Efficacy and Efficiency of Artificial Intelligence-based Preoperative Anesthesia Evaluation: A Randomized Controlled Non-Inferiority Study

Efficacy and Efficiency of Artificial Intelligence-based Preoperative Anesthesia Evaluation: A Randomized Controlled Non-Inferiority Study | 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 Efficacy and Efficiency of Artificial Intelligence-based Preoperative Anesthesia Evaluation: A Randomized Controlled Non-Inferiority Study Jiangtao Qi, Jingjing Shen, Yiqi Wu, Shuchi Zhang, Daojie Xu, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7364932/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 8 You are reading this latest preprint version Abstract Study Objective: To evaluate the clinical effectiveness and feasibility of a novel AI-assisted anesthesia evaluation system compared with conventional preoperative anesthesia assessments. Design: Single-center, randomized, parallel-group, open-label, non-inferiority trial. Patients: 600 adult patients scheduled for elective non-cardiac surgery under general anesthesia were randomly assigned to AI-assisted assessment group or traditional in-person anesthesia evaluation group. Measurements: The primary outcome was the accuracy of ASA (American Society of Anesthesiologists) physical status classification. Secondary outcomes included the quality and completeness of medical history documentation, assessment duration, and patient satisfaction. Main Results: The AI-assisted group achieved non-inferior accuracy in ASA classification compared to the traditional group (93.3% [280/300] vs. 91.7% [275/300], P = 0.033). The difference in accuracy was 1.6% (95% CI: -2.6% to 5.9%), with the lower bound above the predefined non-inferiority margin of -5%. The AI system demonstrated significantly higher documentation quality, including fewer missing items (4.3% vs. 21.7%) and incorrect entries (7.0% vs. 18.0%). Assessment time was markedly shorter in the AI group (3.0 [2.0-5.0] vs. 7.0 [6.0-8.0] minutes, P < 0.001), and overall patient satisfaction was significantly higher (87.3% [262/300] vs. 76.0% [228/300], P < 0.01). Conclusions: The AI-assisted anesthesia evaluation system was non-inferior to traditional assessment in ASA classification accuracy while offering superior efficiency, documentation quality, and patient satisfaction. This AI-based approach may represent a scalable and effective alternative for preoperative anesthesia evaluations across diverse clinical settings. Registry: chictr.org.cn, TRN: ChiCTR2400086869, Registration date: 12 July 2024. Retrospectively registered Artificial intelligence Anesthesia assessment Randomized controlled trial Noninferiority Figures Figure 1 Figure 2 Figure 3 Figure 4 Introduction Patient safety remains a central concern in modern healthcare. A recent study in The New England Journal of Medicine reported that 23% of hospitalized patients experienced at least one adverse event, with surgical and medication-related incidents being the most frequent; notably, 22% of these were preventable 1 . Surgery offers both the promise of cure and the risk of harm - it is a double-edged sword capable of resolving disease yet potentially inducing complications. Perioperative adverse event rates can reach as high as 36.8% 2 . Anesthesiologists play a pivotal role in perioperative safety, being responsible for risk assessment, airway management, vital signs monitoring, and pain control 3 . Among these duties, preoperative anesthesia evaluation is essential for ensuring patient safety, reducing postoperative complications, shortening hospitalization, improving clinical outcomes, and lowering healthcare costs 4 , 5 . Anesthesia evaluation involves reviewing a patient’s medical history, physical examination, and diagnostic results to assess their overall condition, followed by tailoring an anesthesia plan to the patient’s health status and surgical requirements. The ultimate goal is to reduce perioperative morbidity and mortality while facilitating rapid recovery 6 . For anesthesiologists, this process enables optimal selection of anesthetic techniques and drugs, while from the patient’s perspective, it provides opportunities for risk discussion, reassurance, and anxiety reduction. Comprehensive evaluation improves efficiency and satisfaction while lowering complication rates 7 , whereas inadequate assessment may cause surgical delays, waste resources, and threaten patient safety 8 . In recent years, completing standardized anesthesia assessments for all patients has become increasingly challenging due to global population aging and the growth of outpatient