Predictive Model for Early Prognosis After Total Knee Arthroplasty Based on Multidimensional Indicators

Predictive Model for Early Prognosis After Total Knee Arthroplasty Based on Multidimensional Indicators | 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 Predictive Model for Early Prognosis After Total Knee Arthroplasty Based on Multidimensional Indicators Pengcheng Li, Runkai Zhao, Juntao Lu, Xiwei Zhang, Shuai Yang, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8514723/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 01 Apr, 2026 Read the published version in BMC Musculoskeletal Disorders → Version 1 posted 12 You are reading this latest preprint version Abstract Objective To comprehensively evaluate the significance of multidimensional perioperative indicators for the prognosis following total knee arthroplasty (TKA), construct and validate a nomogram model for predicting optimal early knee joint function recovery at 2 weeks post-TKA, and provide evidence-based support for clinical precise intervention, thereby accelerating patients' rehabilitation process and improving the quality of prognosis. Methods A total of 297 patients with end-stage knee osteoarthritis (KOA) who underwent TKA were retrospectively enrolled and divided into a training set (n = 247) and a validation set (n = 50) at a ratio of 5:1. Multidimensional data, including demographic characteristics, surgical indicators, imaging parameters, hematological results, and scale scores, were systematically collected preoperatively and perioperatively. The minimum clinically important difference (MCID) of the Knee Society Score (KSS) functional score was calculated using the anchor-based method and defined as the primary outcome variable. Variables were initially screened via Bootstrap-LASSO regression, and a nomogram model was constructed by integrating multivariate Logistic regression to identify independent risk factors affecting prognosis. The model performance was evaluated in terms of discrimination, calibration, and clinical utility through receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA), respectively. Results The MCID of the KSS functional score at 2 weeks post-TKA was determined to be 8.2. Multivariate Logistic regression analysis revealed that preoperative KSS functional score (OR = 0.944, 95% CI: 0.922–0.965, P < 0.001), SF-36 role-emotional score (OR = 0.989, 95% CI: 0.982–0.996, P = 0.003), and duration of pain (OR = 0.426, 95% CI: 0.209–0.847, P = 0.017) were protective factors; whereas preoperative uric acid level (OR = 1.005, 95% CI: 1.001–1.010, P = 0.031) and tourniquet application time (OR = 2.068, 95% CI: 1.042–4.206, P = 0.041) were independent risk factors. The area under the ROC curve (AUC) of the nomogram model was 0.81 (95% CI: 0.75–0.87) in the training set and 0.75 (95% CI: 0.55–0.95) in the validation set. The Hosmer-Lemeshow goodness-of-fit test yielded P-values > 0.05 in both sets, with Brier scores ≤ 0.171. The decision curve analysis demonstrated that the net benefit of the nomogram was superior to the extreme strategies of "Treat all" or "Treat none". Conclusion The nomogram constructed based on 5 independent factors effectively predicts the early rehabilitation outcome after TKA with favorable performance. It facilitates the early identification of high-risk patients and the implementation of targeted interventions in clinical practice, providing a valuable reference for the development of individualized perioperative rehabilitation strategies. Total knee arthroplasty Predictive model Early rehabilitation Nomogram Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 Introduction Knee osteoarthritis (KOA) is a prevalent disease among middle-aged and elderly populations, characterized by knee joint pain, swelling, and limited mobility ¹. As one of the most common orthopedic disorders, KOA is also a leading cause of disability in the elderly worldwide, imposing a substantial health burden on both patients and healthcare systems ². Statistics indicate that approximately 650 million individuals aged 40 years and above globally suffered from OA in 2020, with the incidence, prevalence, and disability rate of OA continuously rising over the past three decades —a trend also observed in China³⁻⁴. However, there is currently no curative treatment for KOA. When KOA progresses to the end stage, total knee arthroplasty (TKA) becomes the sole viable option for joint reconstruction in most patients ⁵⁻⁶. Although TKA is hailed as one of the most successful surgical procedures of the 20th century ⁷, patients typically require an extended period of rehabilitation to restore knee joint function, and the final rehabilitation outcome is influenced by multiple factors. In clinical practice, we have observed significant individual variability in post-TKA rehabilitation. Some patients exhibit slow progress in early postoperative rehabilitation, manifested by inadequate recovery of joint range of motion and insufficient pain relief. This not only increases the risk of postoperative complications but also may undermine patients' rehabilitation confidence, reduce treatment adherence, and ultimately affect long-term prognosis. However, previous studies have predominantly focused on long-term functional outcomes at 1 year or more postoperatively, investigating indicators such as prosthesis survival rate and long-term functional status, with insufficient attention paid to early postoperative rehabilitation ⁸⁻⁹. The 2-week post-TKA period represents a critical transition window from in-hospital to home-based rehabilitation. During this phase, joint swelling subsides, pain is alleviated, and soft tissue repair is in a pivotal stage. Early functional improvement not only lays a foundation for subsequent rehabilitation but also enhances patients' enthusiasm through positive feedback. Despite several attempts to explore factors related to post-TKA outcomes using risk calculators and predictive models ¹⁰⁻¹², the influencing factors of early functional prognosis after TKA remain unclear and require further investigation. A nomogram is a visualized predictive tool constructed based on multivariate statistical models such as Logistic regression, enabling individualized risk prediction with simplicity and feasibility. It only takes a few minutes to complete patient evaluation in clinical practice ¹³. Therefore, this study aimed to systematically collect preoperative and perioperative relevant indicators, screen core influencing factors, and construct an individualized nomogram model to predict optimal early (2 weeks) knee joint function rehabilitation after TKA based on multivariate Logistic regression. The goal is to identify high-risk patients with poor TKA prognosis early, adjust treatment plans promptly, and provide effective interventions to accelerate patients' early rehabilitation process and improve early prognostic outcomes. Materials and Methods Study Subjects Patients diagnosed with end-stage KOA who underwent TKA in the Department of Joint Surgery, Chinese PLA General Hospital between January 2022 and October 2025 were retrospectively selected as study subjects. Inclusion criteria: (1) Aged 18-85 years; (2) Meeting the KOA diagnostic criteria of the American College of Rheumatology; (3) Failed conservative treatment, requiring TKA with clear surgical indications; (4) Undergoing unilateral TKA after admission; (5) Complete clinical and follow-up data during hospitalization. Exclusion criteria: (1) Previous open knee surgery history; (2) Patients with failure of vital organ functions (e.g., heart, lung); (3) Diabetic patients with poorly controlled blood glucose and at risk of infection as assessed by researchers; (4) Complicated with consciousness disturbance or mental illness; (5) Neuromuscular dysfunction affecting lower limb function; (6) Severe coagulation disorders; (7) Active infectious foci in the body (systemic or local infectious lesions); (8) Severe osteoporosis, metabolic bone disease, radiation-induced bone disease, or tumors around the knee joint. This study was approved by the Medical Ethics Committee of Chinese PLA General Hospital (Approval No.: S2025-581-01). Patient-Reported Outcome Measures (PROMs) Patients were evaluated via questionnaires administered through outpatient visits or telephone follow-up preoperatively and at 2 weeks postoperatively. The evaluation included three scales: Knee Society Score (KSS), Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC), and 36-Item Short Form Health Survey (SF-36) 14-16 . The KSS score comprises four dimensions: symptom score (0-25 points), satisfaction score (0-40 points), expectation score (0-15 points), and functional score (-10-100 points); a higher score indicates better knee joint function and higher patient satisfaction. The WOMAC score assesses knee joint pain (0-20 points), stiffness (0-8 points), and functional status (0-68 points); a lower score denotes better knee joint function and higher patient satisfaction. The SF-36 is a globally recognized health-related quality of life assessment tool that evaluates patients' health status from both physical and psychological perspectives. It consists of 8 dimensions: physical function (0-100), role-physical (0-100), bodily pain (0-100), general health (0-100), vitality (0-100), social function (0-100), role-emotional (0-100), and mental health (0-100). A higher score indicates better health-related quality of life. Perioperative Management All surgeries were performed by two senior orthopedic surgeons with more than 8 years of TKA experience, an annual surgical volume exceeding 300 cases (including over 100 robot-assisted TKAs per year), and both had completed the learning curve prior to the study initiation. A standardized medial parapatellar approach was adopted for all surgeries, adhering to the concept of adjusted mechanical alignment (aMA). Specifically, without excessive osteotomy or soft tissue release, the hip-knee-ankle (HKA) axis was restored to a neutral position as much as possible while preserving the patient's inherent mild alignment characteristics. If forced correction would compromise bone mass or ligament stability, priority was given to ensuring the symmetrical stability of the flexion-extension gap. Robot-assisted TKAs in the included cases utilized the Mako Knee Arthroplasty System (Stryker, Mahwah, NJ, USA). Preoperative CT three-dimensional planning was performed to determine the osteotomy range, prosthesis rotation angle, and tibial posterior slope. During surgery, the robotic arm guided osteotomy according to the plan, which could be fine-tuned based on gap assessment. Balance was verified using spacers/trials, with limited soft tissue release performed if necessary. For manual TKA, femoral intramedullary and tibial extramedullary positioning devices were used, following the same aMA principle. Mild deformity could be appropriately retained to optimize gap balance, with gap verification and soft tissue release procedures consistent with the robot-assisted group. Postoperatively, all patients followed a standardized rehabilitation program jointly managed by a senior medical assistant team and outpatient physicians. In-hospital ambulation, joint mobility training, and muscle strength exercises were initiated on the first day after surgery. After discharge, a home-based rehabilitation package (including a training manual, goniometer, and rehabilitation log) was provided for phased training. Medical staff monitored rehabilitation adherence (completion of 80% or more of the training) through telephone follow-up, outpatient re-examination, and telemedicine. The outpatient team provided continuous follow-up evaluation and professional guidance throughout the rehabilitation process. Observation Indicators (1) Preoperative data: General data (gender, age, BMI, educational level, comorbidities); clinical data (duration of pain, total hospital stay, postoperative discharge time, preoperative knee joint range of motion, preoperative KSS, WOMAC, and SF-36 scores); laboratory test results (white blood cell count, hemoglobin, neutrophil-to-lymphocyte ratio, platelet-to-lymphocyte ratio, albumin, prothrombin time, activated partial thromboplastin time, fibrinogen, erythrocyte sedimentation rate, interleukin-6, C-reactive protein, uric acid, red blood cell distribution width, procalcitonin); imaging data (clinical grading of knee osteoarthritis severity using the Kellgren-Lawrence (KL) classification and measurement of lower limb alignment parameters, including HKA angle, mechanical medial proximal tibial angle (mMPTA), mechanical lateral distal femoral angle (mLDFA), joint line convergence angle (JLCA), and anatomical mechanical axis angle (AMA)) via standing knee anteroposterior/lateral radiographs and full-length lower limb radiographs (EOS). (2) Perioperative data: Surgical side, anesthesia method, surgical approach, tourniquet time, operation duration, patellar replacement status, prosthesis name, prosthesis type, femoral/tibial prosthesis size, liner thickness, and platelet-rich plasma (PRP) treatment status. (3) Outcome variable: KSS, WOMAC, and SF-36 scores of patients at 2 weeks post-TKA were obtained through telephone follow-up and outpatient visits. The MCID of the KSS functional score was calculated using data from this cohort. Patients whose KSS functional score change reached the MCID at 2 weeks postoperatively were classified into the optimal knee function group, while those who did not meet the MCID were assigned to the suboptimal knee function group. Calculation of MCID For MCID calculation, patients were first categorized into 4 groups based on their satisfaction at 2 weeks postoperatively: extremely satisfied, satisfied, general, and poor. Changes in preoperative and postoperative KSS functional scores were analyzed across groups, and the MCID of the KSS functional score was determined using the anchor-based method. Spearman rank correlation analysis was performed to assess the correlation between score changes (preoperatively to postoperatively) and satisfaction. Subsequently, the MCID value was estimated using the slope of the linear regression equation. Construction of the Predictive Model Initial variable screening was conducted via Bootstrap-LASSO regression. The training set data were resampled 1000 times with replacement, and variables with non-zero coefficients were selected using LASSO regression after each resampling to identify core variables with high stability. The meaningful variables identified were included in multivariate Logistic regression analysis using the stepwise selection method. The nomogram predictive model was constructed using the car and rms packages in R software (Version 4.5.1). Calibration curves were plotted to evaluate the consistency of the nomogram model. Receiver operating characteristic (ROC) curves were generated to assess the discrimination ability of the model. Decision curve analysis (DCA) was performed to evaluate the clinical utility of the nomogram. Statistical Methods Statistical analysis was conducted using SPSS 18.0 software. Categorical data were expressed as frequencies and percentages (%), with intergroup comparisons performed using the chi-square test. Normality of continuous data was tested using the Shapiro-Wilk method. Continuous data following a normal distribution were presented as mean ± standard deviation (Mean ± SD), with intergroup comparisons using the t-test. Continuous data with a skewed distribution were described as median and interquartile range (M (Q1, Q3)), with intergroup comparisons performed using the Mann-Whitney U test. All tests were two-tailed, and a P-value < 0.05 was considered statistically significant. Results Basic Characteristics A total of 316 patients diagnosed with end-stage KOA who underwent TKA in the Department of Joint Surgery, Chinese PLA General Hospital between January 2022 and October 2025 were initially enrolled. Among them, 15 patients had incomplete follow-up data, 1 patient did not undergo surgery due to poorly controlled blood glucose, 3 patients had traumatic arthritis. Ultimately, 297 patients were included in the final analysis and randomly divided into a training set (n=247) and a validation set (n=50) at a ratio of 5:1 using a random number table (Figure 1). Among the included patients, 63 (21.2%) were male and 234 (78.8%) were female, with a mean age of (66.5 ± 6.7) years and a satisfaction rate of 64.6%. Imaging indicators were independently measured by two clinical physicians, and the mean value was adopted. The inter-rater kappa coefficient was 0.86, indicating good inter-rater reliability. No statistically significant differences were observed in preoperative data, perioperative data, or postoperative follow-up results between the training set and the validation set (P > 0.05) (Table 1-5). MCID Calculation Patients were divided into 4 groups based on their responses to the anchor question (i.e., patient satisfaction at 2 weeks postoperatively). The mean changes in preoperative and 2-week postoperative KSS functional scores were as follows: poor: -11.5 (95% CI: -19.54 to -3.50), general: -1.9 (95% CI: -6.79 to 2.98), satisfied: 2.7 (95% CI: -1.26 to 6.71), and extremely satisfied: 14.6 (95% CI: 9.14 to 20.08). Patient satisfaction was positively correlated with changes in KSS functional scores—the higher the satisfaction, the greater the magnitude of KSS functional score improvement (Spearman correlation coefficient r = 0.297, P < 0.001). The mean KSS functional changes across groups exhibited a linear distribution. Simple linear regression analysis yielded an absolute slope value of 8.2 (95% CI: 5.49 to 10.91), which was defined as the reference MCID for the KSS functional score (Figure 2). Risk Factor Screening Initial variable screening was performed using a combination of Bootstrap and LASSO regression. The training set data were resampled 1000 times with replacement, and LASSO regression was conducted after each resampling. The optimal value of the regularization parameter λ was determined via 10-fold cross-validation (Figure 3a). When λ = lambda.min = 0.0359, the model regularization intensity was enhanced, and 10 variables with non-zero coefficients were ultimately retained: presence of diabetes, comorbidity index, duration of pain, lower limb coronal alignment, tourniquet application time, preoperative WOMAC function score, preoperative KSS function score, preoperative SF-36 role-emotional score, erythrocyte sedimentation rate, and uric acid. The curve in Figure 3b depicts the coefficient trajectory of candidate risk factors, with the model compression degree increasing as λ increases, resulting in the minimum number of candidate variables. Multivariate Logistic regression analysis of the 10 variables using R software revealed that preoperative KSS functional score, preoperative SF-36 role-emotional score, duration of pain, uric acid level, and tourniquet application time were statistically significant (P < 0.05) (Table 6), indicating that these 5 factors are independent risk factors affecting TKA prognosis. Specifically: (1) Preoperative KSS functional score: OR = 0.944 (95% CI: 0.922-0.965, P < 0.001); (2) Preoperative SF-36 role-emotional score: OR = 0.989 (95% CI: 0.982-0.996, P = 0.003); (3) Duration of pain: OR = 0.426 (95% CI: 0.209-0.847, P = 0.017); (4) Preoperative uric acid: OR = 1.005 (95% CI: 1.001-1.010, P = 0.031); (5) Tourniquet application time: OR = 2.068 (95% CI: 1.042-4.206, P = 0.041). Among these, preoperative KSS functional score, preoperative SF-36 role-emotional score, and duration of pain were protective factors for optimal knee joint function at 2 weeks post-TKA, while uric acid level and tourniquet application time were risk factors. Nomogram Construction A nomogram model was constructed using R software based on the 5 independent risk factors identified via multivariate Logistic regression (Figure 4). In this nomogram, the contribution of each factor to the outcome is reflected in the corresponding score for each indicator. The total score, calculated by summing the individual scores, corresponds to the probability of optimal knee joint function at 2 weeks post-TKA (i.e., KSS functional score exceeding the MCID at 2 weeks postoperatively). A higher total score indicates a higher probability of optimal knee joint function at 2 weeks postoperatively. Model Performance Evaluation The predictive performance of the clinical model was evaluated from three aspects: discrimination, calibration, and clinical utility. Receiver operating characteristic (ROC) curves were plotted to assess discrimination. The results showed that the area under the ROC curve (AUC) and its 95% CI were 0.81 (0.75, 0.87) in the training set (Figure 5a) and 0.75 (0.55, 0.95) in the validation set (Figure 5b). The AUC values in both the training and validation sets exceeded 0.70, indicating good discrimination ability of the model and suggesting that the predictive model has a certain discriminative power for the prognosis of patients at 2 weeks post-TKA. Calibration was evaluated using the Hosmer-Lemeshow goodness-of-fit test and Brier score. The P-values were 0.398 (training set) and 0.757 (validation