023;14:1182755. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3389/fphys.2023.1182755\u003c/span\u003e\u003cspan address=\"10.3389/fphys.2023.1182755\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJauhiainen S, et al. Predicting ACL Injury Using Machine Learning on Data From an Extensive Screening Test Battery of 880 Female Elite Athletes. Am J Sports Med. 2022;50:2917\u0026ndash;24. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1177/03635465221112095\u003c/span\u003e\u003cspan address=\"10.1177/03635465221112095\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJauhiainen S, et al. New Machine Learning Approach for Detection of Injury Risk Factors in Young Team Sport Athletes. Int J Sports Med. 2021;42:175\u0026ndash;82. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1055/a-1231-5304\u003c/span\u003e\u003cspan address=\"10.1055/a-1231-5304\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJia P, Xu Y, Research on Image Recognition of Gymnastics Sports Injuries Based on Deep Learning. \u003cem\u003eComput Intell Neurosci\u003c/em\u003e 2022, 8987006 (2022) \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1155/2022/8987006\u003c/span\u003e\u003cspan address=\"10.1155/2022/8987006\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKarbalaie A, et al. Beyond self-reports after anterior cruciate ligament injury - machine learning methods for classifying and identifying movement patterns related to fear of re-injury. J Sports Sci. 2026;44:342\u0026ndash;56. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/https://doi.org/10.1080/02640414.2025.2578584\u003c/span\u003e\u003cspan address=\"10.1080/02640414.2025.2578584\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKolodziej M, et al. Predictive modeling of lower extremity injury risk in male elite youth soccer players using least absolute shrinkage and selection operator regression. Scand J Med Sci Sports. 2023;33:1021\u0026ndash;33. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1111/sms.14322\u003c/span\u003e\u003cspan address=\"10.1111/sms.14322\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKunze KN, et al. Machine Learning Algorithms Predict Functional Improvement After Hip Arthroscopy for Femoroacetabular Impingement Syndrome in Athletes. J Bone Joint Surg Am. 2021;103:1055\u0026ndash;62. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.2106/jbjs.20.01640\u003c/span\u003e\u003cspan address=\"10.2106/jbjs.20.01640\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKunze KN, et al. Application of Machine Learning Algorithms to Predict Clinically Meaningful Improvement After Arthroscopic Anterior Cruciate Ligament Reconstruction. Orthop J Sports Med. 2021;9:23259671211046575. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1177/23259671211046575\u003c/span\u003e\u003cspan address=\"10.1177/23259671211046575\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLipps Lene C, Frere J, Weissland T. Machine learning in knee injury sequelae detection: Unravelling the role of psychological factors and preventing long-term sequelae. J Exp Orthop. 2024;11:e70081. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1002/jeo2.70081\u003c/span\u003e\u003cspan address=\"10.1002/jeo2.70081\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eL\u0026oacute;pez-Valenciano A, et al. A Preventive Model for Muscle Injuries: A Novel Approach based on Learning Algorithms. Med Sci Sports Exerc. 2018;50:915\u0026ndash;27. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1249/mss.0000000000001535\u003c/span\u003e\u003cspan address=\"10.1249/mss.0000000000001535\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eL\u0026ouml;vdal SS, Den Hartigh RJR, Azzopardi G. Injury Prediction in Competitive Runners With Machine Learning. Int J Sports Physiol Perform. 2021;16:1522\u0026ndash;31. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1123/ijspp.2020-0518\u003c/span\u003e\u003cspan address=\"10.1123/ijspp.2020-0518\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMcBee JC, et al. Assessing ChatGPT's Competency in Addressing Interdisciplinary Inquiries on Chatbot Uses in Sports Rehabilitation: Simulation Study. JMIR Med Educ. 2024;10:e51157. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.2196/51157\u003c/span\u003e\u003cspan address=\"10.2196/51157\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMurray NG, et al. Single-Task and Dual-Task Gait Performance After Sport-Related Concussion: A Machine Learning Statistical Approach. Sports Health. 2025;17:666\u0026ndash;77. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1177/19417381241264289\u003c/span\u003e\u003cspan address=\"10.1177/19417381241264289\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eNechita LC, et al. A Resting ECG Screening Protocol Improved with Artificial Intelligence for the Early Detection of Cardiovascular Risk in Athletes. Diagnostics (Basel). 2025;15. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3390/diagnostics15040477\u003c/span\u003e\u003cspan address=\"10.3390/diagnostics15040477\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eNonnenmacher L, Fischer M, Kaderali L, Wassilew GI. Predicting early return to sport after periacetabular osteotomy: a machine-learning approach. Bone Jt Open. 2025;6:33\u0026ndash;42. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1302/2633-1462.66.bjo-2024-0257.r1\u003c/span\u003e\u003cspan address=\"10.1302/2633-1462.66.bjo-2024-0257.r1\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. https://doi.org/.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eOhlsen SM, Pirkle SB, Yang J, Gee AO. Do ChatGPT and Gemini Provide Appropriate Recommendations for Anterior Cruciate Ligament and Isolated Meniscal Injuries? \u003cem\u003eCureus\u003c/em\u003e 17, e94315 (2025) \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/https://doi.org/10.7759/cureus.94315\u003c/span\u003e\u003cspan address=\"10.7759/cureus.94315\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eOliver JL, et al. Using machine learning to improve our understanding of injury risk and prediction in elite male youth football players. J Sci Med Sport. 2020;23:1044\u0026ndash;8. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.jsams.2020.04.021\u003c/span\u003e\u003cspan address=\"10.1016/j.jsams.2020.04.021\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eOzbek EA, et al. ChatGPT Can Offer At Least Satisfactory Responses to Common Patient Questions Regarding Hip Arthroscopy. Arthroscopy. 2025;41:1806\u0026ndash;27. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.arthro.2024.08.036\u003c/span\u003e\u003cspan address=\"10.1016/j.arthro.2024.08.036\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/https://doi.org/\u003c/span\u003e\u003cspan address=\"https://doi.org/https://doi.org/\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eP\u0026eacute;rez-Contreras J, et al. Are Countermovement Jump Variables Indicators of Injury Risk in Professional Soccer Players? A Machine Learning Approach. Appl Sci-Basel. 2025;15. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/https://doi.org/10.3390/app152312721\u003c/span\u003e\u003cspan address=\"10.3390/app152312721\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePiłka T, Grzelak B, Sadurska A, G\u0026oacute;recki T, Dyczkowski K. Predicting Injuries in Football Based on Data Collected from GPS-Based Wearable Sensors. Sens (Basel). 2023;23. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3390/s23031227\u003c/span\u003e\u003cspan address=\"10.3390/s23031227\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eQuinn M et al. Artificial Intelligence Large Language Models Address Anterior Cruciate Ligament Reconstruction: Superior Clarity and Completeness by Gemini Compared With ChatGPT-4 in Response to American Academy of Orthopaedic Surgeons Clinical Practice Guidelines. \u003cem\u003eArthroscopy\u003c/em\u003e 41, 2002\u0026ndash;2008 (2025) \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.arthro.2024.09.020\u003c/span\u003e\u003cspan address=\"10.1016/j.arthro.2024.09.020\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRossi A, Pappalardo L, Filetti C, Cintia P. Blood sample profile helps to injury forecasting in elite soccer players. Sport Sci Health. 2023;19:285\u0026ndash;96. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s11332-022-00932-1\u003c/span\u003e\u003cspan address=\"10.1007/s11332-022-00932-1\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. https://doi.org/.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRobinson M, Johnson AM, Fischer LK. MacKenzie HM Two Symptoms to Triage Acute Concussions: Using Decision Tree Modeling to Predict Prolonged Recovery After a Concussion. Am J Phys Med Rehabil. 2022;101:135\u0026ndash;8. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1097/phm.0000000000001754\u003c/span\u003e\u003cspan address=\"10.1097/phm.0000000000001754\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRuddy JD, et al. Predictive Modeling of Hamstring Strain Injuries in Elite Australian Footballers. Med Sci Sports Exerc. 2018;50:906\u0026ndash;14. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1249/mss.0000000000001527\u003c/span\u003e\u003cspan address=\"10.1249/mss.0000000000001527\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRuiz-P\u0026eacute;rez I, et al. A Field-Based Approach to Determine Soft Tissue Injury Risk in Elite Futsal Using Novel Machine Learning Techniques. Front Psychol. 2021;12:610210. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3389/fpsyg.2021.610210\u003c/span\u003e\u003cspan address=\"10.3389/fpsyg.2021.610210\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSaghafi B, et al. Quantifying the Association between White Matter Integrity Changes and Subconcussive Head Impact Exposure from a Single Season of Youth and High School Football using 3D Convolutional Neural Networks. Proc SPIE Int Soc Opt Eng. 2018;10575. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1117/12.2293023\u003c/span\u003e\u003cspan address=\"10.1117/12.2293023\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSaglam S, et al. Comparative evaluation of artificial intelligence models GPT-4 and GPT-3.5 in clinical decision-making in sports surgery and physiotherapy: a cross-sectional study. BMC Med Inf Decis Mak. 2025;25:163. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/https://doi.org/10.1186/s12911-025-02996-8\u003c/span\u003e\u003cspan address=\"10.1186/s12911-025-02996-8\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSchulc A, et al. Identifying Anterior Cruciate Ligament Injuries Through Automated Video Analysis of In-Game Motion Patterns. Orthop J Sports Med. 2024;12:23259671231221579. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1177/23259671231221579\u003c/span\u003e\u003cspan address=\"10.1177/23259671231221579\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eShibata Y, et al. Prediction of quadriceps strength recovery after anterior cruciate ligament reconstruction with a hamstring autograft: Decision tree analysis. J Orthop Sci. 2019;24:301\u0026ndash;5. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.jos.2018.10.007\u003c/span\u003e\u003cspan address=\"10.1016/j.jos.2018.10.007\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. https://doi.org/.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSparks CA, et al. ChatGPT Is Moderately Accurate in Providing a General Overview of Orthopaedic Conditions. JB JS Open Access. 2024;9. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.2106/jbjs.Oa.23.00129\u003c/span\u003e\u003cspan address=\"10.2106/jbjs.Oa.23.00129\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eStirling CE, Pavlovic N, Manske SL, Walker REA, Boyd SK. Longitudinal Progression of Traumatic Bone Marrow Lesions Following Anterior Cruciate Ligament Injury: Associations With Knee Pain and Concomitant Injuries. J Orthop Res. 2025;43:2178\u0026ndash;87. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/https://doi.org/10.1002/jor.70067\u003c/span\u003e\u003cspan address=\"10.1002/jor.70067\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTamez-Pe\u0026ntilde;a J, et al. Post-concussive mTBI in Student Athletes: MRI Features and Machine Learning. Front Neurol. 2021;12:734329. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3389/fneur.2021.734329\u003c/span\u003e\u003cspan address=\"10.3389/fneur.2021.734329\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTedesco S, et al. Motion Sensors-Based Machine Learning Approach for the Identification of Anterior Cruciate Ligament Gait Patterns in On-the-Field Activities in Rugby Players. Sens (Basel). 2020;20. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3390/s20113029\u003c/span\u003e\u003cspan address=\"10.3390/s20113029\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTsilimigkras T, Kakkos I, Matsopoulos GK, Bogdanis GC. Enhancing Sports Injury Risk Assessment in Soccer Through Machine Learning and Training Load Analysis. J Sports Sci Med. 2024;23:537\u0026ndash;47. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.52082/jssm.2024.537\u003c/span\u003e\u003cspan address=\"10.52082/jssm.2024.537\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eUsami S, et al. A new neural network model that detects graft ruptures and contralateral anterior cruciate ligament injuries. Knee Surg Sports Traumatol Arthrosc. 2024;32:872\u0026ndash;80. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1002/ksa.12123\u003c/span\u003e\u003cspan address=\"10.1002/ksa.12123\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVallance E, Sutton-Charani N, Imoussaten A, Montmain J, Perrey S. Combining Internal- and External-Training-Loads to Predict Non-Contact Injuries in Soccer. Appl Sci-Basel. 2020;10. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/https://doi.org/10.3390/app10155261\u003c/span\u003e\u003cspan address=\"10.3390/app10155261\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eValle X, et al. Return to Play Prediction Accuracy of the MLG-R Classification System for Hamstring Injuries in Football Players: A Machine Learning Approach. Sports Med. 2022;52:2271\u0026ndash;82. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s40279-022-01672-5\u003c/span\u003e\u003cspan address=\"10.1007/s40279-022-01672-5\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVillarreal-Espinosa JB, et al. Accuracy assessment of ChatGPT responses to frequently asked questions regarding anterior cruciate ligament surgery. Knee. 2024;51:84\u0026ndash;92. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.knee.2024.08.014\u003c/span\u003e\u003cspan address=\"10.1016/j.knee.2024.08.014\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWeng YH, Chang PH, Wu KP, Lin JJ, Huang TS. Enhanced personalized prediction of baseball-related upper extremity injuries through novel features and explainable artificial intelligence. J Sports Sci. 2025;43:719\u0026ndash;27. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1080/02640414.2025.2474328\u003c/span\u003e\u003cspan address=\"10.1080/02640414.2025.2474328\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYates LC, et al. Developing a multivariate model for the prediction of concussion recovery in sportspeople: a machine learning approach. BMJ Open Sport Exerc Med. 2025;11:e002090. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1136/bmjsem-2024-002090\u003c/span\u003e\u003cspan address=\"10.1136/bmjsem-2024-002090\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYe X, Huang Y, Bai Z, Wang Y. A novel approach for sports injury risk prediction: based on time-series image encoding and deep learning. Front Physiol. 2023;14:1174525. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3389/fphys.2023.1174525\u003c/span\u003e\u003cspan address=\"10.3389/fphys.2023.1174525\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eY\u0026uuml;ce A, Erkurt N, Yerli M, Misir A. The Potential of ChatGPT for High-Quality Information in Patient Education for Sports Surgery. \u003cem\u003eCureus\u003c/em\u003e 16, e58874 (2024) \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.7759/cureus.58874\u003c/span\u003e\u003cspan address=\"10.7759/cureus.58874\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhan H et al. Machine-Learning Models Reliably Predict Clinical Outcomes in Medial Patellofemoral Ligament Reconstruction. \u003cem\u003eArthroscopy\u003c/em\u003e 41, 1896\u0026ndash;1908.e1892 (2025) \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.arthro.2024.07.028\u003c/span\u003e\u003cspan address=\"10.1016/j.arthro.2024.07.028\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhan X, et al. Machine-learning-based head impact subtyping based on the spectral densities of the measurable head kinematics. J Sport Health Sci. 2023;12:619\u0026ndash;29. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.jshs.2023.03.003\u003c/span\u003e\u003cspan address=\"10.1016/j.jshs.2023.03.003\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhang H, Zheng H, Deng R, Luo K, Duan S. Computed Tomography Imaging under Artificial Intelligence Reconstruction Algorithm Used in Recovery of Sports Injury of the Knee Anterior Cruciate Ligament. \u003cem\u003eContrast Media Mol Imaging\u003c/em\u003e 2022, 1199841 (2022) \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1155/2022/1199841\u003c/span\u003e\u003cspan address=\"10.1155/2022/1199841\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhu T, et al. Alterations of urinary proteomic profiles are correlated with return to sport after anterior cruciate ligament reconstruction. BMC Sports Sci Med Rehabil. 2026;10. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1186/s13102-025-01527-2\u003c/span\u003e\u003cspan address=\"10.1186/s13102-025-01527-2\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. https://doi.org/.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMoons KGM et al. PROBAST\u0026thinsp;+\u0026thinsp;AI: an updated quality, risk of bias, and applicability assessment tool for prediction models using regression or artificial intelligence methods. \u003cem\u003eBmj\u003c/em\u003e 388, e082505 (2025) \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1136/bmj-2024-082505\u003c/span\u003e\u003cspan address=\"10.1136/bmj-2024-082505\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBahr R, Krosshaug T. Understanding injury mechanisms: a key component of preventing injuries in sport. Br J Sports Med. 2005;39:324\u0026ndash;9. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1136/bjsm.2005.018341\u003c/span\u003e\u003cspan address=\"10.1136/bjsm.2005.018341\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBittencourt NFN, et al. Complex systems approach for sports injuries: moving from risk factor identification to injury pattern recognition-narrative review and new concept. Br J Sports Med. 2016;50:1309\u0026ndash;14. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1136/bjsports-2015-095850\u003c/span\u003e\u003cspan address=\"10.1136/bjsports-2015-095850\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTonekaboni S, Joshi S, McCradden MD, Goldenberg A, editors. What clinicians want: contextualizing explainable machine learning for clinical end use. Machine learning for healthcare conference; 2019: PMLR.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGhassemi M, Oakden-Rayner L, Beam AL. The false hope of current approaches to explainable artificial intelligence in health care. Lancet Digit Health. 2021;3:e745\u0026ndash;50. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/s2589-7500(21)00208-9\u003c/span\u003e\u003cspan address=\"10.1016/s2589-7500(21)00208-9\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVan Tiggelen D, Wickes S, Stevens V, Roosen P, Witvrouw E. Effective prevention of sports injuries: a model integrating efficacy, efficiency, compliance and risk-taking behaviour. Br J Sports Med. 2008;42:648\u0026ndash;52. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1136/bjsm.2008.046441\u003c/span\u003e\u003cspan address=\"10.1136/bjsm.2008.046441\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGuo Z, et al. Large Language Models for Mental Health Applications: Systematic Review. JMIR Ment Health. 2024;11:e57400. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.2196/57400\u003c/span\u003e\u003cspan address=\"10.2196/57400\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFarhat F, ChatGPT as a Complementary Mental Health Resource. A Boon or a Bane. Ann Biomed Eng. 2024;52:1111\u0026ndash;4. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s10439-023-03326-7\u003c/span\u003e\u003cspan address=\"10.1007/s10439-023-03326-7\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZech JR, et al. Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: A cross-sectional study. PLoS Med. 2018;15:e1002683. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1371/journal.pmed.1002683\u003c/span\u003e\u003cspan address=\"10.1371/journal.pmed.1002683\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLitjens G, et al. A survey on deep learning in medical image analysis. Med Image Anal. 2017;42:60\u0026ndash;88. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.media.2017.07.005\u003c/span\u003e\u003cspan address=\"10.1016/j.media.2017.07.005\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMoassefi M, et al. Reproducibility of Deep Learning Algorithms Developed for Medical Imaging Analysis: A Systematic Review. J Digit Imaging. 2023;36:2306\u0026ndash;12. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s10278-023-00870-5\u003c/span\u003e\u003cspan address=\"10.1007/s10278-023-00870-5\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWolpert DH, Macready WG. No free lunch theorems for optimization. IEEE Trans Evol Comput. 1997;1:67\u0026ndash;82. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1109/4235.585893\u003c/span\u003e\u003cspan address=\"10.1109/4235.585893\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eD'Amour A, et al. Underspecification presents challenges for credibility in modern machine learning. J Mach Learn Res. 2022;23:1\u0026ndash;61.\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"bmc-medical-informatics-and-decision-making","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"midm","sideBox":"Learn more about [BMC Medical Informatics and Decision Making](http://bmcmedinformdecismak.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/midm/default.aspx","title":"BMC Medical Informatics and Decision Making","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"AI, predictive modeling, diagnostic imaging, rehabilitation, deep learning, return to sport","lastPublishedDoi":"10.21203/rs.3.rs-9259496/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9259496/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eArtificial intelligence (AI) and machine learning (ML) are rapidly transforming the medical field. The aim of this review was to outline the current scientific state of AI and ML application in sports medicine, evaluate the developmental and clinical maturity, and identify key priorities to guide future advancements and implementation. A scoping review was conducted with a literature search performed on February 5, 2026, using the MEDLINE, EMBASE and Web of Science databases which targeted AI or ML application on athletes within rehabilitation. Of 8,677 studies, 97 studies were included. Most research covered orthopaedics (70.1%) and neurology (18.6%), where AI was applied for injury prediction, diagnostic image analysis, and recovery estimation. Predictive and estimation models were the dominant application (57.7%). Reported discriminative performance was frequently high. However, the majority of studies relied on retrospective datasets and internal validation. Calibration reporting was uncommon, and prospective workflow integration was rare, with a single study attempting an interventional prevention strategy. Substantial heterogeneity in modelling approaches, data inputs, and outcomes definitions was observed. Although AI and ML applications in sports medicine frequently demonstrate strong within-sample performance, most remain in early-stage development. Currently, these tools should be viewed as supportive adjuncts rather than autonomous decision-making systems.\u003c/p\u003e","manuscriptTitle":"Artificial Intelligence and Machine Learning in Sports Medicine: Mapping clinical tasks and assessing clinical maturity - a scoping review","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-14 02:07:01","doi":"10.21203/rs.3.rs-9259496/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-04-20T09:34:13+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-20T06:47:23+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-15T18:29:54+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"6533092577561702411849539056846043597","date":"2026-04-05T05:14:29+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"296873505960531660559810323298261080476","date":"2026-04-05T03:53:00+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-04T22:11:33+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-04-03T11:14:34+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-03-31T08:32:16+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-31T08:31:28+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Medical Informatics and Decision Making","date":"2026-03-29T14:23:58+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-medical-informatics-and-decision-making","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"midm","sideBox":"Learn more about [BMC Medical Informatics and Decision Making](http://bmcmedinformdecismak.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/midm/default.aspx","title":"BMC Medical Informatics and Decision Making","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"e1b4a6c6-491c-4216-af7b-5ae594aaf818","owner":[],"postedDate":"April 14th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-09T09:08:40+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-14 02:07:01","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9259496","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9259496","identity":"rs-9259496","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}