surgery. Aging populations have increased the number of surgical candidates with multiple comorbidities, functional decline, reduced respiratory reserve, frailty, neurocognitive impairment, mobility limitations, and polypharmacy 9 – 12 , necessitating more careful evaluations. Advances in surgical techniques have expanded outpatient surgery, which offers low cancellation rates, shorter waits, reduced costs, and fewer nosocomial infections 13 , 14 , but rapid turnover requires early identification and optimization of health issues. Alternatives to in-person anesthesia clinics include remote telephone/video consultations and questionnaire-assisted screening. In-person clinics foster trust and allow thorough examination 16 , but require significant patient time and resources. Remote evaluations, more frequently studied abroad 17 – 19 , improve convenience and satisfaction but often serve as supplementary methods. Wienhold et al. demonstrated the feasibility and high satisfaction of a teleconsultation-based anesthesia platform, though with high technical requirements 20 . Questionnaire-based screening has also been developed internationally to improve efficiency 21 , 22 . The rise of artificial intelligence (AI) and mobile health (mHealth) offers promising solutions 23 . Since the U.S. FDA’s first approval of AI for clinical use in 2018, AI has been applied in diagnosis, screening, and prediction 24 . Machine learning enables computers to process complex clinical data and assist in decision-making 25 , 26 . In anesthesia, AI has supported tasks such as predicting hypotension from arterial waveforms 27 , estimating anesthesia depth from EEG 28 , predicting neuromuscular blockade from EMG 29 , identifying difficult airways from facial image 30 , assisting ultrasound-guided nerve blocks 31 , and predicting transfusion-related acute lung injury 32 . However, existing AI-based anesthesia assessment tools remain largely hospital-bound, with limited accessibility and functionality, lacking integrated features such as voice interaction and comprehensive decision support. To address these limitations, we developed firstly AI-assisted anesthesia evaluation system for Asian, capable of electronic assessment with external network compatibility, interactive evaluation, and clinical decision support. We subsequently initiated a single-center, randomized, parallel-group, open-label non-inferiority clinical trial to compare AI-assisted anesthesia assessment with traditional methods in terms of clinical outcomes. Methods AI-assisted anesthesia evaluation system The AI-assisted anesthesia evaluation system was designed as a multi-layer, cross-platform architecture, integrating advanced web frameworks, high-performance databases, and intelligent external interfaces to deliver real-time, clinically relevant recommendations (Fig. 1 ). Development was conducted in Visual Studio Code (Microsoft Corporation, Redmond, WA, USA), with a focus on scalability, interoperability, and seamless user experience across Android, iOS, Windows, and WeChat mini-programs. Backend Architecture The backend was implemented in Python. Two complementary frameworks - Django for full-featured, high-level web development and Flask for lightweight, microservice-oriented tasks - were combined to optimize both stability and flexibility. Data storage was designed for high concurrency and low-latency performance. PostgreSQL, a robust object-relational database, handles structured clinical and operational data, while Redis, an in-memory key–value store, supports millisecond-level access to frequently queried items such as patient questionnaires and scoring scales. For unstructured data (e.g., medical images, uploaded documents), Alibaba Cloud OSS provides distributed, persistent object storage with global low-latency access. Network communication is managed through Nginx as a reverse proxy for traffic routing and Gunicorn as a high-performance HTTP server, ensuring efficient request handling under peak loads. Frontend and Multi-Platform Deployment The frontend was built with HTML, JavaScript, and CSS, enhanced by Vue and Uni-app frameworks. Using HBuilder, the codebase was compiled into both Android applications and WeChat mini-programs from a single source, reducing maintenance costs and ensuring consistent user experience across platforms. Deployment employed Docker containerization for modular scalability, combined with Alibaba Cloud SLB load balancing for optimal availability under high query-per-second (QPS) conditions. Jenkins automated the DevOps pipeline, achieving continuous integration, delivery, and