set), both > 0.05, with Brier scores of 0.167 and 0.171, respectively (Figure 6). These results indicated good consistency between the predicted probabilities and actual outcomes of the model. Clinical utility was assessed via decision curve analysis (DCA) (Figure 7). The threshold probabilities were 0-96% for the training set and 0-83% for the validation set. The net benefit of applying the nomogram model was higher than that of the "Treat all" and "Treat none" strategies, suggesting that the nomogram has favorable clinical utility. Discussion KOA is a degenerative disease characterized by limited joint function, stiffness, and pain as the main clinical symptoms. With the aging of the global population, the number of KOA patients is increasing annually. Currently, there is no curative treatment for knee osteoarthritis, making TKA the primary therapeutic option for end-stage patients. However, literature reports indicate that the dissatisfaction rate after TKA is approximately 10% 17 . Given the increasing annual volume of TKA surgeries, this represents a substantial patient population. Therefore, early identification of high-risk groups with poor prognosis, exploration of factors influencing patient outcomes, and timely intervention are of paramount importance. Previous studies have primarily focused on relatively long-term TKA prognosis (≥ 1 year) 18 . However, during the early post-TKA period (2 weeks), patients experience more significant functional changes and pain perception. Facilitating favorable functional recovery in the early postoperative phase not only contributes to rapid rehabilitation but also enhances patients' confidence, adherence, and enthusiasm for rehabilitation. Based on previous literature and clinical experience, this study extensively incorporated preoperative and perioperative data potentially influencing patient prognosis, covering multidimensional parameters such as general demographic characteristics (gender, age, BMI, etc.), clinical functional indicators (duration of pain, preoperative joint range of motion, etc.), hematological markers (white blood cell count, hemoglobin, inflammatory factors, coagulation function, uric acid, etc.), imaging parameters (lower limb alignment HKA angle, mMPTA, mLDFA, etc.), and perioperative variables (surgical method, anesthesia type, prosthesis information, etc.). The physiological and psychological status of patients preoperatively and postoperatively were comprehensively evaluated using scales including KSS, WOMAC, and SF-36. MCID refers to the minimum clinically meaningful improvement in function perceived by patients, integrating objective score changes with subjective patient experiences to avoid judging rehabilitation outcomes solely based on numerical changes 19 . In previous studies, MCID calculation after TKA has mostly focused on 3 months or more postoperatively, with varying MCID values due to differences in assessment tools, study populations, and calculation methods 20 – 21 . Additionally, few studies have calculated MCID at 2 weeks post-TKA. Using the anchor-based method, we determined the MCID of the KSS functional score at 2 weeks post-TKA as 8.2 based on data from this cohort, which was used as the outcome indicator to evaluate early knee joint function after TKA. In this study, we adopted a combined Bootstrap-LASSO regression approach for initial variable screening, leveraging a dual mechanism of "regularization screening + resampling validation". Compared with traditional univariate analysis, this method effectively handles high-dimensional data and multicollinearity, improves the stability and generalization ability of variable selection, and reduces the risk of Type I error 22 . Subsequent multivariate Logistic analysis identified five independent risk factors influencing TKA prognosis: preoperative KSS functional score, preoperative SF-36 role-emotional score, duration of pain, uric acid level, and tourniquet application time. Firstly, preoperative KSS functional score was a protective factor for prognosis at 2 weeks post-TKA, indicating that better preoperative baseline knee joint function is associated with greater potential for early postoperative rehabilitation. Previous studies have also suggested that preoperative prehabilitation training for TKA can effectively reduce early postoperative pain, minimize the loss of musculoskeletal mass, shorten hospital stay, and improve early postoperative knee joint function 23 – 25 . Therefore, it is crucial to emphasize the assessment of preoperative functional reserve for TKA patients and implement perioperative prehabilitation training (e.g., quadriceps strength training, joint range of motion exercises) to enhance early postoperative recovery by improving preoperative functional capacity. The role-emotional score in the SF-36 assesses work or daily activity limitations caused by emotional issues. Our results indicate that better preoperative role-emotional function (less anxiety and depression) is associated with more favorable early postoperative rehabilitation, consistent with previous findings 26 – 27 . The incidence of preoperative anxiety and depression in TKA patients is as high as 35%. Such negative emotions can affect rehabilitation through multiple pathways: on the one hand, anxiety and depression can induce hyperalgesia ²⁵, reducing patients' tolerance to rehabilitation training; on the other hand, negative emotions can disrupt the neuroendocrine system, inhibit fibroblast proliferation and collagen synthesis, and delay tissue repair 29 . additionally, patients with poor psychological status are more prone to decreased rehabilitation adherence, thereby impairing training outcomes. Therefore, preoperative psychological counseling can help alleviate the adverse effects of negative emotions on rehabilitation, thereby improving rehabilitation efficacy. Similarly, duration of pain was a protective factor for prognosis at 2 weeks post-TKA, with patients experiencing shorter pain duration demonstrating better early postoperative rehabilitation. KOA is a chronic degenerative disease with a prolonged course. Long-term chronic pain may lead to muscle atrophy and reduced pain threshold, directly affecting patients' postoperative rehabilitation exercises and knee joint function recovery 30 – 31 . Therefore, for patients with inadequate response to conservative treatment, there is no need for excessive delay in surgical timing. Timely TKA can reduce the irreversible impact of chronic pain on neuromuscular function and improve early postoperative rehabilitation outcomes. Furthermore, preoperative uric acid level and tourniquet application time were identified as risk factors for prognosis at 2 weeks post-TKA. Hyperuricemia may affect postoperative rehabilitation through multiple mechanisms, including the deposition of urate crystals in periarticular soft tissues, inducing aseptic inflammation and exacerbating postoperative joint swelling and pain 32 ; hyperuricemia can reduce collagen expression, increase the transcription levels of matrix-degrading enzymes and pro-inflammatory factors, and interfere with tissue repair, thereby hindering early functional recovery 33 – 35 ; prolonged tourniquet application (> 60 minutes) may cause ischemia and hypoxia of lower limb tissues, leading to the production of a large number of reactive oxygen species after reperfusion, damaging vascular endothelial cells and myocytes, aggravating tissue edema and inflammatory response, increasing the incidence of adverse events 36 – 38 , and similarly delaying early recovery. Therefore, for patients with high preoperative uric acid levels, a low-purine diet and uric acid-lowering therapy should be implemented. During surgery, the duration and pressure of tourniquet application should be strictly controlled. For complex cases, intermittent release or tourniquet-free techniques should be adopted to minimize tissue damage 39 . In this study, a nomogram model was established to predict the probability of favorable knee joint function prognosis at 2 weeks post-TKA based on five independent risk factors: preoperative KSS functional score, preoperative SF-36 role-emotional score, duration of pain, uric acid level, and tourniquet application time. The nomogram demonstrated good discrimination (AUC of 0.81 and 0.75 in the training and validation sets, respectively), calibration (Hosmer-Lemeshow test P-values > 0.05, Brier scores < 0.2), and clinical utility (DCA net benefit superior to the extreme strategies of "all intervention" and "no intervention") in both the training and validation sets, indicating favorable and stable predictive performance of the model. However, the model's predictive ability has not reached an excellent level (AUC > 0.9), which may be attributed to the relatively small sample size and fluctuations in knee joint function recovery among patients at 2 weeks postoperatively. This study also has several limitations: Firstly, it is a single-center retrospective study with a relatively limited sample size, which may introduce selection bias. The external generalization ability of the model needs to be further verified by multi-center, large-sample prospective studies. Secondly, potential influencing factors such as economic status, family rehabilitation support, and rehabilitation training adherence were not included, which may indirectly affect early rehabilitation by influencing patients' postoperative training compliance. Thirdly, the follow-up period was only 2 weeks postoperatively, and the long-term sustained impact of relevant risk factors on mid-term and long-term rehabilitation was not explored. Conclusion This study focuses on the clinical challenge of early rehabilitation at 2 weeks post-TKA. Core variables were screened using Bootstrap-LASSO regression combined with multivariate Logistic regression, and a nomogram predictive model was constructed and validated. The model integrates five independent influencing factors: preoperative KSS functional score, SF-36 role-emotional score, duration of pain, uric acid level, and tourniquet application time, enabling individualized risk assessment and intervention. It facilitates the early identification of high-risk patients with poor early postoperative rehabilitation and improves TKA prognosis by implementing targeted measures such as preoperative prehabilitation, psychological counseling, uric acid control, and shortening tourniquet application time, thereby accelerating patients' early rehabilitation process and enhancing rehabilitation adherence. Declarations Funding This study was supported by the National Natural Science Foundation of China (82272558)；Beijing Natural Science Foundation（L252165） Ethics approval and consent to participate This study was approved by the Medical Ethics Committee of Chinese PLA General Hospital (Approval No.: S2025-581-01). The requirement for written informed consent was waived due to the retrospective nature of the study and the use of anonymized patient data. All procedures involving human participants, data or material fully complied with the Declaration of Helsinki. Consent for publication Not applicable. Competing interests The authors declare no competing financial interests. Author contributions Pengcheng Li: Data collection, Writing-original draft; Runkai Zhao: Investigation, Statistical analysis; Juntao Lu: Data curation, Writing-review & editing; Xiwei Zhang: Statistical analysis; Shuai Yang: Validation; Lin Hao: Validation; Haoran Wang: Formal analysis; Quanbo Ji: Conceptualization, Supervision, Funding acquisition, Writing-review & editing; Guoqiang Zhang: Conceptualization, Supervision, Funding acquisition, Writing-review & editing; Data availability No, I do not have any research data outside the submitted manuscript file. All data generated or analysed during this study are included in this published article. References Duong, V. et al. Risk factors for the development of knee osteoarthritis across the lifespan: A systematic review and meta-analysis. Osteoarthritis Cartilage 33, 1162–1179 (2025). Giorgino, R. et al. Knee Osteoarthritis: Epidemiology, Pathogenesis, and Mesenchymal Stem Cells: What Else Is New? An Update. Int J Mol Sci 24, 6405 (2023). Chen, S. et al. Epidemiological trends and characteristics of osteoarthritis in China during 1990-2021. J Orthop Translat 51, 218–226 (2025). Cui, A. et al. Global, regional prevalence, incidence and risk factors of knee osteoarthritis in population-based studies. EClinicalMedicine 29–30, 100587 (2020). Perruccio, A. V. et al. Osteoarthritis year in review 2023: Epidemiology & therapy. Osteoarthritis Cartilage 32, 159–165 (2024). Yan, L. et al. Comparative efficacy and safety of exercise modalities in knee osteoarthritis: systematic review and network meta-analysis. BMJ 391, e085242 (2025). Pagan, C. A. et al. Technology in Total Knee Arthroplasty in 2023. J Arthroplasty 39, S54–S59 (2024). Feng, B. et al. Long-term clinical outcomes following total knee arthroplasty in patients with hemophilic arthropathy: a single-surgeon cohort after a 10- to 17-year follow-up. Chin Med J (Engl) 136, 1478–1484 (2023). Montagna, A. et al. A novel knee implant for total knee arthroplasty meets expectations at 10 years. First long-term follow-up report of clinical outcomes and survivorship. Knee Surg Sports Traumatol Arthrosc https://doi.org/10.1002/ksa.70037 (2025) doi:10.1002/ksa.70037. Langenberger, B., Schrednitzki, D., Halder, A. M., Busse, R. & Pross, C. M. Predicting whether patients will achieve minimal clinically important differences following hip or knee arthroplasty. Bone Joint Res 12, 512–521 (2023). Lundgren, L. S., Willems, N., Marchand, R. C., Batailler, C. & Lustig, S. Surgical factors play a critical role in predicting functional outcomes using machine learning in robotic-assisted total knee arthroplasty. Knee Surg Sports Traumatol Arthrosc 32, 3198–3209 (2024). Strahl, A. et al. A clinical risk score enables early prediction of dissatisfaction 1 year after total knee arthroplasty. Knee Surg Sports Traumatol Arthrosc 33, 252–264 (2025). Lang, L. et al. An independently validated nomogram for individualised estimation of short-term mortality risk among patients with severe traumatic brain injury: a modelling analysis of the CENTER-TBI China Registry Study. EClinicalMedicine 59, 101975 (2023). Scuderi, G. R. et al. The new Knee Society Knee Scoring System. Clin Orthop Relat Res 470, 3–19 (2012). Bellamy, N., Buchanan, W. W., Goldsmith, C. H., Campbell, J. & Stitt, L. W. Validation study of WOMAC: a health status instrument for measuring clinically important patient relevant outcomes to antirheumatic drug therapy in patients with osteoarthritis of the hip or knee. J Rheumatol 15, 1833–1840 (1988). Ware, J. E. & Sherbourne, C. D. The MOS 36-item short-form health survey (SF-36). I. Conceptual framework and item selection. Med Care 30, 473–483 (1992). DeFrance, M. J. & Scuderi, G. R. Are 20% of Patients Actually Dissatisfied Following Total Knee Arthroplasty? A Systematic Review of the Literature. J Arthroplasty 38, 594–599 (2023). Nakao, Y. et al. Preoperative Gait Speed as a Predictor of Patient-Reported Outcomes After Total Hip Arthroplasty: Insights from Patient Acceptable Symptom State and K-Means Clustering Analyses. J Bone Joint Surg Am. 25.00542 (2025) Malec, J. F. & Ketchum, J. M. A Standard Method for Determining the Minimal Clinically Important Difference for Rehabilitation Measures. Arch Phys Med Rehabil 101, 1090–1094 (2020). Çelik, D., Çoban, Ö. & Kılıçoğlu, Ö. Minimal clinically important difference of commonly used hip-, knee-, foot-, and ankle-specific questionnaires: a systematic review. J Clin Epidemiol 113, 44–57 (2019). Lee, W. C., Kwan, Y. H., Chong, H. C. & Yeo, S. J. The minimal clinically important difference for Knee Society Clinical Rating System after total knee arthroplasty for primary osteoarthritis. Knee Surg Sports Traumatol Arthrosc 25, 3354–3359 (2017). Harris, A. H. S. et al. Can Machine Learning Methods Produce Accurate and Easy-to-Use Preoperative Prediction Models of One-Year Improvements in Pain and Functioning After Knee Arthroplasty? J Arthroplasty 36, 112-117.e6 (2021). Zhang, W., Lu, X., Yang, N., Zhu, X. & Hu, H. Prehabilitation is effective in relieving pain after knee arthroplasty, but has little effect on length of stay and knee function: a meta-analysis of randomized controlled trials. Front Med (Lausanne) 12, 1457407 (2025). Wang, Z. et al. Effectiveness of Preoperative Rehabilitation Compared With Usual Care in Total Knee Arthroplasty: A Meta-analysis of Randomized Controlled Trials. Arch Phys Med Rehabil S0003-9993(25)00904–9 (2025) Franz, A., Ji, S., Bittersohl, B., Zilkens, C. & Behringer, M. Impact of a Six-Week Prehabilitation With Blood-Flow Restriction Training on Pre- and Postoperative Skeletal Muscle Mass and Strength in Patients Receiving Primary Total Knee Arthroplasty. Front Physiol 13, 881484 (2022). Aalders, M. B., van der List, J. P., Keijser, L. C. M. & Benner, J. L. Anxiety and depression prior to total knee arthroplasty are associated with worse pain and subjective function: A prospective comparative study. Knee Surg Sports Traumatol Arthrosc 33, 308–318 (2025). Ten Noever de Brauw, G. V. et al. The mind matters: Psychological factors influence subjective outcomes following unicompartmental knee arthroplasty-A prospective study. Knee Surg Sports Traumatol Arthrosc 33, 239–251 (2025). Song, Q. et al. An ACC-VTA-ACC positive-feedback loop mediates the persistence of neuropathic pain and emotional consequences. Nat Neurosci 27, 272–285 (2024). Chan, H. et al. Psychological stress increases skin infection through the action of TGFβ to suppress immune-acting fibroblasts. Sci Immunol 10, eads0519 (2025). Nijs, J. et al. Central sensitisation in chronic pain conditions: latest discoveries and their potential for precision medicine. Lancet Rheumatol 3, e383–e392 (2021). Vigotsky, A. D. et al. Prognostic value of preoperative mechanical hyperalgesia and neuropathic pain qualities for postoperative pain after total knee replacement. Eur J Pain 28, 1387–1401 (2024). Yang, S., Liu, H., Fang, X.