deployment. Comprehensive testing - including unit, integration, system, and performance evaluations - ensured stability and clinical reliability after each update. Intelligent External Interfaces Three external modules extend the system’s clinical utility. Baidu Cloud Language Service- Enables real-time speech-to-text and text-to-speech, enhancing accessibility for elderly patients. Barcode-Based Drug Identification-Integrates with a third-party pharmaceutical database for rapid medication entry via barcode scan or partial name input. Hospital Information System Integration-Provides reserved interfaces for HIS/LIS connectivity, allowing automated retrieval and synchronization of diagnostic results. System Workflow Following integration and testing, the system was packaged for multi-platform release, offering clinicians and patients an intuitive, interactive, and intelligent preoperative anesthesia evaluation tool-minimizing manual input while maximizing automation, precision, and accessibility in perioperative care. Study Design This was a single-center, randomized, controlled, parallel-group, open-label, non-inferiority trial conducted at Huashan Hospital. The study was approved by the Biomedical Ethics Committee of Huashan Hospital, and all participants provided written informed consent. The clinical registration number of the study was ChiCTR2400086869. Participants Written informed consent was obtained from all participants prior to their enrollment in this randomized controlled non-inferiority study. The study protocol was reviewed and approved by the Clinical Research Ethics Committee of Huashan Hospital, Fudan University (approval number: KY2022-917). Hospitalized patients scheduled for elective non-cardiac, non-endovascular, and non-day surgeries under general anesthesia between February 1 and March 31, 2023, were screened for eligibility. Inclusion criteria were: (1) age between 18 and 65 years; (2) undergoing elective surgery; (3) planned general anesthesia; and (4) ability to understand and sign informed consent. Exclusion criteria included: (1) patients with newly diagnosed severe conditions requiring multidisciplinary consultation prior to evaluation; (2) inability to complete anesthesia assessment after communication; or (3) concurrent participation in another clinical trial. Randomization and Group Allocation Eligible patients were identified upon anesthesia appointment notification. Contact information was retrieved from the hospital information system, and consent was obtained prior to enrollment. Using SPSS 22.0 (IBM Corp., Armonk, NY, USA), a randomization list was generated containing numbers 1 to 600, which were shuffled using a randomization algorithm. Participants were assigned in a 1:1 ratio to either the control group or the intervention group based on their randomized sequence. If a patient withdrew, the number plus 600 was used as the recruitment index, with group assignment unchanged. Intervention Control group (traditional evaluation) A trained anesthesiology resident performed standard face-to-face preoperative evaluation at the bedside. The completed evaluation was documented and provided to the attending anesthesiologist on the day of surgery. Intervention group (AI-assisted evaluation) A link to the AI-based anesthesia evaluation system (via WeChat Mini Program) was sent to patients or their caregivers. Patients were instructed to complete the self-guided assessment. The anesthesiology resident reviewed the AI-generated report prior to bedside confirmation. If the patient could not complete the evaluation independently, the resident assisted using the system interface. The finalized report was automatically forwarded to the attending anesthesiologist. On the day of surgery, all patients were re-evaluated by an experienced attending anesthesiologist, who also assessed the quality of the initial anesthesia evaluation report using a standardized scoring form. Additionally, patients completed a questionnaire assessing satisfaction with the anesthesia evaluation process. Anesthesia Evaluation Patient satisfaction with the evaluation process was assessed using a questionnaire that included items on patients’ understanding of anesthesia procedures and any remaining concerns or anxiety (Supplementary Tables 1 and 2). Anesthesia evaluations were conducted by anesthesiology residents who had completed standardized residency training. On the day of surgery, anesthesia was administered by senior anesthesiologists holding intermediate or advanced professional titles. The grading criteria for the completeness and accuracy of the