-M., Yan, F. & Zhang, Y. Signaling pathways in uric acid homeostasis and gout: From pathogenesis to therapeutic interventions. Int Immunopharmacol 132, 111932 (2024). Yu, J., Mi, T., Shao, Z. & Yan, X. The Outcomes of Patients With Hyperuricemia After Total Knee Arthroplasty: A Retrospective Cohort Study. Orthop Surg 17, 3477–3487 (2025). Zhang, J. et al. The impact of uric acid on musculoskeletal diseases: clinical associations and underlying mechanisms. Front Endocrinol (Lausanne) 16, 1515176 (2025). Liang, J. et al. Asymptomatic Hyperuricemia Is Associated with Achilles Tendon Rupture through Disrupting the Normal Functions of Tendon Stem/Progenitor Cells. Stem Cells Int 2022, 6795573 (2022). Cao, Z., Guo, J., Li, Q., Wu, J. & Li, Y. Comparison of efficacy and safety of different tourniquet applications in total knee arthroplasty: a network meta-analysis of randomized controlled trials. Ann Med 53, 1816–1826 (2021). Ahmed, I. et al. Time to reconsider the routine use of tourniquets in total knee arthroplasty surgery. Bone Joint J 103-B, 830–839 (2021). Tabata Fukushima, C. et al. Reactive oxygen species generation by reverse electron transfer at mitochondrial complex I under simulated early reperfusion conditions. Redox Biol 70, 103047 (2024). Zhong, Q. et al. Comparison of medium- and long-term total knee arthroplasty follow-up with or without tourniquet. BMC Musculoskelet Disord 26, 205 (2025). Tables Table 1. Comparison of Clinical Data Between the Training Set and Validation Set Variables Training Set (n=247) Validation Set (n=50) X²/t/Z P value Gender, n(%) 0.371 0.542 Male 54 (21.9) 9 (18.0) Female 193 (78.1) 41 (82.0) Age, n(%) ≤65 years 95 (38.5) 17 (34.0) 0.337 0.561 ＞65 years 152 (61.5) 33 (66.0) BMI (kg/m²) 26.9±3.4 26.3±3.4 -0.928 0.353 Educational level, n(%) 1.249 0.741 Primary school or below 101 (40.9) 20 (40.0) Junior high school 77 (31.2) 13 (26.0) Senior high school/Technical secondary school 46 (18.6) 11 (22.0) Bachelor's degree or above 23 (9.3) 6 (12.0) Diabetes mellitus, n(%) 1.382 0.240 No 198 (80.2) 43 (86.0) Yes 49 (19.8) 7 (14.0) Comorbidity index 3.0 (2.0,3.0) 3.0 (2.0,3.0) -0.348 0.728 Duration of pain, n(%) 1.261 0.261 ＜10 years 120 (48.6) 28 (56.0) ≥10 years 127 (51.4) 22 (44.0) Postoperative hospital stay (days) 3.0（3.0,4.0） 4.0（3.0,4.0） -0.746 0.456 Total hospital stay (days) 7.0（7.0,9.0） 7.0（7.0,10.0） -0.388 0.698 Preoperative knee flexion (°) 119.0（100.0,130.0） 110.0（100.0,124.3） -1.371 0.170 Preoperative knee extension (°) 3.00（0.0,10.0） 3.00（0.0,10.0） -0.284 0.776 Preoperative knee range of motion (°) 110.0（90.0,127.0） 107.5（90.0,120.0） -1.012 0.312 Table 2. Comparison of Imaging Data Between the Training Set and Validation Set Variables Training Set (n=247) Validation Set (n=50) X²/t/Z P value HKA (° ) 10.5（5.2,14.3） 10.4（6.8,13.9） -0.188 0.851 Lower limb coronal alignment, n(%) 1.552 0.460 Varus 202 (81.8) 43 (86.0) Neutral 20 (8.1) 2 (4.0) Valgus 25 (10.1) 5 (10.0) mMPTA (° ) 84.1（81.8,86.5） 83.5（81.8,85.5） -0.755 0.450 mLDFA (° ) 89.1±3.4 88.4±3.3 -1.281 0.201 JLCA (° ) 4.9（3.2,6.6） 5.4±2.9 -0.744 0.457 Femoral AMA (° ) 6.7（5.9,7.7） 6.45（5.6,7.9） -0.338 0.736 Operative side K-L grade, n(%) 2.977 0.226 Grade 2 14 (5.7) 1 (2.0) Grade 3 100 (40.5) 18 (36.0) Grade 4 133 (53.8) 31 (62.0) Contralateral K-L grade, n(%) 8.151 0.148 Grade 2 37 (15.0) 6 (12.0) Grade 3 112 (45.3) 21 (42.0) Grade 4 39 (15.8) 15 (30.0) TKA 59 (23.9) 8 (16.0) HKA, Hip-Knee-Ankle angle; mMPTA, Mechanical Medial Proximal Tibial Angle; mLDFA, Mechanical Lateral Distal Femoral Angle; JLCA, Joint Line Convergence Angle; AMA, Anatomical Mechanical Axis Angle; K-L, Kellgren-Lawrence; TKA, Total Knee Arthroplasty. Table 3. Comparison of Surgery-Related Data Between the Training Set and Validation Set Variables Training Set (n=247) Validation Set (n=50) X²/t/Z P value Surgical side, n(%) 1.138 0.566 Left 122 (49.4) 28 (56.0) Right 125 (50.6) 22 (44.0) Anesthesia method, n(%) 2.903 0.574 General anesthesia 133 (53.8) 29 (58.0) Spinal anesthesia 120 (48.6) 2 (4.0) General anesthesia + Spinal anesthesia 6 (2.4) 2 (4.0) General anesthesia + Nerve block 88 (35.6) 17 (34.0) Robot-assisted surgery, n(%) 2.221 0.329 No 88 (35.6) 23 (46.0) Yes 159 (64.4) 27 (54.0) Tourniquet application time, n(%) 3.265 0.071 ≤60 min 98 (39.7) 27 (54.0) ＞60 min 149 (60.3) 23 (46.0) Operation time (min) 105.0（92.0,120.0） 101.5（84.0,117.3） -1.419 0.156 Patellar resurfacing, n(%) 1.742 0.628 No 152 (61.5) 32 (64.0) Yes 95 (38.5) 18 (36.0) Prosthesis brand, n(%) 12.733 0.121 Stryker 49 (19.8) 7 (14.0) Smith & Nephew 45 (18.2) 2 (4.0) Johnson & Johnson 81 (32.8) 22 (44.0) Zhengtian 46 (18.6) 15 (30.0) Zimmer Biomet 19 (7.7) 4 (8.0) Dabo Medical 5 (2.0) 0 (0.0) Aikang 2 (0.8) 0 (0.0) Prosthesis type, n(%) 4.435 0.109 PS 209 (84.6) 47 (94.0) CR 38 (15.4) 3 (6.0) Femoral prosthesis size 5.0（4.0,6.0） 4.5（4.0,6.0） -0.675 0.500 Tibial prosthesis size 4.0（3.0,5.0） 4.0（3.0,5.0） -1.113 0.266 Liner thickness 8.0（6.0,9.0） 8.0（5.0,9.0） -1.236 0.217 Intraoperative PRP, n(%) 0.956 0.620 No 183 (74.1) 36 (72.0) Yes 64 (25.9) 14 (28.0) PS, Posterior Cruciate Ligament-Substituting; CR, Posterior Cruciate Ligament-Retaining; PRP, Platelet-Rich Plasma. Table 4. Comparison of Hematological Data Between the Training Set and Validation Set Variables Training Set (n=247) Validation Set (n=50) X²/t/Z P value White blood cell count (10⁹/L) 5.6（4.7,6.3） 5.4（4.6,6.1） -0.723 0.470 Neutrophil-to-lymphocyte ratio 1.5（1.2,1.9） 1.7（1.2,2.1） -1.163 0.245 Platelet-to-lymphocyte ratio 112.1（90.2,137.0） 118.0（94.8,145.1） -1.184 0.237 Hemoglobin (g/L) 128.8±12.1 126.7±11.9 -1.098 0.273 Red blood cell distribution width (L/L) 12.5（12.1,13.0） 12.5（12.0,12.8） -0.655 0.513 Erythrocyte sedimentation rate (mm/h) 9.0（5.0,13.0） 9.0（6.0,15.3） -0.266 0.790 Serum albumin (g/L) 41.1±2.7 40.6±2.8 -1.014 0.312 Uric acid (umol/L) 296.6±72.0 296.1±76.07 -0.041 0.968 C-reactive protein, n(%) Normal 169 (68.4) 33 (66.0) Abnormal 78 (31.6) 17 (34.0) Sodium (mmol/L) 142.1（140.8,143.4） 142.0 (140.8,143.8) -0.161 0.872 Interleukin-6, n(%) 0.443 0.509 Normal 211 (85.4) 41 (82.0) Abnormal 36 (14.6) 9 (18.0) Prothrombin time (s) 11.2（10.9,11.7） 11.3（10.8,11.7） -0.388 0.698 International normalized ratio 0.97（0.94,1.03） 0.98 (0.96,1.04) -0.457 0.648 Activated partial thromboplastin time (s) 28.4（26.5,31.0） 28.3(25.7,30.3) -0.972 0.331 Fibrinogen (g/L) 2.9（2.5,3.3） 2.9（2.7,3.3） -0.409 0.683 Normal range of C-reactive protein: 0-0.8 mg/dL; Normal range of interleukin-6: 0-5.9 pg/ml. Table 5. Comparison of Scale Scores Between the Training Set and Validation Set Variables Training Set (n=247) Validation Set (n=50) X²/t/Z P value Preoperative WOMAC pain (points) 10.0（7.0,12.0） 9.5±4.7 -0.365 0.715 Preoperative WOMAC stiffness (points) 4.0（2.0,5.0） 4.0（2.0,6.00） -0.054 0.957 Preoperative WOMAC function (points) 28.0（17.0,37.0） 24.5（16.0,33.8） -0.559 0.576 Preoperative WOMAC total score (points) 42.0（26.0,53.0） 36.5（26.3,48.0） -0.529 0.597 2-week WOMAC pain (points) 6.0（5.0,9.0） 6.0（3.0,9.0） -0.527 0.598 2-week WOMAC stiffness (points) 2.0（2.0,4.0） 3.0（2.0,4.0） -1.012 0.311 2-week WOMAC function (points) 20.0（13.0,30.0） 21.0（13.5,35.0） -1.361 0.174 2-week WOMAC total score (points) 29.0（21.0,41.0） 30.0（20.0,45.3） -0.951 0.342 Preoperative KSS symptoms (points) 13.0（11.0,15.0） 13.0（12.0,14.0） -0.009 0.993 Preoperative KSS satisfaction (points) 14.0（10.0,20.0） 14.0（10.0,19.5） -0.272 0.785 Preoperative KSS expectation (points) 15.0（14.0,15.0） 15.0（13.0,15.0） -1.526 0.127 Preoperative KSS function (points) 39.3±19.6 36.8±17.5 -0.828 0.408 2-week KSS symptoms (points) 11.0（8.5,13.5） 11.0（8.0,15.0） -0.889 0.374 2-week KSS function (points) 42.4±19.8 36.56±17.0 -1.931 0.054 Preoperative SF-36 physical function (points) 40.0（20.0,55.0） 40.0 (25.0,46.3) -0.673 0.501 Preoperative SF-36 role-physical (points) 0.0（0.0,75.0） 0.0（0.0,50.0） -0.334 0.739 Preoperative SF-36 bodily pain (points) 51.0（31.0,62.0） 42.00(31.0,62.0) -0.220 0.826 Preoperative SF-36 general health (points) 62.0（47.0,72.0） 57.0 (46.5,70.5) -1.773 0.076 Preoperative SF-36 vitality (points) 60.0（45.0,75.0） 65.0（45.0,75.0） -0.598 0.550 Preoperative SF-36 social function (points) 55.6（44.4,77.8） 66.7 (44.4,77.8) -0.272 0.786 Preoperative SF-36 role-emotional (points) 100.0（0.0,100.0） 100.0（0.0,100.0） -0.512 0.608 Preoperative SF-36 mental health (points) 72.0（56.0,88.0） 68.0 (60.0,81.0) -0.794 0.427 Preoperative SF-36 health transition (points) 50.0（50.0,75.0） 50.0（50.0,75.0） -0.381 0.703 Preoperative SF-36 PCS (points) 40.1（35.8,46.7） 39.60 (35.5,48.9) -1.031 0.302 Preoperative SF-36 MCS (points) 45.4（38.1,53.5） 44.2（36.7,52.3） -0.664 0.507 2-week postoperative satisfaction, n(%) 0.976 0.502 Terrible 25 (10.1) 6 (12.0) Poor 61 (24.7) 13 (26.0) Good 100 (40.5) 21 (42.0) Excellent 61 (24.7) 10 (20.0) WOMAC, Western Ontario and McMaster Universities Osteoarthritis Index; KSS, Knee Society Score; SF-36, 36-Item Short Form Health Survey; PCS, Physical Component Summary; MCS, Mental Component Summary. Table 6. Multivariate Logistic Regression Analysis for Screening Independent Risk Factors Variables B Standard Error (SE) Wald (z) OR (95%CI) P value Constant 0.508 0.852 0.596 1.662(0.313-9.015) 0.551 Preoperative KSS function -0.057 0.012 -4.991 0.944(0.922-0.965) <0.001 Preoperative SF-36 role-emotional -0.011 0.004 -2.946 0.989 (0.982-0.996) 0.003 Duration of pain -0.852 0.356 -2.396 0.426(0.209-0.847) 0.017 Uric acid 0.005 0.002 2.161 1.005(1.001-1.010) 0.031 Tourniquet application time 0.727 0.355 2.049 2.068(1.042-4.206) 0.041 Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 01 Apr, 2026 Read the published version in BMC Musculoskeletal Disorders → Version 1 posted Editorial decision: Revision requested 04 Feb, 2026 Reviews received at journal 03 Feb, 2026 Reviewers agreed at journal 21 Jan, 2026 Reviewers agreed at journal 15 Jan, 2026 Reviewers agreed at journal 12 Jan, 2026 Reviews received at journal 12 Jan, 2026 Reviewers agreed at journal 12 Jan, 2026 Reviewers invited by journal 12 Jan, 2026 Editor invited by journal 09 Jan, 2026 Editor assigned by journal 09 Jan, 2026 Submission checks completed at journal 08 Jan, 2026 First submitted to journal 08 Jan, 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-8514723","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":573620230,"identity":"a2e1bbc6-b211-4869-8b2c-8ba337fef93d","order_by":0,"name":"Pengcheng Li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA1klEQVRIiWNgGAWjYBACNvnjBx98qKipb2xvbHyQUFFDWAufBE+y4Ywzxxibew4fNnhw5hhhLXISDGbSvG3MjO0z0tIkH7YwE+Ew6QaQLWzMvDNyzCoSG9gY+Nu7E/BrkTkI8osMm2TPG7MbiTtkGCTOnN2AXwtDAtgWHsP2HKCWM2wMBhK5BLWA/SJhfyDHrCCxjZkILRIQLQaMHWlpDMRp4TkDDuQERmAgSyScOcZD0C/y7e3gqExgBEblxx8VNXL87b34tWAAHtKUj4JRMApGwSjACgAcZU8h1SVnGAAAAABJRU5ErkJggg==","orcid":"","institution":"Chinese PLA General Hospital","correspondingAuthor":true,"prefix":"","firstName":"Pengcheng","middleName":"","lastName":"Li","suffix":""},{"id":573620238,"identity":"742e542b-ec36-42eb-b3d8-876a373afb17","order_by":1,"name":"Runkai Zhao","email":"","orcid":"","institution":"The First Affiliated Hospital of Henan Medical University","correspondingAuthor":false,"prefix":"","firstName":"Runkai","middleName":"","lastName":"Zhao","suffix":""},{"id":573620240,"identity":"1a2afb9a-dd23-43f0-80ed-7c6dd35fdd11","order_by":2,"name":"Juntao Lu","email":"","orcid":"","institution":"Chinese PLA General Hospital","correspondingAuthor":false,"prefix":"","firstName":"Juntao","middleName":"","lastName":"Lu","suffix":""},{"id":573620241,"identity":"12765216-69ae-4348-99d1-aece07d02c28","order_by":3,"name":"Xiwei Zhang","email":"","orcid":"","institution":"Chinese PLA General Hospital","correspondingAuthor":false,"prefix":"","firstName":"Xiwei","middleName":"","lastName":"Zhang","suffix":""},{"id":573620242,"identity":"faded41b-081e-46c7-991a-cf604e4d72dc","order_by":4,"name":"Shuai Yang","email":"","orcid":"","institution":"Chinese PLA General Hospital","correspondingAuthor":false,"prefix":"","firstName":"Shuai","middleName":"","lastName":"Yang","suffix":""},{"id":573620243,"identity":"a24eaac8-2afa-4c3c-9e46-d19f1894cca5","order_by":5,"name":"Lin Hao","email":"","orcid":"","institution":"Chinese PLA General Hospital","correspondingAuthor":false,"prefix":"","firstName":"Lin","middleName":"","lastName":"Hao","suffix":""},{"id":573620244,"identity":"67ff6260-d2f8-440e-bec4-fc4cfff78bc9","order_by":6,"name":"Haoran Wang","email":"","orcid":"","institution":"The First Affiliated Hospital of Henan Medical University","correspondingAuthor":false,"prefix":"","firstName":"Haoran","middleName":"","lastName":"Wang","suffix":""},{"id":573620246,"identity":"69f2864e-1a9e-473d-bd79-d8d085b17fbb","order_by":7,"name":"Quanbo Ji","email":"","orcid":"","institution":"Chinese PLA General Hospital","correspondingAuthor":false,"prefix":"","firstName":"Quanbo","middleName":"","lastName":"Ji","suffix":""},{"id":573620251,"identity":"acb6e0dd-15b2-4172-a5b1-ef507a53381c","order_by":8,"name":"Guoqiang Zhang","email":"","orcid":"","institution":"Chinese PLA General Hospital","correspondingAuthor":false,"prefix":"","firstName":"Guoqiang","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2026-01-04 17:23:41","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8514723/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8514723/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s12891-026-09693-1","type":"published","date":"2026-04-01T15:58:12+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":100401301,"identity":"aec8ae6a-e7d2-4adf-a161-f03e24ccc314","added_by":"auto","created_at":"2026-01-16 11:58:51","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":34625,"visible":true,"origin":"","legend":"","description":"","filename":"Revisedmanuscript.docx","url":"https://assets-eu.researchsquare.com/files/rs-8514723/v1/b509604d742d3442cd688490.docx"},{"id":100399567,"identity":"07bf90e2-fba9-4207-b0fd-b0997f9b770b","added_by":"auto","created_at":"2026-01-16 11:57:15","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3493085,"visible":true,"origin":"","legend":"","description":"","filename":"Figure.docx","url":"https://assets-eu.researchsquare.com/files/rs-8514723/v1/96e2c6b06fe8e95818014703.docx"},{"id":100399720,"identity":"7c8e19d3-ec21-4d21-a890-d99385731b8a","added_by":"auto","created_at":"2026-01-16 11:57:32","extension":"docx","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":45032,"visible":true,"origin":"","legend":"","description":"","filename":"Table.docx","url":"https://assets-eu.researchsquare.com/files/rs-8514723/v1/b34b8d9b837007b80ce5677f.docx"},{"id":100399565,"identity":"868928d4-96e4-47d4-aade-40e7ff800d22","added_by":"auto","created_at":"2026-01-16 11:57:14","extension":"json","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":11052,"visible":true,"origin":"","legend":"","description":"","filename":"5906334154e5413a949f749e947de4d2.json","url":"https://assets-eu.researchsquare.com/files/rs-8514723/v1/1730389a3b2ccedd50101f3e.json"},{"id":100400421,"identity":"450a8be7-a01a-4185-96d7-9b414186ee51","added_by":"auto","created_at":"2026-01-16 11:58:08","extension":"xml","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":154157,"visible":true,"origin":"","legend":"","description":"","filename":"5906334154e5413a949f749e947de4d21enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8514723/v1/b8d6b7d1a38dae4b5d2f8919.xml"},{"id":100400982,"identity":"6cb7493c-a16e-4fbd-96a7-54d02bfab32b","added_by":"auto","created_at":"2026-01-16 11:58:37","extension":"jpeg","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":118136,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8514723/v1/35d16d0ec773c2adcff688bb.jpeg"},{"id":100401287,"identity":"edb174e8-d2c8-4c74-a188-791677a01d27","added_by":"auto","created_at":"2026-01-16 11:58:50","extension":"jpeg","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1074,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage10.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8514723/v1/74dadc1c39f1f25d27e7b4f7.jpeg"},{"id":100400158,"identity":"9527473c-7611-4399-8db1-dcbfed965ea3","added_by":"auto","created_at":"2026-01-16 11:57:57","extension":"jpeg","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":77313,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8514723/v1/52616261b1299e06bd06c14b.jpeg"},{"id":100400897,"identity":"37b16283-0d30-4f85-92c0-b8913825b9df","added_by":"auto","created_at":"2026-01-16 11:58:30","extension":"jpeg","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":223565,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8514723/v1/aee1fe8d6599426e3f5c7100.jpeg"},{"id":100400769,"identity":"89fa1b8c-eea8-463e-9094-dc682228a47d","added_by":"auto","created_at":"2026-01-16 11:58:25","extension":"jpeg","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":160161,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8514723/v1/dd2e3d64645797f8b5832263.jpeg"},{"id":100401191,"identity":"f9d8d910-c437-4538-9fb3-69e5c13cf6af","added_by":"auto","created_at":"2026-01-16 11:58:45","extension":"jpeg","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":214849,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8514723/v1/6855b443266dca534361ad6f.jpeg"},{"id":100400626,"identity":"6616eb03-b702-44c8-8724-72a099f50455","added_by":"auto","created_at":"2026-01-16 11:58:20","extension":"jpeg","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1074,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage10.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8514723/v1/c3da393b76cae59e70a1c300.jpeg"},{"id":100400814,"identity":"5be2709e-4296-407c-9564-c336addd8c8c","added_by":"auto","created_at":"2026-01-16 11:58:27","extension":"jpeg","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":208284,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8514723/v1/fcd1faa1a81f13ce09421ba2.jpeg"},{"id":100401181,"identity":"a78c2308-7df1-4f7d-a8b8-87d8b64614a5","added_by":"auto","created_at":"2026-01-16 11:58:44","extension":"jpeg","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1074,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage10.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8514723/v1/4e4cc50e0e8beff22d99748f.jpeg"},{"id":100399681,"identity":"13911878-5417-41d4-8341-a64c3030688e","added_by":"auto","created_at":"2026-01-16 11:57:32","extension":"jpeg","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":196542,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage9.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8514723/v1/ab1ca58e661e5c30b8389217.jpeg"},{"id":100400431,"identity":"9a1db8d6-0de3-4911-86e6-60d5cc412307","added_by":"auto","created_at":"2026-01-16 11:58:09","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":49013,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8514723/v1/adeb88863624e84d0624dc61.png"},{"id":100400140,"identity":"05cc54ad-21f1-403e-bc0a-a35e09aca76e","added_by":"auto","created_at":"2026-01-16 11:57:55","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":935,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage10.png","url":"https://assets-eu.researchsquare.com/files/rs-8514723/v1/d8a05e5f7ce6dc4278f67e59.png"},{"id":100400548,"identity":"17ef8230-2eda-4e75-9779-d518f402c84e","added_by":"auto","created_at":"2026-01-16 11:58:17","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":35943,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8514723/v1/b8394cd1b94cbb76b9ed856f.png"},{"id":100399827,"identity":"a04b40c6-95c7-4544-9207-fdf26278f7a9","added_by":"auto","created_at":"2026-01-16 11:57:38","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":40192,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8514723/v1/2a5340fcc92ba3d119fbc59c.png"},{"id":100401263,"identity":"59759880-c35d-4556-8207-d4bedb53f79c","added_by":"auto","created_at":"2026-01-16 11:58:49","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":78461,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-8514723/v1/e0b3ed313d4b6384867d3883.png"},{"id":100401098,"identity":"ec90c9f7-9fa2-453f-8bd3-706b66d70e72","added_by":"auto","created_at":"2026-01-16 11:58:42","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":33723,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-8514723/v1/434e0e865aef3751c081ae37.png"},{"id":100399802,"identity":"d3928401-4985-4534-baf8-0985445cb38d","added_by":"auto","created_at":"2026-01-16 11:57:37","extension":"png","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":935,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage10.png","url":"https://assets-eu.researchsquare.com/files/rs-8514723/v1/4f75a3c7bd9c0dc4384bba1c.png"},{"id":100400839,"identity":"ac868843-2038-42be-97a0-676935b7995a","added_by":"auto","created_at":"2026-01-16 11:58:28","extension":"png","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":100073,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-8514723/v1/cdf1cf5409e6a94d953868f9.png"},{"id":100400884,"identity":"d8ae79ef-59d1-4014-afc8-efd99c0fb214","added_by":"auto","created_at":"2026-01-16 11:58:29","extension":"png","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":935,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage10.png","url":"https://assets-eu.researchsquare.com/files/rs-8514723/v1/b70e5453244045b5007d5c60.png"},{"id":100400403,"identity":"cbfa37e5-5804-48b1-ac0c-3fcf72c4887e","added_by":"auto","created_at":"2026-01-16 11:58:08","extension":"png","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":40168,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-8514723/v1/6d9a4dcb8f5cadda50a226c6.png"},{"id":100400799,"identity":"1568cc12-a79f-4860-a094-03374be69a61","added_by":"auto","created_at":"2026-01-16 11:58:26","extension":"xml","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":152208,"visible":true,"origin":"","legend":"","description":"","filename":"5906334154e5413a949f749e947de4d21structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8514723/v1/81ef44fcdc640386463bbc3f.xml"},{"id":100400613,"identity":"a1e8a001-7472-406a-8f44-a2b331d8548a","added_by":"auto","created_at":"2026-01-16 11:58:20","extension":"html","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":161605,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8514723/v1/e697671fc275dd8488143069.html"},{"id":100400528,"identity":"b6993ef6-f3e3-48ee-8784-81481fda1076","added_by":"auto","created_at":"2026-01-16 11:58:11","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":77156,"visible":true,"origin":"","legend":"\u003cp\u003eFlow chart of participants. Participants were screened according to inclusion and exclusion criteria, then randomly assigned to the training set and validation set.\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-8514723/v1/e4f59fdb6c0773b4b6483cbb.png"},{"id":100400972,"identity":"b44855b5-6105-485f-a14b-9376e9fa721b","added_by":"auto","created_at":"2026-01-16 11:58:37","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":58913,"visible":true,"origin":"","legend":"\u003cp\u003eCorrelation between patient satisfaction and changes in KSS functional score. A linear regression equation was established based on the changes in KSS functional scores (preoperatively vs. 2 weeks postoperatively) and patient satisfaction.\u003c/p\u003e","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-8514723/v1/930d5a0fff58999bf550c2e8.png"},{"id":100400539,"identity":"b74fc4fe-db42-42bc-9581-7306af2f4b1c","added_by":"auto","created_at":"2026-01-16 11:58:12","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":145791,"visible":true,"origin":"","legend":"\u003cp\u003eScreening of risk factors based on LASSO regression. a. Cross-validation curve of LASSO regression: The red dashed line indicates the number of variables corresponding to lambda.min, and the blue dashed line indicates the number of variables corresponding to lambda.1se. b. Coefficient path plot of LASSO regression: Shows the trajectory of coefficients of each independent variable changing with λ.\u003c/p\u003e","description":"","filename":"3.png","url":"https://assets-eu.researchsquare.com/files/rs-8514723/v1/afe60164eaff69bccb8b79fa.png"},{"id":100400126,"identity":"efb9849b-4082-430b-bf27-18f62cbe3b20","added_by":"auto","created_at":"2026-01-16 11:57:54","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":108870,"visible":true,"origin":"","legend":"\u003cp\u003eNomogram for predicting favorable functional prognosis at 2 weeks post-TKA. Each variable corresponds to a specific score; the total score corresponds to the predicted probability of favorable functional prognosis at 2 weeks post-TKA.\u003c/p\u003e","description":"","filename":"4.png","url":"https://assets-eu.researchsquare.com/files/rs-8514723/v1/730b1693957d924aa95c0dc1.png"},{"id":100400599,"identity":"6b9bb7c7-19b5-4ce1-b64d-4a3d535c92eb","added_by":"auto","created_at":"2026-01-16 11:58:19","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":136613,"visible":true,"origin":"","legend":"\u003cp\u003eROC curves of the predictive model in the training set and validation set. a. ROC curve of the training set: AUC = 0.809 (95% CI: 0.7501-0.8674). b. ROC curve of the validation set: AUC = 0.754 (95% CI: 0.5545-0.9528).\u003c/p\u003e","description":"","filename":"5.png","url":"https://assets-eu.researchsquare.com/files/rs-8514723/v1/c3328124777a307db4e9e3e7.png"},{"id":100400785,"identity":"7ae3b316-dbae-46da-840d-ad099396a1d9","added_by":"auto","created_at":"2026-01-16 11:58:26","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":153457,"visible":true,"origin":"","legend":"\u003cp\u003eCalibration curves of the predictive model in the training set and validation set. a. Calibration curve of the training set: Brier score = 0.167. b. Calibration curve of the validation set: Brier score = 0.171.\u003c/p\u003e","description":"","filename":"6.png","url":"https://assets-eu.researchsquare.com/files/rs-8514723/v1/45ae3566cb96392e4cdc4272.png"},{"id":100400407,"identity":"8a2caae5-4e2c-41b8-a404-597f4cc2fd00","added_by":"auto","created_at":"2026-01-16 11:58:08","extension":"png","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":125695,"visible":true,"origin":"","legend":"\u003cp\u003eDCA curves of the predictive model in the training set and validation set. Used to quantify the clinical benefit of \"model-based decision-making\" compared with \"Treat all or Treat none\".a. Decision curve of the training set. b. Decision curve of the validation set.\u003c/p\u003e","description":"","filename":"7.png","url":"https://assets-eu.researchsquare.com/files/rs-8514723/v1/83bb74e421f3aa8f12aa6b79.png"},{"id":106343608,"identity":"cf0cd811-a703-4380-9cf2-58848cf3ebbc","added_by":"auto","created_at":"2026-04-07 16:07:20","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1850565,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8514723/v1/bc461566-3768-4d81-a3ac-06e2e1b42c98.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Predictive Model for Early Prognosis After Total Knee Arthroplasty Based on Multidimensional Indicators","fulltext":[{"header":"Introduction","content":"\u003cp\u003eKnee osteoarthritis (KOA) is a prevalent disease among middle-aged and elderly populations, characterized by knee joint pain, swelling, and limited mobility \u0026sup1;. As one of the most common orthopedic disorders, KOA is also a leading cause of disability in the elderly worldwide, imposing a substantial health burden on both patients and healthcare systems \u0026sup2;. Statistics indicate that approximately 650\u0026nbsp;million individuals aged 40 years and above globally suffered from OA in 2020, with the incidence, prevalence, and disability rate of OA continuously rising over the past three decades \u0026mdash;a trend also observed in China\u0026sup3;⁻⁴. However, there is currently no curative treatment for KOA. When KOA progresses to the end stage, total knee arthroplasty (TKA) becomes the sole viable option for joint reconstruction in most patients ⁵⁻⁶.\u003c/p\u003e \u003cp\u003eAlthough TKA is hailed as one of the most successful surgical procedures of the 20th century ⁷, patients typically require an extended period of rehabilitation to restore knee joint function, and the final rehabilitation outcome is influenced by multiple factors. In clinical practice, we have observed significant individual variability in post-TKA rehabilitation. Some patients exhibit slow progress in early postoperative rehabilitation, manifested by inadequate recovery of joint range of motion and insufficient pain relief. This not only increases the risk of postoperative complications but also may undermine patients' rehabilitation confidence, reduce treatment adherence, and ultimately affect long-term prognosis. However, previous studies have predominantly focused on long-term functional outcomes at 1 year or more postoperatively, investigating indicators such as prosthesis survival rate and long-term functional status, with insufficient attention paid to early postoperative rehabilitation ⁸⁻⁹. The 2-week post-TKA period represents a critical transition window from in-hospital to home-based rehabilitation. During this phase, joint swelling subsides, pain is alleviated, and soft tissue repair is in a pivotal stage. Early functional improvement not only lays a foundation for subsequent rehabilitation but also enhances patients' enthusiasm through positive feedback. Despite several attempts to explore factors related to post-TKA outcomes using risk calculators and predictive models \u0026sup1;⁰⁻\u0026sup1;\u0026sup2;, the influencing factors of early functional prognosis after TKA remain unclear and require further investigation. A nomogram is a visualized predictive tool constructed based on multivariate statistical models such as Logistic regression, enabling individualized risk prediction with simplicity and feasibility. It only takes a few minutes to complete patient evaluation in clinical practice \u0026sup1;\u0026sup3;. Therefore, this study aimed to systematically collect preoperative and perioperative relevant indicators, screen core influencing factors, and construct an individualized nomogram model to predict optimal early (2 weeks) knee joint function rehabilitation after TKA based on multivariate Logistic regression. The goal is to identify high-risk patients with poor TKA prognosis early, adjust treatment plans promptly, and provide effective interventions to accelerate patients' early rehabilitation process and improve early prognostic outcomes.\u003c/p\u003e"},{"header":"Materials and Methods","content":"\u003cp\u003e\u003cstrong\u003e\u003cem\u003eStudy Subjects\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003ePatients diagnosed with end-stage KOA who underwent TKA in the Department of Joint Surgery, Chinese PLA General Hospital between January 2022 and October 2025 were retrospectively selected as study subjects.\u0026nbsp;Inclusion criteria: (1) Aged 18-85 years; (2) Meeting the KOA diagnostic criteria of the American College of Rheumatology; (3) Failed conservative treatment, requiring TKA with clear surgical indications; (4) Undergoing unilateral TKA after admission; (5) Complete clinical and follow-up data during hospitalization.\u0026nbsp;Exclusion criteria: (1) Previous open knee surgery history; (2) Patients with failure of vital organ functions (e.g., heart, lung); (3) Diabetic patients with poorly controlled blood glucose and at risk of infection as assessed by researchers; (4) Complicated with consciousness disturbance or mental illness; (5) Neuromuscular dysfunction affecting lower limb function; (6) Severe coagulation disorders; (7) Active infectious foci in the body (systemic or local infectious lesions); (8) Severe osteoporosis, metabolic bone disease, radiation-induced bone disease, or tumors around the knee joint. This study was approved by the Medical Ethics Committee of Chinese PLA General Hospital (Approval No.: S2025-581-01).\u003cstrong\u003e\u003cem\u003e\u0026nbsp;\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003ePatient-Reported Outcome Measures (PROMs)\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003ePatients were evaluated via questionnaires administered through outpatient visits or telephone follow-up preoperatively and at 2 weeks postoperatively. The evaluation included three scales: Knee Society Score (KSS), Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC), and 36-Item Short Form Health Survey (SF-36)\u003csup\u003e14-16\u003c/sup\u003e. The KSS score comprises four dimensions: symptom score (0-25 points), satisfaction score (0-40 points), expectation score (0-15 points), and functional score (-10-100 points); a higher score indicates better knee joint function and higher patient satisfaction. The WOMAC score assesses knee joint pain (0-20 points), stiffness (0-8 points), and functional status (0-68 points); a lower score denotes better knee joint function and higher patient satisfaction. The SF-36 is a globally recognized health-related quality of life assessment tool that evaluates patients\u0026apos; health status from both physical and psychological perspectives. It consists of 8 dimensions: physical function (0-100), role-physical (0-100), bodily pain (0-100), general health (0-100), vitality (0-100), social function (0-100), role-emotional (0-100), and mental health (0-100). A higher score indicates better health-related quality of life.\u003cstrong\u003e\u003cem\u003e\u0026nbsp;\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003ePerioperative Management\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAll surgeries were performed by two senior orthopedic surgeons with more than 8 years of TKA experience, an annual surgical volume exceeding 300 cases (including over 100 robot-assisted TKAs per year), and both had completed the learning curve prior to the study initiation. A standardized medial parapatellar approach was adopted for all surgeries, adhering to the concept of adjusted mechanical alignment (aMA). Specifically, without excessive osteotomy or soft tissue release, the hip-knee-ankle (HKA) axis was restored to a neutral position as much as possible while preserving the patient\u0026apos;s inherent mild alignment characteristics. If forced correction would compromise bone mass or ligament stability, priority was given to ensuring the symmetrical stability of the flexion-extension gap. Robot-assisted TKAs in the included cases utilized the Mako Knee Arthroplasty System (Stryker, Mahwah, NJ, USA). Preoperative CT three-dimensional planning was performed to determine the osteotomy range, prosthesis rotation angle, and tibial posterior slope. During surgery, the robotic arm guided osteotomy according to the plan, which could be fine-tuned based on gap assessment. Balance was verified using spacers/trials, with limited soft tissue release performed if necessary. For manual TKA, femoral intramedullary and tibial extramedullary positioning devices were used, following the same aMA principle. Mild deformity could be appropriately retained to optimize gap balance, with gap verification and soft tissue release procedures consistent with the robot-assisted group. Postoperatively, all patients followed a standardized rehabilitation program jointly managed by a senior medical assistant team and outpatient physicians. In-hospital ambulation, joint mobility training, and muscle strength exercises were initiated on the first day after surgery. After discharge, a home-based rehabilitation package (including a training manual, goniometer, and rehabilitation log) was provided for phased training. Medical staff monitored rehabilitation adherence (completion of 80% or more of the training) through telephone follow-up, outpatient re-examination, and telemedicine. The outpatient team provided continuous follow-up evaluation and professional guidance throughout the rehabilitation process.\u003cstrong\u003e\u003cem\u003e\u0026nbsp;\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eObservation Indicators\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e(1)\u0026nbsp;Preoperative data: General data (gender, age, BMI, educational level, comorbidities); clinical data (duration of pain, total hospital stay, postoperative discharge time, preoperative knee joint range of motion, preoperative KSS, WOMAC, and SF-36 scores); laboratory test results (white blood cell count, hemoglobin, neutrophil-to-lymphocyte ratio, platelet-to-lymphocyte ratio, albumin, prothrombin time, activated partial thromboplastin time, fibrinogen, erythrocyte sedimentation rate, interleukin-6, C-reactive protein, uric acid, red blood cell distribution width, procalcitonin); imaging data (clinical grading of knee osteoarthritis severity using the Kellgren-Lawrence (KL) classification and measurement of lower limb alignment parameters, including HKA angle, mechanical medial proximal tibial angle (mMPTA), mechanical lateral distal femoral angle (mLDFA), joint line convergence angle (JLCA), and anatomical mechanical axis angle (AMA)) via standing knee anteroposterior/lateral radiographs and full-length lower limb radiographs (EOS).\u003c/p\u003e\n\u003cp\u003e(2)\u0026nbsp;Perioperative data: Surgical side, anesthesia method, surgical approach, tourniquet time, operation duration, patellar replacement status, prosthesis name, prosthesis type, femoral/tibial prosthesis size, liner thickness, and platelet-rich plasma (PRP) treatment status.\u003c/p\u003e\n\u003cp\u003e(3)\u0026nbsp;Outcome variable: KSS, WOMAC, and SF-36 scores of patients at 2 weeks post-TKA were obtained through telephone follow-up and outpatient visits. The MCID of the KSS functional score was calculated using data from this cohort. Patients whose KSS functional score change reached the MCID at 2 weeks postoperatively were classified into the optimal knee function group, while those who did not meet the MCID were assigned to the suboptimal knee function group.\u003cstrong\u003e\u003cem\u003e\u0026nbsp;\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eCalculation of MCID\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eFor MCID calculation, patients were first categorized into 4 groups based on their satisfaction at 2 weeks postoperatively: extremely satisfied, satisfied, general, and poor. Changes in preoperative and postoperative KSS functional scores were analyzed across groups, and the MCID of the KSS functional score was determined using the anchor-based method. Spearman rank correlation analysis was performed to assess the correlation between score changes (preoperatively to postoperatively) and satisfaction. Subsequently, the MCID value was estimated using the slope of the linear regression equation.\u003cstrong\u003e\u003cem\u003e\u0026nbsp;\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eConstruction of the Predictive Model\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eInitial variable screening was conducted via Bootstrap-LASSO regression. The training set data were resampled 1000 times with replacement, and variables with non-zero coefficients were selected using LASSO regression after each resampling to identify core variables with high stability. The meaningful variables identified were included in multivariate Logistic regression analysis using the stepwise selection method. The nomogram predictive model was constructed using the\u0026nbsp;car\u0026nbsp;and\u0026nbsp;rms\u0026nbsp;packages in R software (Version 4.5.1). Calibration curves were plotted to evaluate the consistency of the nomogram model. Receiver operating characteristic (ROC) curves were generated to assess the discrimination ability of the model. Decision curve analysis (DCA) was performed to evaluate the clinical utility of the nomogram.\u003cstrong\u003e\u003cem\u003e\u0026nbsp;\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eStatistical Methods\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eStatistical analysis was conducted using SPSS 18.0 software. Categorical data were expressed as frequencies and percentages (%), with intergroup comparisons performed using the chi-square test. Normality of continuous data was tested using the Shapiro-Wilk method. Continuous data following a normal distribution were presented as mean \u0026plusmn; standard deviation (Mean \u0026plusmn; SD), with intergroup comparisons using the t-test. Continuous data with a skewed distribution were described as median and interquartile range (M (Q1, Q3)), with intergroup comparisons performed using the Mann-Whitney U test. All tests were two-tailed, and a P-value \u0026lt; 0.05 was considered statistically significant.\u003c/p\u003e"},{"header":"Results","content":"\u003cp\u003e\u003cstrong\u003e\u003cem\u003eBasic Characteristics\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eA total of 316 patients diagnosed with end-stage KOA who underwent TKA in the Department of Joint Surgery, Chinese PLA General Hospital between January 2022 and October 2025 were initially enrolled. Among them, 15 patients had incomplete follow-up data, 1 patient did not undergo surgery due to poorly controlled blood glucose, 3 patients had traumatic arthritis. Ultimately, 297 patients were included in the final analysis and randomly divided into a training set (n=247) and a validation set (n=50) at a ratio of 5:1 using a random number table (Figure 1). Among the included patients, 63 (21.2%) were male and 234 (78.8%) were female, with a mean age of (66.5 \u0026plusmn; 6.7) years and a satisfaction rate of 64.6%. Imaging indicators were independently measured by two clinical physicians, and the mean value was adopted. The inter-rater kappa coefficient was 0.86, indicating good inter-rater reliability. No statistically significant differences were observed in preoperative data, perioperative data, or postoperative follow-up results between the training set and the validation set (P \u0026gt; 0.05) (Table 1-5).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eMCID Calculation\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003ePatients were divided into 4 groups based on their responses to the anchor question (i.e., patient satisfaction at 2 weeks postoperatively). The mean changes in preoperative and 2-week postoperative KSS functional scores were as follows: poor: -11.5 (95% CI: -19.54 to -3.50), general: -1.9 (95% CI: -6.79 to 2.98), satisfied: 2.7 (95% CI: -1.26 to 6.71), and extremely satisfied: 14.6 (95% CI: 9.14 to 20.08). Patient satisfaction was positively correlated with changes in KSS functional scores\u0026mdash;the higher the satisfaction, the greater the magnitude of KSS functional score improvement (Spearman correlation coefficient r = 0.297, P \u0026lt; 0.001). The mean KSS functional changes across groups exhibited a linear distribution. Simple linear regression analysis yielded an absolute slope value of 8.2 (95% CI: 5.49 to 10.91), which was defined as the reference MCID for the KSS functional score (Figure 2).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eRisk Factor Screening\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eInitial variable screening was performed using a combination of Bootstrap and LASSO regression. The training set data were resampled 1000 times with replacement, and LASSO regression was conducted after each resampling. The optimal value of the regularization parameter \u0026lambda; was determined via 10-fold cross-validation (Figure 3a). When \u0026lambda; = lambda.min = 0.0359, the model regularization intensity was enhanced, and 10 variables with non-zero coefficients were ultimately retained: presence of diabetes, comorbidity index, duration of pain, lower limb coronal alignment, tourniquet application time, preoperative WOMAC function score, preoperative KSS function score, preoperative SF-36 role-emotional score, erythrocyte sedimentation rate, and uric acid. The curve in Figure 3b depicts the coefficient trajectory of candidate risk factors, with the model compression degree increasing as \u0026lambda; increases, resulting in the minimum number of candidate variables.\u003c/p\u003e\n\u003cp\u003eMultivariate Logistic regression analysis of the 10 variables using R software revealed that preoperative KSS functional score, preoperative SF-36 role-emotional score, duration of pain, uric acid level, and tourniquet application time were statistically significant (P \u0026lt; 0.05) (Table 6), indicating that these 5 factors are independent risk factors affecting TKA prognosis. Specifically: (1) Preoperative KSS functional score: OR = 0.944 (95% CI: 0.922-0.965, P \u0026lt; 0.001); (2) Preoperative SF-36 role-emotional score: OR = 0.989 (95% CI: 0.982-0.996, P = 0.003); (3) Duration of pain: OR = 0.426 (95% CI: 0.209-0.847, P = 0.017); (4) Preoperative uric acid: OR = 1.005 (95% CI: 1.001-1.010, P = 0.031); (5) Tourniquet application time: OR = 2.068 (95% CI: 1.042-4.206, P = 0.041). Among these, preoperative KSS functional score, preoperative SF-36 role-emotional score, and duration of pain were protective factors for optimal knee joint function at 2 weeks post-TKA, while uric acid level and tourniquet application time were risk factors.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eNomogram Construction\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eA nomogram model was constructed using R software based on the 5 independent risk factors identified via multivariate Logistic regression (Figure 4). In this nomogram, the contribution of each factor to the outcome is reflected in the corresponding score for each indicator. The total score, calculated by summing the individual scores, corresponds to the probability of optimal knee joint function at 2 weeks post-TKA (i.e., KSS functional score exceeding the MCID at 2 weeks postoperatively). A higher total score indicates a higher probability of optimal knee joint function at 2 weeks postoperatively.