anesthesia assessment were as follows. Grade A was defined as a fully complete anesthesia assessment with no identified errors, such as a report containing entirely accurate and comprehensive information. Grade B referred to results with one to five distinct issues, for example, a report missing two items and containing one incorrect entry. Grade C applied to results with six or more issues, such as a report missing seven items, containing two incorrect entries, and including three illegible items. Outcomes The primary outcome of this study was the accuracy of ASA (American Society of Anesthesiologists) physical status classification. Accuracy was defined as the level of agreement between the initial classification - whether AI-assisted or traditional - and the final classification determined by the attending anesthesiologist. Secondary outcomes included the accuracy and completeness of medical history collection, which was evaluated by the attending anesthesiologist using a predefined grading scale. Additionally, the time required to complete the anesthesia evaluation was recorded, measured from the beginning to the end of the assessment process, excluding the time spent on obtaining informed consent. Quality Control All evaluators underwent standardized training prior to study initiation to ensure consistency. To reduce data loss, up-to-date contact information was maintained for all participants. Data were double-checked and entered independently by two researchers not involved in the study. Sample Size Calculating For sample size calculation, pilot data indicated an accuracy of 91% in the control group and 93% in the intervention group. Using a non-inferiority margin (Δ) of 5%, a one-sided alpha of 0.025, and 80% power, the minimum required sample size was calculated with PASS 11 software. This resulted in a target of 472 patients (236 per group). Allowing for a 10% dropout rate, the final sample size was set at 600 patients, with 300 in each group (Supplementary Table 1). Statistical Analysis All analyses were performed using SPSS 22.0 and and R software 4.5.1. Descriptive statistics included frequencies and percentages for categorical variables, and mean ± standard deviation or median (interquartile range) for continuous variables. Between-group comparisons were conducted using the chi-square test or Fisher’s exact test for categorical variables, and t-tests or Wilcoxon rank-sum tests for continuous variables, depending on distribution. For ordinal outcomes, Kruskal–Wallis tests were used. A two-sided P-value < 0.05 was considered statistically significant. Results Flowchart of the study A total of 692 patients were initially screened for eligibility. After applying exclusion criteria, 92 patients were excluded: 33 requested anesthesia consultations, 26 surgeries were cancelled, 16 were concurrently enrolled in other clinical trials, and 17 were unable to cooperate with the anesthesia assessment. Ultimately, 600 patients were enrolled and included in the final analysis, with 300 in the traditional evaluation group and 300 in the AI-assisted evaluation group (Fig. 2 ). Baseline demographics and clinical characteristics Clinical features of participants were presented in Table 1 . Among all participants, 318 (53.0%) were male and 282 (47.0%) were female. ASA physical status classifications were as follows: 355 (59.2%) ASA I, 221 (36.8%) ASA II, and 24 (4.0%) ASA III. Patients were scheduled for surgeries across various departments, including neurosurgery (10.2%), general surgery (19.0%), thoracic surgery (12.0%), ENT/head and neck surgery (6.5%), urology (9.3%), pancreatic surgery (1.7%), hand surgery (21.3%), orthopedics (13.8%), and sports medicine (6.2%). Baseline demographics, ASA classifications, and surgical types were comparable between the two groups ( P > 0.05). Table 1 Baseline characteristics of the per protocol population Category Traditional Evaluation Group ( n = 300) AI-assisted Evaluation Group ( n = 300) P value Sex, n (%) 0.567 Male 163 (54.3%) 155 (51.7%) Female 137 (45.7%) 145 (48.3%) Age (years), Median (IQR) 48.0 (35.0, 58.0) 46.0 (29.0, 54.0) 0.698 ASA Classification by Senior Anesthesiologists , n (%) 0.624 Grade I 173 (57.7%) 182 (60.7%) Grade II 116 (38.7%) 105 (35.0%) Grade III 11 (3.7%) 13 (4.3%) Planned Surgical Department , n (%) 0.733 Neurosurgery 35 (11.7%) 26 (8.7%) General Surgery 57 (19.0%) 57 (19.0%) Cardiothoracic Surgery 41 (13.7%) 31 (10.3%) Otorhinolaryngology- Head and Neck Surgery 17 (5.7%) 22 (7.3%) Urology 27 (9.0%) 29 (9.7%) Pancreatic Surgery 5 (1.7%) 5 (1.7%) Hand Surgery 63 (21.0%) 64 (21.3%) Orthopedics 40 (13.3%) 43 (14.3%) Sports Medicine 15 (5.0%) 23 (7.7%) Primary outcome The accuracy of ASA classification was 91.7% (275/300) in the traditional group and 93.3% (280/300) in the AI-assisted group ( P = 0.033, Table 2 ). The difference in accuracy was 1.6% (95% CI: -2.6–5.9%), with the lower bound above the predefined non-inferiority margin of -5%. This confirmed the non-inferiority of the AI-assisted evaluation compared to traditional methods (Fig. 3 ). Table 2 ASA classification accuracy rate for each group Group Total ( n ) Correct n (%) Incorrect n (%) Rate Difference (%) Non-Inferiority Test Z value P value Traditional Assessment 300 275(91.7) 25(8.3) 1.6% (-2.6%-5.9%) 1.848 0.033 AI-Based Assessment 300 280(93.3) 20(6.7) Secondary outcomes Evaluation quality, measured by completeness and accuracy of the anesthesia reports, was significantly higher in the AI-assisted group. In the traditional group, 195 (65.0%) of 300 reports contained a total of 971 issues (3.2% error rate), including incomplete information (43.3%), ambiguous entries (20.7%), incorrect entries (18.0%), and missing items (21.7%). In contrast, only 99 (33.0%) of AI-assisted reports contained 337 issues (1.1% error rate), with lower frequencies of all error types (Table 3 ). Table 3 Error rate of the assessment report for each group Category Total Occurrences,( n ) Reports with Issues, n (%) Error Rate Traditional Assessment Group Incomplete information 715 130 (43.3%) 2.40% Ambiguous entries 87 62 (20.7%) 0.30% Incorrect entries 82 54 (18.0%) 0.30% Missing items 87 65 (21.7%) 0.30% Total 971 195 (65.0%) 3.20% AI-based Assessment Group Incomplete information 239 82 (27.3%) 0.80% Ambiguous entries 41 25 (8.3%) 0.10% Incorrect entries 35 21 (7.0%) 0.20% Missing items 22 13 (4.3%) 0.10% Total 337 99 (33.0%) 1.10% Based on the grading criteria for the completeness and accuracy of the anesthesia assessment, 67.0% of AI-assisted reports were rated Grade A, compared to 35.0% in the traditional group. The distribution of report quality ratings differed significantly between groups (X²(2, N = 300) = 63.595, P < 0.001), favoring the AI-assisted method (Fig. 4 A). The anesthesia evaluation time was significantly shorter in the AI-assisted group, with a median (IQR) of 3.0 (2.0–5.0) minutes, compared to the traditional group, which had a median (IQR) of 7.0 (6.0–8.0) minutes (Z = 17.25, P < 0.01) (Fig. 4 B). There were no statistically significant differences between groups regarding patients’ understanding of anesthesia procedures, anesthesia-related risks, resolution of concerns, or reduction of anxiety (Table 4 ). Overall satisfaction with the evaluation process was higher in the AI-assisted group, with 262 patients (87.3%) indicating they "strongly agreed" or "agreed" that they were satisfied, compared to 228 (76.0%) in the traditional group ( P < 0.01) (Fig. 4 C). Table 4 Anesthesia assessment effect Question Strongly Agree Agree Neutral Disagree Strongly Disagree Traditional Assessment Group I clearly understand the anesthesia procedure 71 157 35 21 16 I clearly understand the anesthesia risks 56 158 33 23 30 My questions about anesthesia were addressed during assessment 59 173 31 19 18 I no longer have any fear or anxiety about anesthesia 45 143 36 25 51 I am very satisfied with the anesthesia assessment process 70 158 28 21 23 AI-Assisted Assessment Group I clearly understand the anesthesia procedure 108 92 35 45 20 I clearly understand the anesthesia risks 68 89 53 55 35 My questions about anesthesia were addressed during assessment 104 66 100 20 10 I no longer have any fear or anxiety about anesthesia 67 225 63 37 16 I am very satisfied with the anesthesia assessment process 43 9 Discussion In this study, we designed a novel form of preoperative anesthesia evaluation, wherein anesthesiologists conducted assessments with the assistance of a newly developed AI-based anesthesia evaluation system. This approach was intended to maintain diagnostic accuracy while improving assessment efficiency and reducing the time burden on anesthesiologists. Our findings demonstrated that the AI-assisted group achieved non-inferior performance in ASA classification accuracy compared to the traditional evaluation group, suggesting comparable capacity to identify the severity of patients’ comorbidities. In addition, evaluation reports generated in the AI-assisted group were of higher quality, offering more comprehensive information to support individualized anesthetic planning. Importantly, anesthesiologists in the AI group saved an average of 4 minutes per patient during the evaluation process, and patient