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eModel Performance Evaluation\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe predictive performance of the clinical model was evaluated from three aspects: discrimination, calibration, and clinical utility. Receiver operating characteristic (ROC) curves were plotted to assess discrimination. The results showed that the area under the ROC curve (AUC) and its 95% CI were 0.81 (0.75, 0.87) in the training set (Figure 5a) and 0.75 (0.55, 0.95) in the validation set (Figure 5b). The AUC values in both the training and validation sets exceeded 0.70, indicating good discrimination ability of the model and suggesting that the predictive model has a certain discriminative power for the prognosis of patients at 2 weeks post-TKA. Calibration was evaluated using the Hosmer-Lemeshow goodness-of-fit test and Brier score. The P-values were 0.398 (training set) and 0.757 (validation set), both \u0026gt; 0.05, with Brier scores of 0.167 and 0.171, respectively (Figure 6). These results indicated good consistency between the predicted probabilities and actual outcomes of the model. Clinical utility was assessed via decision curve analysis (DCA) (Figure 7). The threshold probabilities were 0-96% for the training set and 0-83% for the validation set. The net benefit of applying the nomogram model was higher than that of the \u0026quot;Treat all\u0026quot; and \u0026quot;Treat none\u0026quot; strategies, suggesting that the nomogram has favorable clinical utility.\u003c/p\u003e"},{"header":"Discussion","content":"\u003cp\u003eKOA is a degenerative disease characterized by limited joint function, stiffness, and pain as the main clinical symptoms. With the aging of the global population, the number of KOA patients is increasing annually. Currently, there is no curative treatment for knee osteoarthritis, making TKA the primary therapeutic option for end-stage patients. However, literature reports indicate that the dissatisfaction rate after TKA is approximately 10% \u003csup\u003e17\u003c/sup\u003e. Given the increasing annual volume of TKA surgeries, this represents a substantial patient population. Therefore, early identification of high-risk groups with poor prognosis, exploration of factors influencing patient outcomes, and timely intervention are of paramount importance. Previous studies have primarily focused on relatively long-term TKA prognosis (\u0026ge;\u0026thinsp;1 year)\u003csup\u003e\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e\u003c/sup\u003e. However, during the early post-TKA period (2 weeks), patients experience more significant functional changes and pain perception. Facilitating favorable functional recovery in the early postoperative phase not only contributes to rapid rehabilitation but also enhances patients' confidence, adherence, and enthusiasm for rehabilitation.\u003c/p\u003e \u003cp\u003eBased on previous literature and clinical experience, this study extensively incorporated preoperative and perioperative data potentially influencing patient prognosis, covering multidimensional parameters such as general demographic characteristics (gender, age, BMI, etc.), clinical functional indicators (duration of pain, preoperative joint range of motion, etc.), hematological markers (white blood cell count, hemoglobin, inflammatory factors, coagulation function, uric acid, etc.), imaging parameters (lower limb alignment HKA angle, mMPTA, mLDFA, etc.), and perioperative variables (surgical method, anesthesia type, prosthesis information, etc.). The physiological and psychological status of patients preoperatively and postoperatively were comprehensively evaluated using scales including KSS, WOMAC, and SF-36. MCID refers to the minimum clinically meaningful improvement in function perceived by patients, integrating objective score changes with subjective patient experiences to avoid judging rehabilitation outcomes solely based on numerical changes \u003csup\u003e\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e\u003c/sup\u003e. In previous studies, MCID calculation after TKA has mostly focused on 3 months or more postoperatively, with varying MCID values due to differences in assessment tools, study populations, and calculation methods \u003csup\u003e\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e\u003c/sup\u003e. Additionally, few studies have calculated MCID at 2 weeks post-TKA. Using the anchor-based method, we determined the MCID of the KSS functional score at 2 weeks post-TKA as 8.2 based on data from this cohort, which was used as the outcome indicator to evaluate early knee joint function after TKA.\u003c/p\u003e \u003cp\u003eIn this study, we adopted a combined Bootstrap-LASSO regression approach for initial variable screening, leveraging a dual mechanism of \"regularization screening\u0026thinsp;+\u0026thinsp;resampling validation\". Compared with traditional univariate analysis, this method effectively handles high-dimensional data and multicollinearity, improves the stability and generalization ability of variable selection, and reduces the risk of Type I error \u003csup\u003e\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e\u003c/sup\u003e. Subsequent multivariate Logistic analysis identified five independent risk factors influencing TKA prognosis: preoperative KSS functional score, preoperative SF-36 role-emotional score, duration of pain, uric acid level, and tourniquet application time. Firstly, preoperative KSS functional score was a protective factor for prognosis at 2 weeks post-TKA, indicating that better preoperative baseline knee joint function is associated with greater potential for early postoperative rehabilitation. Previous studies have also suggested that preoperative prehabilitation training for TKA can effectively reduce early postoperative pain, minimize the loss of musculoskeletal mass, shorten hospital stay, and improve early postoperative knee joint function \u003csup\u003e\u003cspan additionalcitationids=\"CR24\" citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e\u003c/sup\u003e. Therefore, it is crucial to emphasize the assessment of preoperative functional reserve for TKA patients and implement perioperative prehabilitation training (e.g., quadriceps strength training, joint range of motion exercises) to enhance early postoperative recovery by improving preoperative functional capacity. The role-emotional score in the SF-36 assesses work or daily activity limitations caused by emotional issues. Our results indicate that better preoperative role-emotional function (less anxiety and depression) is associated with more favorable early postoperative rehabilitation, consistent with previous findings \u003csup\u003e\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e\u003c/sup\u003e. The incidence of preoperative anxiety and depression in TKA patients is as high as 35%. Such negative emotions can affect rehabilitation through multiple pathways: on the one hand, anxiety and depression can induce hyperalgesia \u0026sup2;⁵, reducing patients' tolerance to rehabilitation training; on the other hand, negative emotions can disrupt the neuroendocrine system, inhibit fibroblast proliferation and collagen synthesis, and delay tissue repair\u003csup\u003e\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e\u003c/sup\u003e. additionally, patients with poor psychological status are more prone to decreased rehabilitation adherence, thereby impairing training outcomes. Therefore, preoperative psychological counseling can help alleviate the adverse effects of negative emotions on rehabilitation, thereby improving rehabilitation efficacy. Similarly, duration of pain was a protective factor for prognosis at 2 weeks post-TKA, with patients experiencing shorter pain duration demonstrating better early postoperative rehabilitation. KOA is a chronic degenerative disease with a prolonged course. Long-term chronic pain may lead to muscle atrophy and reduced pain threshold, directly affecting patients' postoperative rehabilitation exercises and knee joint function recovery \u003csup\u003e\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e\u003c/sup\u003e. Therefore, for patients with inadequate response to conservative treatment, there is no need for excessive delay in surgical timing. Timely TKA can reduce the irreversible impact of chronic pain on neuromuscular function and improve early postoperative rehabilitation outcomes. Furthermore, preoperative uric acid level and tourniquet application time were identified as risk factors for prognosis at 2 weeks post-TKA. Hyperuricemia may affect postoperative rehabilitation through multiple mechanisms, including the deposition of urate crystals in periarticular soft tissues, inducing aseptic inflammation and exacerbating postoperative joint swelling and pain \u003csup\u003e\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e\u003c/sup\u003e; hyperuricemia can reduce collagen expression, increase the transcription levels of matrix-degrading enzymes and pro-inflammatory factors, and interfere with tissue repair, thereby hindering early functional recovery \u003csup\u003e\u003cspan additionalcitationids=\"CR34\" citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e35\u003c/span\u003e\u003c/sup\u003e; prolonged tourniquet application (\u0026gt;\u0026thinsp;60 minutes) may cause ischemia and hypoxia of lower limb tissues, leading to the production of a large number of reactive oxygen species after reperfusion, damaging vascular endothelial cells and myocytes, aggravating tissue edema and inflammatory response, increasing the incidence of adverse events \u003csup\u003e\u003cspan additionalcitationids=\"CR37\" citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e38\u003c/span\u003e\u003c/sup\u003e, and similarly delaying early recovery. Therefore, for patients with high preoperative uric acid levels, a low-purine diet and uric acid-lowering therapy should be implemented. During surgery, the duration and pressure of tourniquet application should be strictly controlled. For complex cases, intermittent release or tourniquet-free techniques should be adopted to minimize tissue damage \u003csup\u003e\u003cspan citationid=\"CR39\" class=\"CitationRef\"\u003e39\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eIn this study, a nomogram model was established to predict the probability of favorable knee joint function prognosis at 2 weeks post-TKA based on five independent risk factors: preoperative KSS functional score, preoperative SF-36 role-emotional score, duration of pain, uric acid level, and tourniquet application time. The nomogram demonstrated good discrimination (AUC of 0.81 and 0.75 in the training and validation sets, respectively), calibration (Hosmer-Lemeshow test P-values\u0026thinsp;\u0026gt;\u0026thinsp;0.05, Brier scores\u0026thinsp;\u0026lt;\u0026thinsp;0.2), and clinical utility (DCA net benefit superior to the extreme strategies of \"all intervention\" and \"no intervention\") in both the training and validation sets, indicating favorable and stable predictive performance of the model. However, the model's predictive ability has not reached an excellent level (AUC\u0026thinsp;\u0026gt;\u0026thinsp;0.9), which may be attributed to the relatively small sample size and fluctuations in knee joint function recovery among patients at 2 weeks postoperatively.\u003c/p\u003e \u003cp\u003eThis study also has several limitations: Firstly, it is a single-center retrospective study with a relatively limited sample size, which may introduce selection bias. The external generalization ability of the model needs to be further verified by multi-center, large-sample prospective studies. Secondly, potential influencing factors such as economic status, family rehabilitation support, and rehabilitation training adherence were not included, which may indirectly affect early rehabilitation by influencing patients' postoperative training compliance. Thirdly, the follow-up period was only 2 weeks postoperatively, and the long-term sustained impact of relevant risk factors on mid-term and long-term rehabilitation was not explored.\u003c/p\u003e"},{"header":"Conclusion","content":"\u003cp\u003eThis study focuses on the clinical challenge of early rehabilitation at 2 weeks post-TKA. Core variables were screened using Bootstrap-LASSO regression combined with multivariate Logistic regression, and a nomogram predictive model was constructed and validated. The model integrates five independent influencing factors: preoperative KSS functional score, SF-36 role-emotional score, duration of pain, uric acid level, and tourniquet application time, enabling individualized risk assessment and intervention. It facilitates the early identification of high-risk patients with poor early postoperative rehabilitation and improves TKA prognosis by implementing targeted measures such as preoperative prehabilitation, psychological counseling, uric acid control, and shortening tourniquet application time, thereby accelerating patients' early rehabilitation process and enhancing rehabilitation adherence.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eFunding\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis study was supported by the National Natural Science Foundation of China (82272558)；Beijing Natural Science Foundation（L252165）\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthics approval and consent to participate\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis study was approved by the Medical Ethics Committee of Chinese PLA General Hospital (Approval No.: S2025-581-01). The requirement for written informed consent was waived due to the retrospective nature of the study and the use of anonymized patient data. All procedures involving human participants, data or material fully complied with the Declaration of Helsinki.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent for publication\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCompeting interests\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors declare no competing financial interests.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthor contributions\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003ePengcheng Li: Data collection, Writing-original draft; Runkai Zhao: Investigation, Statistical analysis; Juntao Lu: Data curation, Writing-review \u0026amp; editing; Xiwei Zhang: Statistical analysis; Shuai Yang: Validation; Lin Hao: Validation; Haoran Wang: Formal analysis; Quanbo Ji: Conceptualization, Supervision, Funding acquisition, Writing-review \u0026amp; editing; Guoqiang Zhang: Conceptualization, Supervision, Funding acquisition, Writing-review \u0026amp; editing;\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData availability\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNo, I do not have any research data outside the submitted manuscript file. All data generated or analysed during this study are included in this published article.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eDuong, V. et al. Risk factors for the development of knee osteoarthritis across the lifespan: A systematic review and meta-analysis. Osteoarthritis Cartilage 33, 1162\u0026ndash;1179 (2025).\u003c/li\u003e\n\u003cli\u003eGiorgino, R. et al. Knee Osteoarthritis: Epidemiology, Pathogenesis, and Mesenchymal Stem Cells: What Else Is New? An Update. Int J Mol Sci 24, 6405 (2023).\u003c/li\u003e\n\u003cli\u003eChen, S. et al. Epidemiological trends and characteristics of osteoarthritis in China during 1990-2021. J Orthop Translat 51, 218\u0026ndash;226 (2025).\u003c/li\u003e\n\u003cli\u003eCui, A. et al. Global, regional prevalence, incidence and risk factors of knee osteoarthritis in population-based studies. EClinicalMedicine 29\u0026ndash;30, 100587 (2020).\u003c/li\u003e\n\u003cli\u003ePerruccio, A. V. et al. Osteoarthritis year in review 2023: Epidemiology \u0026amp; therapy. Osteoarthritis Cartilage 32, 159\u0026ndash;165 (2024).\u003c/li\u003e\n\u003cli\u003eYan, L. et al. Comparative efficacy and safety of exercise modalities in knee osteoarthritis: systematic review and network meta-analysis. BMJ 391, e085242 (2025).\u003c/li\u003e\n\u003cli\u003ePagan, C. A. et al. Technology in Total Knee Arthroplasty in 2023. J Arthroplasty 39, S54\u0026ndash;S59 (2024).\u003c/li\u003e\n\u003cli\u003eFeng, B. et al. Long-term clinical outcomes following total knee arthroplasty in patients with hemophilic arthropathy: a single-surgeon cohort after a 10- to 17-year follow-up. Chin Med J (Engl) 136, 1478\u0026ndash;1484 (2023).\u003c/li\u003e\n\u003cli\u003eMontagna, A. et al. A novel knee implant for total knee arthroplasty meets expectations at 10 years. First long-term follow-up report of clinical outcomes and survivorship. Knee Surg Sports Traumatol Arthrosc https://doi.org/10.1002/ksa.70037 (2025) doi:10.1002/ksa.70037.\u003c/li\u003e\n\u003cli\u003eLangenberger, B., Schrednitzki, D., Halder, A. M., Busse, R. \u0026amp; Pross, C. M. Predicting whether patients will achieve minimal clinically important differences following hip or knee arthroplasty. Bone Joint Res 12, 512\u0026ndash;521 (2023).\u003c/li\u003e\n\u003cli\u003eLundgren, L. S., Willems, N., Marchand, R. C., Batailler, C. \u0026amp; Lustig, S. Surgical factors play a critical role in predicting functional outcomes using machine learning in robotic-assisted total knee arthroplasty. Knee Surg Sports Traumatol Arthrosc 32, 3198\u0026ndash;3209 (2024).\u003c/li\u003e\n\u003cli\u003eStrahl, A. et al. A clinical risk score enables early prediction of dissatisfaction 1 year after total knee arthroplasty. Knee Surg Sports Traumatol Arthrosc 33, 252\u0026ndash;264 (2025).\u003c/li\u003e\n\u003cli\u003eLang, L. et al. An independently validated nomogram for individualised estimation of short-term mortality risk among patients with severe traumatic brain injury: a modelling analysis of the CENTER-TBI China Registry Study. EClinicalMedicine 59, 101975 (2023).\u003c/li\u003e\n\u003cli\u003eScuderi, G. R. et al. The new Knee Society Knee Scoring System. Clin Orthop Relat Res 470, 3\u0026ndash;19 (2012).\u003c/li\u003e\n\u003cli\u003eBellamy, N., Buchanan, W. W., Goldsmith, C. H., Campbell, J. \u0026amp; Stitt, L. W. Validation study of WOMAC: a health status instrument for measuring clinically important patient relevant outcomes to antirheumatic drug therapy in patients with osteoarthritis of the hip or knee. J Rheumatol 15, 1833\u0026ndash;1840 (1988).\u003c/li\u003e\n\u003cli\u003eWare, J. E. \u0026amp; Sherbourne, C. D. The MOS 36-item short-form health survey (SF-36). I. Conceptual framework and item selection. Med Care 30, 473\u0026ndash;483 (1992).\u003c/li\u003e\n\u003cli\u003eDeFrance, M. J. \u0026amp; Scuderi, G. R. Are 20% of Patients Actually Dissatisfied Following Total Knee Arthroplasty? A Systematic Review of the Literature. J Arthroplasty 38, 594\u0026ndash;599 (2023).\u003c/li\u003e\n\u003cli\u003eNakao, Y. et al. Preoperative Gait Speed as a Predictor of Patient-Reported Outcomes After Total Hip Arthroplasty: Insights from Patient Acceptable Symptom State and K-Means Clustering Analyses. J Bone Joint Surg Am. 25.00542 (2025) \u003c/li\u003e\n\u003cli\u003eMalec, J. F. \u0026amp; Ketchum, J. M. A Standard Method for Determining the Minimal Clinically Important Difference for Rehabilitation Measures. Arch Phys Med Rehabil 101, 1090\u0026ndash;1094 (2020).\u003c/li\u003e\n\u003cli\u003e\u0026Ccedil;elik, D., \u0026Ccedil;oban, \u0026Ouml;. \u0026amp; Kılı\u0026ccedil;oğlu, \u0026Ouml;. Minimal clinically important difference of commonly used hip-, knee-, foot-, and ankle-specific questionnaires: a systematic review. J Clin Epidemiol 113, 44\u0026ndash;57 (2019).\u003c/li\u003e\n\u003cli\u003eLee, W. C., Kwan, Y. H., Chong, H. C. \u0026amp; Yeo, S. J. The minimal clinically important difference for Knee Society Clinical Rating System after total knee arthroplasty for primary osteoarthritis. Knee Surg Sports Traumatol Arthrosc 25, 3354\u0026ndash;3359 (2017).\u003c/li\u003e\n\u003cli\u003eHarris, A. H. S. et al. Can Machine Learning Methods Produce Accurate and Easy-to-Use Preoperative Prediction Models of One-Year Improvements in Pain and Functioning After Knee Arthroplasty? J Arthroplasty 36, 112-117.e6 (2021).\u003c/li\u003e\n\u003cli\u003eZhang, W., Lu, X., Yang, N., Zhu, X. \u0026amp; Hu, H. Prehabilitation is effective in relieving pain after knee arthroplasty, but has little effect on length of stay and knee function: a meta-analysis of randomized controlled trials. Front Med (Lausanne) 12, 1457407 (2025).\u003c/li\u003e\n\u003cli\u003eWang, Z. et al. Effectiveness of Preoperative Rehabilitation Compared With Usual Care in Total Knee Arthroplasty: A Meta-analysis of Randomized Controlled Trials. Arch Phys Med Rehabil S0003-9993(25)00904\u0026ndash;9 (2025) \u003c/li\u003e\n\u003cli\u003eFranz, A., Ji, S., Bittersohl, B., Zilkens, C. \u0026amp; Behringer, M. Impact of a Six-Week Prehabilitation With Blood-Flow Restriction Training on Pre- and Postoperative Skeletal Muscle Mass and Strength in Patients Receiving Primary Total Knee Arthroplasty. Front Physiol 13, 881484 (2022).\u003c/li\u003e\n\u003cli\u003eAalders, M. B., van der List, J. P., Keijser, L. C. M. \u0026amp; Benner, J. L. Anxiety and depression prior to total knee arthroplasty are associated with worse pain and subjective function: A prospective comparative study. Knee Surg Sports Traumatol Arthrosc 33, 308\u0026ndash;318 (2025).\u003c/li\u003e\n\u003cli\u003eTen Noever de Brauw, G. V. et al. The mind matters: Psychological factors influence subjective outcomes following unicompartmental knee arthroplasty-A prospective study. Knee Surg Sports Traumatol Arthrosc 33, 239\u0026ndash;251 (2025).\u003c/li\u003e\n\u003cli\u003eSong, Q. et al. An ACC-VTA-ACC positive-feedback loop mediates the persistence of neuropathic pain and emotional consequences. Nat Neurosci 27, 272\u0026ndash;285 (2024).\u003c/li\u003e\n\u003cli\u003eChan, H. et al. Psychological stress increases skin infection through the action of TGF\u0026beta; to suppress immune-acting fibroblasts. Sci Immunol 10, eads0519 (2025).\u003c/li\u003e\n\u003cli\u003eNijs, J. et al. Central sensitisation in chronic pain conditions: latest discoveries and their potential for precision medicine. Lancet Rheumatol 3, e383\u0026ndash;e392 (2021).\u003c/li\u003e\n\u003cli\u003eVigotsky, A. D. et al. Prognostic value of preoperative mechanical hyperalgesia and neuropathic pain qualities for postoperative pain after total knee replacement. Eur J Pain 28, 1387\u0026ndash;1401 (2024).\u003c/li\u003e\n\u003cli\u003eYang, S., Liu, H., Fang, X.-M., Yan, F. \u0026amp; Zhang, Y. Signaling pathways in uric acid homeostasis and gout: From pathogenesis to therapeutic interventions. Int Immunopharmacol 132, 111932 (2024).\u003c/li\u003e\n\u003cli\u003eYu, J., Mi, T., Shao, Z. \u0026amp; Yan, X. The Outcomes of Patients With Hyperuricemia After Total Knee Arthroplasty: A Retrospective Cohort Study. Orthop Surg 17, 3477\u0026ndash;3487 (2025).\u003c/li\u003e\n\u003cli\u003eZhang, J. et al. The impact of uric acid on musculoskeletal diseases: clinical associations and underlying mechanisms. Front Endocrinol (Lausanne) 16, 1515176 (2025).\u003c/li\u003e\n\u003cli\u003eLiang, J. et al. Asymptomatic Hyperuricemia Is Associated with Achilles Tendon Rupture through Disrupting the Normal Functions of Tendon Stem/Progenitor Cells. Stem Cells Int 2022, 6795573 (2022).\u003c/li\u003e\n\u003cli\u003eCao, Z., Guo, J., Li, Q., Wu, J. \u0026amp; Li, Y. Comparison of efficacy and safety of different tourniquet applications in total knee arthroplasty: a network meta-analysis of randomized controlled trials. Ann Med 53, 1816\u0026ndash;1826 (2021).\u003c/li\u003e\n\u003cli\u003eAhmed, I. et al. Time to reconsider the routine use of tourniquets in total knee arthroplasty surgery. Bone Joint J 103-B, 830\u0026ndash;839 (2021).\u003c/li\u003e\n\u003cli\u003eTabata Fukushima, C. et al. Reactive oxygen species generation by reverse electron transfer at mitochondrial complex I under simulated early reperfusion conditions. Redox Biol 70, 103047 (2024).\u003c/li\u003e\n\u003cli\u003eZhong, Q. et al. Comparison of medium- and long-term total knee arthroplasty follow-up with or without tourniquet. BMC Musculoskelet Disord 26, 205 (2025).\u003c/li\u003e\n\u003c/ol\u003e"},{"header":"Tables","content":"\u003cp\u003eTable 1. Comparison of Clinical Data Between the Training Set and Validation Set\u003c/p\u003e\n\u003ctable border=\"0\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 25.0478%;\"\u003e\n \u003cp\u003e\u003cstrong\u003eVariables\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 22.7533%;\"\u003e\n \u003cp\u003e\u003cstrong\u003eTraining Set (n=247)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 22.5621%;\"\u003e\n \u003cp\u003e\u003cstrong\u003eValidation Set (n=50)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.3403%;\"\u003e\n \u003cp\u003e\u003cstrong\u003eX\u0026sup2;/t/Z\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 15.2964%;\"\u003e\n \u003cp\u003e\u003cstrong\u003eP value\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 25.0478%;\"\u003e\n \u003cp\u003eGender, n(%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.7533%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.5621%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.3403%;\"\u003e\n \u003cp\u003e0.371\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 15.2964%;\"\u003e\n \u003cp\u003e0.542\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 25.0478%;\"\u003e\n \u003cp\u003eMale\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.7533%;\"\u003e\n \u003cp\u003e54 (21.9)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.5621%;\"\u003e\n \u003cp\u003e9 (18.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.3403%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 15.2964%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 25.0478%;\"\u003e\n \u003cp\u003eFemale\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.7533%;\"\u003e\n \u003cp\u003e193 (78.1)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.5621%;\"\u003e\n \u003cp\u003e41 (82.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.3403%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 15.2964%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 25.0478%;\"\u003e\n \u003cp\u003eAge, n(%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.7533%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.5621%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.3403%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 15.2964%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 25.0478%;\"\u003e\n \u003cp\u003e\u0026le;65 years\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.7533%;\"\u003e\n \u003cp\u003e95 (38.5)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.5621%;\"\u003e\n \u003cp\u003e17 (34.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 14.3403%;\"\u003e\n \u003cp\u003e0.337\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 15.2964%;\"\u003e\n \u003cp\u003e0.561\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 25.0478%;\"\u003e\n \u003cp\u003e＞65 years\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.7533%;\"\u003e\n \u003cp\u003e152 (61.5)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.5621%;\"\u003e\n \u003cp\u003e33 (66.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 14.3403%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 15.2964%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 25.0478%;\"\u003e\n \u003cp\u003eBMI (kg/m\u0026sup2;)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.7533%;\"\u003e\n \u003cp\u003e26.9\u0026plusmn;3.4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.5621%;\"\u003e\n \u003cp\u003e26.3\u0026plusmn;3.4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 14.3403%;\"\u003e\n \u003cp\u003e-0.928\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 15.2964%;\"\u003e\n \u003cp\u003e0.353\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 25.0478%;\"\u003e\n \u003cp\u003eEducational level, n(%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.7533%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.5621%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 14.3403%;\"\u003e\n \u003cp\u003e1.249\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 15.2964%;\"\u003e\n \u003cp\u003e0.741\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 25.0478%;\"\u003e\n \u003cp\u003ePrimary school or below\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.7533%;\"\u003e\n \u003cp\u003e101 (40.9)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.5621%;\"\u003e\n \u003cp\u003e20 (40.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 14.3403%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 15.2964%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 25.0478%;\"\u003e\n \u003cp\u003eJunior high school\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.7533%;\"\u003e\n \u003cp\u003e77 (31.2)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.5621%;\"\u003e\n \u003cp\u003e13 (26.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 14.3403%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 15.2964%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 25.0478%;\"\u003e\n \u003cp\u003eSenior high school/Technical secondary school\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.7533%;\"\u003e\n \u003cp\u003e46 (18.6)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.5621%;\"\u003e\n \u003cp\u003e11 (22.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 14.3403%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 15.2964%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 25.0478%;\"\u003e\n \u003cp\u003eBachelor\u0026apos;s degree or above\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.7533%;\"\u003e\n \u003cp\u003e23 (9.3)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.5621%;\"\u003e\n \u003cp\u003e6 (12.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 14.3403%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 15.2964%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 25.0478%;\"\u003e\n \u003cp\u003eDiabetes mellitus, n(%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.7533%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.5621%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 14.3403%;\"\u003e\n \u003cp\u003e1.382\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 15.2964%;\"\u003e\n \u003cp\u003e0.240\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 25.0478%;\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.7533%;\"\u003e\n \u003cp\u003e198 (80.2)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.5621%;\"\u003e\n \u003cp\u003e43 (86.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 14.3403%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 15.2964%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 25.0478%;\"\u003e\n \u003cp\u003eYes\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.7533%;\"\u003e\n \u003cp\u003e49 (19.8)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.5621%;\"\u003e\n \u003cp\u003e7 (14.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 14.3403%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 15.2964%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 25.0478%;\"\u003e\n \u003cp\u003eComorbidity index\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.7533%;\"\u003e\n \u003cp\u003e3.0 (2.0,3.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.5621%;\"\u003e\n \u003cp\u003e3.0 (2.0,3.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 14.3403%;\"\u003e\n \u003cp\u003e-0.348\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 15.2964%;\"\u003e\n \u003cp\u003e0.728\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 25.0478%;\"\u003e\n \u003cp\u003eDuration of pain, n(%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.7533%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.5621%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.3403%;\"\u003e\n \u003cp\u003e1.261\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 15.2964%;\"\u003e\n \u003cp\u003e0.261\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 25.0478%;\"\u003e\n \u003cp\u003e＜10 years\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.7533%;\"\u003e\n \u003cp\u003e120 (48.6)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.5621%;\"\u003e\n \u003cp\u003e28 (56.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 14.3403%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 15.2964%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 25.0478%;\"\u003e\n \u003cp\u003e\u0026ge;10 years\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.7533%;\"\u003e\n \u003cp\u003e127 (51.4)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.5621%;\"\u003e\n \u003cp\u003e22 (44.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 14.3403%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 15.2964%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 25.0478%;\"\u003e\n \u003cp\u003ePostoperative hospital stay (days)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.7533%;\"\u003e\n \u003cp\u003e3.0（3.0,4.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.5621%;\"\u003e\n \u003cp\u003e4.0（3.0,4.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.3403%;\"\u003e\n \u003cp\u003e-0.746\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 15.2964%;\"\u003e\n \u003cp\u003e0.456\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 25.0478%;\"\u003e\n \u003cp\u003eTotal hospital stay (days)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.7533%;\"\u003e\n \u003cp\u003e7.0（7.0,9.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.5621%;\"\u003e\n \u003cp\u003e7.0（7.0,10.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.3403%;\"\u003e\n \u003cp\u003e-0.388\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 15.2964%;\"\u003e\n \u003cp\u003e0.698\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 25.0478%;\"\u003e\n \u003cp\u003ePreoperative knee flexion (\u0026deg;)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.7533%;\"\u003e\n \u003cp\u003e119.0（100.0,130.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.5621%;\"\u003e\n \u003cp\u003e110.0（100.0,124.3）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 14.3403%;\"\u003e\n \u003cp\u003e-1.371\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 15.2964%;\"\u003e\n \u003cp\u003e0.170\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 25.0478%;\"\u003e\n \u003cp\u003ePreoperative knee extension (\u0026deg;)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.7533%;\"\u003e\n \u003cp\u003e3.00（0.0,10.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.5621%;\"\u003e\n \u003cp\u003e3.00（0.0,10.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 14.3403%;\"\u003e\n \u003cp\u003e-0.284\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 15.2964%;\"\u003e\n \u003cp\u003e0.776\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 25.0478%;\"\u003e\n \u003cp\u003ePreoperative knee range of motion (\u0026deg;)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.7533%;\"\u003e\n \u003cp\u003e110.0（90.0,127.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.5621%;\"\u003e\n \u003cp\u003e107.5（90.0,120.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.3403%;\"\u003e\n \u003cp\u003e-1.012\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 15.2964%;\"\u003e\n \u003cp\u003e0.312\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eTable 2. Comparison of Imaging Data Between the Training Set and Validation Set\u003c/p\u003e\n\u003cdiv align=\"center\"\u003e\n \u003ctable border=\"0\" cellspacing=\"0\" cellpadding=\"0\" align=\"\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 24.7672%;\"\u003e\n \u003cp\u003e\u003cstrong\u003eVariables\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 22.905%;\"\u003e\n \u003cp\u003e\u003cstrong\u003eTraining Set (n=247)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 22.905%;\"\u003e\n \u003cp\u003e\u003cstrong\u003eValidation Set (n=50)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.3389%;\"\u003e\n \u003cp\u003e\u003cstrong\u003eX\u0026sup2;/t/Z\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 15.0838%;\"\u003e\n \u003cp\u003e\u003cstrong\u003eP value\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 24.7672%;\"\u003e\n \u003cp\u003eHKA (\u0026deg; )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e10.5（5.2,14.3）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e10.4（6.8,13.9）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.3389%;\"\u003e\n \u003cp\u003e-0.188\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 15.0838%;\"\u003e\n \u003cp\u003e0.851\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 24.7672%;\"\u003e\n \u003cp\u003eLower limb coronal alignment, n(%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 14.3389%;\"\u003e\n \u003cp\u003e1.552\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 15.0838%;\"\u003e\n \u003cp\u003e0.460\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 24.7672%;\"\u003e\n \u003cp\u003eVarus\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e202 (81.8)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e43 (86.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 14.3389%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 15.0838%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 24.7672%;\"\u003e\n \u003cp\u003eNeutral\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e20 (8.1)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e2 (4.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 14.3389%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 15.0838%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 24.7672%;\"\u003e\n \u003cp\u003eValgus\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e25 (10.1)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e5 (10.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 14.3389%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 15.0838%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 24.7672%;\"\u003e\n \u003cp\u003emMPTA (\u0026deg; )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e84.1（81.8,86.5）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e83.5（81.8,85.5）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.3389%;\"\u003e\n \u003cp\u003e-0.755\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 15.0838%;\"\u003e\n \u003cp\u003e0.450\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 24.7672%;\"\u003e\n \u003cp\u003emLDFA (\u0026deg; )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e89.1\u0026plusmn;3.4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e88.4\u0026plusmn;3.3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.3389%;\"\u003e\n \u003cp\u003e-1.281\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 15.0838%;\"\u003e\n \u003cp\u003e0.201\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 24.7672%;\"\u003e\n \u003cp\u003eJLCA (\u0026deg; )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e4.9（3.2,6.6）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e5.4\u0026plusmn;2.9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.3389%;\"\u003e\n \u003cp\u003e-0.744\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 15.0838%;\"\u003e\n \u003cp\u003e0.457\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 24.7672%;\"\u003e\n \u003cp\u003eFemoral AMA (\u0026deg; )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e6.7（5.9,7.7）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e6.45（5.6,7.9）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.3389%;\"\u003e\n \u003cp\u003e-0.338\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 15.0838%;\"\u003e\n \u003cp\u003e0.736\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 24.7672%;\"\u003e\n \u003cp\u003eOperative side K-L grade, n(%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 14.3389%;\"\u003e\n \u003cp\u003e2.977\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 15.0838%;\"\u003e\n \u003cp\u003e0.226\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 24.7672%;\"\u003e\n \u003cp\u003eGrade 2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e14 (5.7)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e1 (2.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 14.3389%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 15.0838%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 24.7672%;\"\u003e\n \u003cp\u003eGrade 3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e100 (40.5)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e18 (36.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 14.3389%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 15.0838%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 24.7672%;\"\u003e\n \u003cp\u003eGrade 4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e133 (53.8)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e31 (62.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 14.3389%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 15.0838%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 24.7672%;\"\u003e\n \u003cp\u003eContralateral K-L grade, n(%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 14.3389%;\"\u003e\n \u003cp\u003e8.151\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 15.0838%;\"\u003e\n \u003cp\u003e0.148\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 24.7672%;\"\u003e\n \u003cp\u003eGrade 2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e37 (15.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e6 (12.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 14.3389%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 15.0838%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 24.7672%;\"\u003e\n \u003cp\u003eGrade 3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e112 (45.3)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e21 (42.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 14.3389%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 15.0838%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 24.7672%;\"\u003e\n \u003cp\u003eGrade 4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e39 (15.8)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e15 (30.