satisfaction was significantly higher in this group. Collectively, these results indicate that AI-assisted anesthesia evaluation may serve as a clinically applicable, efficient, and high-quality alternative to traditional face-to-face assessments. Previous studies evaluating new anesthesia assessment formats have primarily focused on remote video or telephone-based consultations, with outcomes such as reduced travel time, economic cost, patient satisfaction, or surgical cancellation rate 33 . In contrast, our AI-based system was implemented in-hospital, with anesthesiologists reviewing and confirming each evaluation. Given the confounding factors during the COVID-19 pandemic, surgical cancellation was not chosen as a primary endpoint. Instead, ASA classification was selected based on two main considerations. First, despite its limitations as a sole predictor of surgical risk, the ASA physical status system - established over six decades ago - remains a widely accepted tool for quantifying patients’ physiological reserve and tolerance to anesthesia and surgery. Second, ASA classification is familiar to anesthesiologists, making it a reliable and credible primary outcome measure in this setting 34 . As our assessors were well-trained in applying ASA grading, a non-inferiority design was adopted and confirmed by the results. Beyond ASA classification, the completeness and quality of the evaluation report are central to the anesthetic assessment. Prior studies have shown that electronic evaluations can capture more detailed information while saving time, whereas paper records may be prone to loss, damage, or illegibility - particularly when the assessment and operative anesthesiologists are not the same 35 . Our AI-based system was designed with a structured decision-tree algorithm based on standardized anesthetic assessment guidelines. It dynamically generates individualized questionnaires through follow-up prompts, based on patient-specific responses. As evidenced by our results, the AI-generated reports demonstrated significantly higher quality ratings than those from conventional face-to-face evaluations. Regarding time efficiency, consistent with findings from previous studies on electronic preoperative screening, the AI-based assessment reduced overall evaluation time 36 . This improvement can be attributed to two main factors: (1) the AI system guides patients through the assessment independently, minimizing the need for item-by-item inquiries from the anesthesiologist; (2) patients can directly record their current medications via voice input or barcode scanning from a built-in pharmaceutical database. However, the average time saved was modest (4 minutes), partially because many patients were unfamiliar with smartphone operations and required additional assistance from medical staff. In terms of effectiveness, the AI-based system performed comparably to traditional evaluations in communicating anesthesia procedures, disclosing anesthesia-related risks, addressing patient concerns, and alleviating preoperative anxiety. Patient satisfaction scores were higher in the AI group, further supporting its potential as a high-quality and valuable tool for clinical anesthesia evaluation. There were several limitations in our study. This study included patients aged 18–65 years and did not cover high-risk elderly populations (> 65 years), as these patients are typically assessed by dedicated teams in our institution, making randomization between groups impractical. Additionally, the time spent by anesthesiologists obtaining informed consent was not recorded, as many patients lacked available family members or legal proxies during the assessment process. Moreover, since the AI system had not yet integrated with the hospital’s laboratory reporting interface, anesthesiologists needed to manually retrieve test results from the hospital information system (HIS), increasing preparation time, which was not counted as part of the evaluation duration. Conclusions Our study was the first to present a novel AI-assisted anesthesia evaluation system for Asian and conducted a randomized controlled trial to validate its clinical value. The results showed that the clinical performance of AI-assisted anesthesia evaluation was non-inferior to that of the traditional assessment. Moreover, the AI-assisted system demonstrated additional advantages, including higher assessment quality, reduced evaluation time, and greater patient satisfaction. These findings suggest that AI-assisted anesthesia evaluation may represent a superior alternative for clinical anesthesia assessment. Abbreviations