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 14.3389%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 15.0838%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 24.7672%;\"\u003e\n \u003cp\u003eTKA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e59 (23.9)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 22.905%;\"\u003e\n \u003cp\u003e8 (16.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 14.3389%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 15.0838%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n\u003c/div\u003e\n\u003cp\u003eHKA, Hip-Knee-Ankle angle; mMPTA, Mechanical Medial Proximal Tibial Angle; mLDFA, Mechanical Lateral Distal Femoral Angle; JLCA, Joint Line Convergence Angle; AMA, Anatomical Mechanical Axis Angle; K-L, Kellgren-Lawrence; TKA, Total Knee Arthroplasty.\u003c/p\u003e\n\u003cp\u003eTable 3. Comparison of Surgery-Related Data Between the Training Set and Validation Set\u003c/p\u003e\n\u003ctable border=\"0\" cellspacing=\"0\" cellpadding=\"0\" align=\"\" width=\"583\"\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eVariables\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eTraining Set (n=247)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eValidation Set (n=50)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eX\u0026sup2;/t/Z\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eP value\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003eSurgical side, n(%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e1.138\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e0.566\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003eLeft\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e122 (49.4)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e28 (56.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003eRight\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e125 (50.6)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e22 (44.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003eAnesthesia method, n(%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e2.903\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e0.574\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003eGeneral anesthesia\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e133 (53.8)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e29 (58.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003eSpinal anesthesia\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e120 (48.6)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e2 (4.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003eGeneral anesthesia + Spinal anesthesia\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e6 (2.4)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e2 (4.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003eGeneral anesthesia + Nerve block\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e88 (35.6)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e17 (34.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003eRobot-assisted surgery, n(%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e2.221\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e0.329\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e88 (35.6)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e23 (46.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003eYes\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e159 (64.4)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e27 (54.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003eTourniquet application time, n(%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e3.265\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e0.071\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003e\u0026le;60 min\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e98 (39.7)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e27 (54.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003e＞60 min\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e149 (60.3)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e23 (46.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003eOperation time (min)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e105.0（92.0,120.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e101.5（84.0,117.3）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e-1.419\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e0.156\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003ePatellar resurfacing, n(%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e1.742\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e0.628\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e152 (61.5)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e32 (64.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003eYes\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e95 (38.5)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e18 (36.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003eProsthesis brand, n(%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e12.733\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e0.121\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003eStryker\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e49 (19.8)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e7 (14.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003eSmith \u0026amp; Nephew\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e45 (18.2)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e2 (4.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003eJohnson \u0026amp; Johnson\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e81 (32.8)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e22 (44.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003eZhengtian\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e46 (18.6)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e15 (30.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003eZimmer Biomet\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e19 (7.7)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e4 (8.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003eDabo Medical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e5 (2.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e0 (0.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003eAikang\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e2 (0.8)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e0 (0.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003eProsthesis type, n(%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e4.435\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e0.109\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003ePS\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e209 (84.6)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e47 (94.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003eCR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e38 (15.4)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e3 (6.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003eFemoral prosthesis size\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e5.0（4.0,6.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e4.5（4.0,6.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e-0.675\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e0.500\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003eTibial prosthesis size\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e4.0（3.0,5.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e4.0（3.0,5.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e-1.113\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e0.266\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003eLiner thickness\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e8.0（6.0,9.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e8.0（5.0,9.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e-1.236\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e0.217\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003eIntraoperative PRP, n(%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e0.956\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e0.620\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e183 (74.1)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e36 (72.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 198px;\"\u003e\n \u003cp\u003eYes\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 135px;\"\u003e\n \u003cp\u003e64 (25.9)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 137px;\"\u003e\n \u003cp\u003e14 (28.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003ePS, Posterior Cruciate Ligament-Substituting; CR, Posterior Cruciate Ligament-Retaining; PRP, Platelet-Rich Plasma.\u003c/p\u003e\n\u003cp\u003eTable 4. Comparison of Hematological Data Between the Training Set and Validation Set\u003c/p\u003e\n\u003ctable border=\"0\" cellspacing=\"0\" cellpadding=\"0\" align=\"\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 131px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eVariables\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 119px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eTraining Set (n=247)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 118px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eValidation Set (n=50)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 75px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eX\u0026sup2;/t/Z\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 80px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eP value\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 131px;\"\u003e\n \u003cp\u003eWhite blood cell count (10⁹/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 119px;\"\u003e\n \u003cp\u003e5.6（4.7,6.3）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 118px;\"\u003e\n \u003cp\u003e5.4（4.6,6.1）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 75px;\"\u003e\n \u003cp\u003e-0.723\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 80px;\"\u003e\n \u003cp\u003e0.470\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 131px;\"\u003e\n \u003cp\u003eNeutrophil-to-lymphocyte ratio\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 119px;\"\u003e\n \u003cp\u003e1.5（1.2,1.9）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 118px;\"\u003e\n \u003cp\u003e1.7（1.2,2.1）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 75px;\"\u003e\n \u003cp\u003e-1.163\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 80px;\"\u003e\n \u003cp\u003e0.245\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 131px;\"\u003e\n \u003cp\u003ePlatelet-to-lymphocyte ratio\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 119px;\"\u003e\n \u003cp\u003e112.1（90.2,137.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 118px;\"\u003e\n \u003cp\u003e118.0（94.8,145.1）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 75px;\"\u003e\n \u003cp\u003e-1.184\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 80px;\"\u003e\n \u003cp\u003e0.237\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 131px;\"\u003e\n \u003cp\u003eHemoglobin (g/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 119px;\"\u003e\n \u003cp\u003e128.8\u0026plusmn;12.1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 118px;\"\u003e\n \u003cp\u003e126.7\u0026plusmn;11.9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 75px;\"\u003e\n \u003cp\u003e-1.098\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 80px;\"\u003e\n \u003cp\u003e0.273\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 131px;\"\u003e\n \u003cp\u003eRed blood cell distribution width (L/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 119px;\"\u003e\n \u003cp\u003e12.5（12.1,13.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 118px;\"\u003e\n \u003cp\u003e12.5（12.0,12.8）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 75px;\"\u003e\n \u003cp\u003e-0.655\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 80px;\"\u003e\n \u003cp\u003e0.513\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 131px;\"\u003e\n \u003cp\u003eErythrocyte sedimentation rate (mm/h)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 119px;\"\u003e\n \u003cp\u003e9.0（5.0,13.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 118px;\"\u003e\n \u003cp\u003e9.0（6.0,15.3）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 75px;\"\u003e\n \u003cp\u003e-0.266\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 80px;\"\u003e\n \u003cp\u003e0.790\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 131px;\"\u003e\n \u003cp\u003eSerum albumin (g/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 119px;\"\u003e\n \u003cp\u003e41.1\u0026plusmn;2.7\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 118px;\"\u003e\n \u003cp\u003e40.6\u0026plusmn;2.8\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 75px;\"\u003e\n \u003cp\u003e-1.014\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 80px;\"\u003e\n \u003cp\u003e0.312\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 131px;\"\u003e\n \u003cp\u003eUric acid (umol/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 119px;\"\u003e\n \u003cp\u003e296.6\u0026plusmn;72.0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 118px;\"\u003e\n \u003cp\u003e296.1\u0026plusmn;76.07\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 75px;\"\u003e\n \u003cp\u003e-0.041\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 80px;\"\u003e\n \u003cp\u003e0.968\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 131px;\"\u003e\n \u003cp\u003eC-reactive protein, n(%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 119px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 118px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 75px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 80px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 131px;\"\u003e\n \u003cp\u003eNormal\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 119px;\"\u003e\n \u003cp\u003e169 (68.4)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 118px;\"\u003e\n \u003cp\u003e33 (66.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 75px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 80px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 131px;\"\u003e\n \u003cp\u003eAbnormal\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 119px;\"\u003e\n \u003cp\u003e78 (31.6)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 118px;\"\u003e\n \u003cp\u003e17 (34.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 75px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 80px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 131px;\"\u003e\n \u003cp\u003eSodium (mmol/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 119px;\"\u003e\n \u003cp\u003e142.1（140.8,143.4）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 118px;\"\u003e\n \u003cp\u003e142.0 (140.8,143.8)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 75px;\"\u003e\n \u003cp\u003e-0.161\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 80px;\"\u003e\n \u003cp\u003e0.872\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 131px;\"\u003e\n \u003cp\u003eInterleukin-6, n(%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 119px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 118px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 75px;\"\u003e\n \u003cp\u003e0.443\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 80px;\"\u003e\n \u003cp\u003e0.509\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 131px;\"\u003e\n \u003cp\u003eNormal\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 119px;\"\u003e\n \u003cp\u003e211 (85.4)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 118px;\"\u003e\n \u003cp\u003e41 (82.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 75px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 80px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 131px;\"\u003e\n \u003cp\u003eAbnormal\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 119px;\"\u003e\n \u003cp\u003e36 (14.6)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 118px;\"\u003e\n \u003cp\u003e9 (18.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 75px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 80px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 131px;\"\u003e\n \u003cp\u003eProthrombin time (s)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 119px;\"\u003e\n \u003cp\u003e11.2（10.9,11.7）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 118px;\"\u003e\n \u003cp\u003e11.3（10.8,11.7）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 75px;\"\u003e\n \u003cp\u003e-0.388\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 80px;\"\u003e\n \u003cp\u003e0.698\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 131px;\"\u003e\n \u003cp\u003eInternational normalized ratio\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 119px;\"\u003e\n \u003cp\u003e0.97（0.94,1.03）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 118px;\"\u003e\n \u003cp\u003e0.98 (0.96,1.04)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 75px;\"\u003e\n \u003cp\u003e-0.457\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 80px;\"\u003e\n \u003cp\u003e0.648\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 131px;\"\u003e\n \u003cp\u003eActivated partial thromboplastin time (s)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 119px;\"\u003e\n \u003cp\u003e28.4（26.5,31.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 118px;\"\u003e\n \u003cp\u003e28.3(25.7,30.3)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 75px;\"\u003e\n \u003cp\u003e-0.972\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 80px;\"\u003e\n \u003cp\u003e0.331\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 131px;\"\u003e\n \u003cp\u003eFibrinogen (g/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 119px;\"\u003e\n \u003cp\u003e2.9（2.5,3.3）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 118px;\"\u003e\n \u003cp\u003e2.9（2.7,3.3）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 75px;\"\u003e\n \u003cp\u003e-0.409\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 80px;\"\u003e\n \u003cp\u003e0.683\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003eNormal range of C-reactive protein: 0-0.8 mg/dL; Normal range of interleukin-6: 0-5.9 pg/ml.\u003c/p\u003e\n\u003cp\u003eTable 5. Comparison of Scale Scores Between the Training Set and Validation Set\u003c/p\u003e\n\u003cdiv align=\"\"\u003e\n \u003ctable border=\"0\" cellspacing=\"0\" cellpadding=\"0\" width=\"588\"\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 229px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eVariables\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 117px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eTraining Set\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003e(n=247)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 119px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eValidation Set\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003e(n=50)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eX\u0026sup2;/t/Z\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eP value\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 229px;\"\u003e\n \u003cp\u003ePreoperative WOMAC pain (points)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 117px;\"\u003e\n \u003cp\u003e10.0（7.0,12.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 119px;\"\u003e\n \u003cp\u003e9.5\u0026plusmn;4.7\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e-0.365\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0.715\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 229px;\"\u003e\n \u003cp\u003ePreoperative WOMAC stiffness (points)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 117px;\"\u003e\n \u003cp\u003e4.0（2.0,5.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 119px;\"\u003e\n \u003cp\u003e4.0（2.0,6.00）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e-0.054\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0.957\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 229px;\"\u003e\n \u003cp\u003ePreoperative WOMAC function (points)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 117px;\"\u003e\n \u003cp\u003e28.0（17.0,37.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 119px;\"\u003e\n \u003cp\u003e24.5（16.0,33.8）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e-0.559\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0.576\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 229px;\"\u003e\n \u003cp\u003ePreoperative WOMAC total score (points)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 117px;\"\u003e\n \u003cp\u003e42.0（26.0,53.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 119px;\"\u003e\n \u003cp\u003e36.5（26.3,48.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e-0.529\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0.597\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 229px;\"\u003e\n \u003cp\u003e2-week WOMAC pain (points)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 117px;\"\u003e\n \u003cp\u003e6.0（5.0,9.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 119px;\"\u003e\n \u003cp\u003e6.0（3.0,9.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e-0.527\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0.598\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 229px;\"\u003e\n \u003cp\u003e2-week WOMAC stiffness (points)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 117px;\"\u003e\n \u003cp\u003e2.0（2.0,4.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 119px;\"\u003e\n \u003cp\u003e3.0（2.0,4.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e-1.012\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0.311\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 229px;\"\u003e\n \u003cp\u003e2-week WOMAC function (points)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 117px;\"\u003e\n \u003cp\u003e20.0（13.0,30.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 119px;\"\u003e\n \u003cp\u003e21.0（13.5,35.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e-1.361\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0.174\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 229px;\"\u003e\n \u003cp\u003e2-week WOMAC total score (points)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 117px;\"\u003e\n \u003cp\u003e29.0（21.0,41.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 119px;\"\u003e\n \u003cp\u003e30.0（20.0,45.3）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e-0.951\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0.342\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 229px;\"\u003e\n \u003cp\u003ePreoperative KSS symptoms (points)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 117px;\"\u003e\n \u003cp\u003e13.0（11.0,15.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 119px;\"\u003e\n \u003cp\u003e13.0（12.0,14.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e-0.009\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0.993\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 229px;\"\u003e\n \u003cp\u003ePreoperative KSS satisfaction (points)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 117px;\"\u003e\n \u003cp\u003e14.0（10.0,20.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 119px;\"\u003e\n \u003cp\u003e14.0（10.0,19.5）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e-0.272\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0.785\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 229px;\"\u003e\n \u003cp\u003ePreoperative KSS expectation (points)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 117px;\"\u003e\n \u003cp\u003e15.0（14.0,15.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 119px;\"\u003e\n \u003cp\u003e15.0（13.0,15.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e-1.526\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0.127\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 229px;\"\u003e\n \u003cp\u003ePreoperative KSS function (points)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 117px;\"\u003e\n \u003cp\u003e39.3\u0026plusmn;19.6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 119px;\"\u003e\n \u003cp\u003e36.8\u0026plusmn;17.5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e-0.828\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0.408\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 229px;\"\u003e\n \u003cp\u003e2-week KSS symptoms (points)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 117px;\"\u003e\n \u003cp\u003e11.0（8.5,13.5）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 119px;\"\u003e\n \u003cp\u003e11.0（8.0,15.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e-0.889\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0.374\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 229px;\"\u003e\n \u003cp\u003e2-week KSS function (points)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 117px;\"\u003e\n \u003cp\u003e42.4\u0026plusmn;19.8\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 119px;\"\u003e\n \u003cp\u003e36.56\u0026plusmn;17.0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e-1.931\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0.054\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 229px;\"\u003e\n \u003cp\u003ePreoperative SF-36 physical function (points)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 117px;\"\u003e\n \u003cp\u003e40.0（20.0,55.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 119px;\"\u003e\n \u003cp\u003e40.0 (25.0,46.3)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e-0.673\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0.501\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 229px;\"\u003e\n \u003cp\u003ePreoperative SF-36 role-physical (points)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 117px;\"\u003e\n \u003cp\u003e0.0（0.0,75.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 119px;\"\u003e\n \u003cp\u003e0.0（0.0,50.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e-0.334\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0.739\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 229px;\"\u003e\n \u003cp\u003ePreoperative SF-36 bodily pain (points)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 117px;\"\u003e\n \u003cp\u003e51.0（31.0,62.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 119px;\"\u003e\n \u003cp\u003e42.00(31.0,62.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e-0.220\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0.826\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 229px;\"\u003e\n \u003cp\u003ePreoperative SF-36 general health (points)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 117px;\"\u003e\n \u003cp\u003e62.0（47.0,72.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 119px;\"\u003e\n \u003cp\u003e57.0 (46.5,70.5)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e-1.773\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0.076\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 229px;\"\u003e\n \u003cp\u003ePreoperative SF-36 vitality (points)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 117px;\"\u003e\n \u003cp\u003e60.0（45.0,75.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 119px;\"\u003e\n \u003cp\u003e65.0（45.0,75.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e-0.598\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0.550\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 229px;\"\u003e\n \u003cp\u003ePreoperative SF-36 social function (points)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 117px;\"\u003e\n \u003cp\u003e55.6（44.4,77.8）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 119px;\"\u003e\n \u003cp\u003e66.7 (44.4,77.8)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e-0.272\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0.786\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 229px;\"\u003e\n \u003cp\u003ePreoperative SF-36 role-emotional (points)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 117px;\"\u003e\n \u003cp\u003e100.0（0.0,100.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 119px;\"\u003e\n \u003cp\u003e100.0（0.0,100.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e-0.512\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0.608\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 229px;\"\u003e\n \u003cp\u003ePreoperative SF-36 mental health (points)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 117px;\"\u003e\n \u003cp\u003e72.0（56.0,88.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 119px;\"\u003e\n \u003cp\u003e68.0 (60.0,81.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e-0.794\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0.427\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 229px;\"\u003e\n \u003cp\u003ePreoperative SF-36 health transition (points)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 117px;\"\u003e\n \u003cp\u003e50.0（50.0,75.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 119px;\"\u003e\n \u003cp\u003e50.0（50.0,75.0）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e-0.381\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0.703\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 229px;\"\u003e\n \u003cp\u003ePreoperative SF-36 PCS (points)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 117px;\"\u003e\n \u003cp\u003e40.1（35.8,46.7）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 119px;\"\u003e\n \u003cp\u003e39.60 (35.5,48.9)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e-1.031\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0.302\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 229px;\"\u003e\n \u003cp\u003ePreoperative SF-36 MCS (points)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 117px;\"\u003e\n \u003cp\u003e45.4（38.1,53.5）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 119px;\"\u003e\n \u003cp\u003e44.2（36.7,52.3）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e-0.664\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0.507\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 229px;\"\u003e\n \u003cp\u003e2-week postoperative satisfaction, n(%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 117px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 119px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e0.976\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0.502\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 229px;\"\u003e\n \u003cp\u003eTerrible\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 117px;\"\u003e\n \u003cp\u003e25 (10.1)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 119px;\"\u003e\n \u003cp\u003e6 (12.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 229px;\"\u003e\n \u003cp\u003ePoor\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 117px;\"\u003e\n \u003cp\u003e61 (24.7)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 119px;\"\u003e\n \u003cp\u003e13 (26.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 229px;\"\u003e\n \u003cp\u003eGood\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 117px;\"\u003e\n \u003cp\u003e100 (40.5)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 119px;\"\u003e\n \u003cp\u003e21 (42.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 229px;\"\u003e\n \u003cp\u003eExcellent\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 117px;\"\u003e\n \u003cp\u003e61 (24.7)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 119px;\"\u003e\n \u003cp\u003e10 (20.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n\u003c/div\u003e\n\u003cp\u003eWOMAC, Western Ontario and McMaster Universities Osteoarthritis Index; KSS, Knee Society Score; SF-36, 36-Item Short Form Health Survey; PCS, Physical Component Summary; MCS, Mental Component Summary.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eTable 6. Multivariate Logistic Regression Analysis for Screening Independent Risk Factors\u003c/p\u003e\n\u003ctable border=\"0\" cellspacing=\"0\" cellpadding=\"0\" align=\"left\" width=\"544\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 113px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eVariables\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eB\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 85px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eStandard Error (SE)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 87px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eWald (z)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 125px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eOR (95%CI)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 77px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eP value\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 113px;\"\u003e\n \u003cp\u003eConstant\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e0.508\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 85px;\"\u003e\n \u003cp\u003e0.852\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 87px;\"\u003e\n \u003cp\u003e0.596\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 125px;\"\u003e\n \u003cp\u003e1.662(0.313-9.015)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 77px;\"\u003e\n \u003cp\u003e0.551\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 113px;\"\u003e\n \u003cp\u003ePreoperative KSS function\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e-0.057\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 85px;\"\u003e\n \u003cp\u003e0.012\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 87px;\"\u003e\n \u003cp\u003e-4.991\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 125px;\"\u003e\n \u003cp\u003e0.944(0.922-0.965)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 77px;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 113px;\"\u003e\n \u003cp\u003ePreoperative SF-36 role-emotional\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e-0.011\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 85px;\"\u003e\n \u003cp\u003e0.004\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 87px;\"\u003e\n \u003cp\u003e-2.946\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 125px;\"\u003e\n \u003cp\u003e0.989 (0.982-0.996)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 77px;\"\u003e\n \u003cp\u003e0.003\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 113px;\"\u003e\n \u003cp\u003eDuration of pain\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e-0.852\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 85px;\"\u003e\n \u003cp\u003e0.356\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 87px;\"\u003e\n \u003cp\u003e-2.396\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 125px;\"\u003e\n \u003cp\u003e0.426(0.209-0.847)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 77px;\"\u003e\n \u003cp\u003e0.017\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 113px;\"\u003e\n \u003cp\u003eUric acid\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e0.005\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 85px;\"\u003e\n \u003cp\u003e0.002\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 87px;\"\u003e\n \u003cp\u003e2.161\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 125px;\"\u003e\n \u003cp\u003e1.005(1.001-1.010)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 77px;\"\u003e\n \u003cp\u003e0.031\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 113px;\"\u003e\n \u003cp\u003eTourniquet application time\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 57px;\"\u003e\n \u003cp\u003e0.727\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 85px;\"\u003e\n \u003cp\u003e0.355\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 87px;\"\u003e\n \u003cp\u003e2.049\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 125px;\"\u003e\n \u003cp\u003e2.068(1.042-4.206)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 77px;\"\u003e\n \u003cp\u003e0.041\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"bmc-musculoskeletal-disorders","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bmsd","sideBox":"Learn more about [BMC Musculoskeletal Disorders](http://bmcmusculoskeletdisord.biomedcentral.com/)","snPcode":"","submissionUrl":"https://author-welcome.nature.com/12891","title":"BMC Musculoskeletal Disorders","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Total knee arthroplasty, Predictive model, Early rehabilitation, Nomogram","lastPublishedDoi":"10.21203/rs.3.rs-8514723/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8514723/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eObjective\u003c/h2\u003e \u003cp\u003eTo comprehensively evaluate the significance of multidimensional perioperative indicators for the prognosis following total knee arthroplasty (TKA), construct and validate a nomogram model for predicting optimal early knee joint function recovery at 2 weeks post-TKA, and provide evidence-based support for clinical precise intervention, thereby accelerating patients' rehabilitation process and improving the quality of prognosis.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eA total of 297 patients with end-stage knee osteoarthritis (KOA) who underwent TKA were retrospectively enrolled and divided into a training set (n\u0026thinsp;=\u0026thinsp;247) and a validation set (n\u0026thinsp;=\u0026thinsp;50) at a ratio of 5:1. Multidimensional data, including demographic characteristics, surgical indicators, imaging parameters, hematological results, and scale scores, were systematically collected preoperatively and perioperatively. The minimum clinically important difference (MCID) of the Knee Society Score (KSS) functional score was calculated using the anchor-based method and defined as the primary outcome variable. Variables were initially screened via Bootstrap-LASSO regression, and a nomogram model was constructed by integrating multivariate Logistic regression to identify independent risk factors affecting prognosis. The model performance was evaluated in terms of discrimination, calibration, and clinical utility through receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA), respectively.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eThe MCID of the KSS functional score at 2 weeks post-TKA was determined to be 8.2. Multivariate Logistic regression analysis revealed that preoperative KSS functional score (OR\u0026thinsp;=\u0026thinsp;0.944, 95% CI: 0.922\u0026ndash;0.965, P\u0026thinsp;\u0026lt;\u0026thinsp;0.001), SF-36 role-emotional score (OR\u0026thinsp;=\u0026thinsp;0.989, 95% CI: 0.982\u0026ndash;0.996, P\u0026thinsp;=\u0026thinsp;0.003), and duration of pain (OR\u0026thinsp;=\u0026thinsp;0.426, 95% CI: 0.209\u0026ndash;0.847, P\u0026thinsp;=\u0026thinsp;0.017) were protective factors; whereas preoperative uric acid level (OR\u0026thinsp;=\u0026thinsp;1.005, 95% CI: 1.001\u0026ndash;1.010, P\u0026thinsp;=\u0026thinsp;0.031) and tourniquet application time (OR\u0026thinsp;=\u0026thinsp;2.068, 95% CI: 1.042\u0026ndash;4.206, P\u0026thinsp;=\u0026thinsp;0.041) were independent risk factors. The area under the ROC curve (AUC) of the nomogram model was 0.81 (95% CI: 0.75\u0026ndash;0.87) in the training set and 0.75 (95% CI: 0.55\u0026ndash;0.95) in the validation set. The Hosmer-Lemeshow goodness-of-fit test yielded P-values\u0026thinsp;\u0026gt;\u0026thinsp;0.05 in both sets, with Brier scores\u0026thinsp;\u0026le;\u0026thinsp;0.171. The decision curve analysis demonstrated that the net benefit of the nomogram was superior to the extreme strategies of \"Treat all\" or \"Treat none\".\u003c/p\u003e\u003ch2\u003eConclusion\u003c/h2\u003e \u003cp\u003eThe nomogram constructed based on 5 independent factors effectively predicts the early rehabilitation outcome after TKA with favorable performance. It facilitates the early identification of high-risk patients and the implementation of targeted interventions in clinical practice, providing a valuable reference for the development of individualized perioperative rehabilitation strategies.\u003c/p\u003e","manuscriptTitle":"Predictive Model for Early Prognosis After Total Knee Arthroplasty Based on Multidimensional Indicators","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-16 08:54:06","doi":"10.21203/rs.3.rs-8514723/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-02-04T08:08:22+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-03T07:14:07+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"319257791120859931442974388825953340569","date":"2026-01-21T11:18:50+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"253213038271087750090412879630628279391","date":"2026-01-15T08:42:06+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"137318729544147513450169027470041665179","date":"2026-01-13T03:12:11+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-12T09:53:08+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"179417623402198462376753577626155716164","date":"2026-01-12T06:02:36+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-01-12T05:42:07+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-01-09T08:55:38+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-01-09T08:52:36+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-01-08T12:42:43+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Musculoskeletal Disorders","date":"2026-01-08T12:30:45+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-musculoskeletal-disorders","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bmsd","sideBox":"Learn more about [BMC Musculoskeletal Disorders](http://bmcmusculoskeletdisord.biomedcentral.com/)","snPcode":"","submissionUrl":"https://author-welcome.nature.com/12891","title":"BMC Musculoskeletal Disorders","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"cdfb01eb-10f5-4c35-95fe-b98165d4481d","owner":[],"postedDate":"January 16th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-04-07T16:03:58+00:00","versionOfRecord":{"articleIdentity":"rs-8514723","link":"https://doi.org/10.1186/s12891-026-09693-1","journal":{"identity":"bmc-musculoskeletal-disorders","isVorOnly":false,"title":"BMC Musculoskeletal Disorders"},"publishedOn":"2026-04-01 15:58:12","publishedOnDateReadable":"April 1st, 2026"},"versionCreatedAt":"2026-01-16 08:54:06","video":"","vorDoi":"10.1186/s12891-026-09693-1","vorDoiUrl":"https://doi.org/10.1186/s12891-026-09693-1","workflowStages":[]},"version":"v1","identity":"rs-8514723","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8514723","identity":"rs-8514723","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}