ACT Anesthesia Control Tower AI Artificial Intelligence ASA American Society of Anesthesiologists CDSS Clinical Decision Support System COVID-19 Coronavirus Disease 2019 EHR Electronic Health Record ERAS Enhanced Recovery After Surgery GSMA Groupe Speciale Mobile Association IOT Internet of things IT Information Technology MDIDSs Medical Device Interface Data Sheets mHealth Mobile Health PACU Post-Anesthesia Care Unit PCMH Patient-Centered Medical Home PHR Personal health record QPS Queries Per Second StaRI Standards for Reporting Implementation Studies SUS System Usability Scale Declarations Funding ： This work was supported by the Foundation of Shanghai Municipal Science and Technology Medical Innovation Research Project (23Y21900600 to Yingwei Wang), the Foundation of Shanghai Municipal Key Clinical Specialty (shslczdzk06901 to Yingwei Wang), the Foundation of Shanghai Municipal Science and Technology Commission (22ZR1409600 to Daojie Xu). Authors’ contributions: Jiangtao Qi: Formal analysis, Validation, Writing- original draft. Jingjing Shen : Methodology, Validation, Writing- review & editing. Yiqi Wu : Methodology, Resources. Shuchi Zhang : Methodology. Daojie Xu : Funding acquisition, Investigation, Writing- review & editing. Yingwei Wang : Project administration, Resources. Ethics approval and consent to participate: This study was conducted in accordance with the ethical principles of the Declaration of Helsinki. This study was approved by the Clinical Research Ethics Committee of Huashan Hospital (KY2022-917). Data and materials availability: Data and materials generated that are relevant to the results are included in this article. Other data are available from the corresponding author upon reasonable request. Declaration of Interest statement All authors have declared no conflicts of interest. Presentation (for original articles only) : None. Study design: Randomized Controlled Trial Registry: chictr.org.cn. Clinical trial number: ChiCTR2400086869. Registration date: 12 July 2024. Retrospectively registered Consent to Publish declaration: Not Applicable. Consent to Participate declaration: Written informed consent was obtained from all participants prior to their enrollment in this randomized controlled non-inferiority study. The study protocol was reviewed and approved by the Clinical Research Ethics Committee of Huashan Hospital, Fudan University (approval number: KY2022-917). CONSORT 2025 Statement: This study was conducted and reported in accordance with the Consolidated Standards of Reporting Trials (CONSORT) guidelines. References Bates DW, Levine DM, Salmasian H, et al. The Safety of Inpatient Health Care. N Engl J Med. 2023;388(2):142–53. Wang Y, Eldridge N, Metersky ML, et al. National trends in patient safety for four common conditions, 2005–2011. N Engl J Med. 2014;370(4):341–51. Wacker J, Staender S. The role of the anesthesiologist in perioperative patient safety. Curr Opin Anaesthesiol. 2014;27(6):649–56. Al Talalwah N, McIltrot KH. Cancellation of Surgeries: Integrative Review. J Perianesth Nurs. 2019;34(1):86–96. Fischer SP. Development and effectiveness of an anesthesia preoperative evaluation clinic in a teaching hospital. Anesthesiology. 1996;85(1):196–206. Zambouri A. Preoperative evaluation and preparation for anesthesia and surgery. Hippokratia. 2007;11(1):13–21. Gebremedhn EG, Nagaratnam V. Assessment of patient satisfaction with the preoperative anesthetic evaluation. Patient Relat Outcome Meas. 2014;5:105–10. Seim AR, Fagerhaug T, Ryen SM, et al. Causes of cancellations on the day of surgery at two major university hospitals. Surg Innov. 2009;16(2):173–80. Peden CJ, Campbell M, Aggarwal G. Quality, safety, and outcomes in anaesthesia: what's to be done? An international perspective. Br J Anaesth. 2017;119(suppl1):i5–14. Monk TG, Weldon BC, Garvan CW, et al. Predictors of cognitive dysfunction after major noncardiac surgery. Anesthesiology. 2008;108(1):18–30. Rivera R, Antognini JF. Perioperative drug therapy in elderly patients. Anesthesiology. 2009;110(5):1176–81. Turrentine FE, Wang H, Simpson VB, Jones RS. Surgical risk factors, morbidity, and mortality in elderly patients. J Am Coll Surg. 2006;203(6):865–77. Cullen KA, Hall MJ, Golosinskiy A. Ambulatory surgery in the United States, 2006. Natl Health Stat Rep 2009(11):1–25. Smith I, Cooke T, Jackson I, Fitzpatrick R. Rising to the challenges of achieving day surgery targets. Anaesthesia. 2006;61(12):1191–9. Tregoning JS, Flight KE, Higham SL, Wang Z, Pierce BF. Progress of the COVID-19 vaccine effort: viruses, vaccines and variants versus efficacy, effectiveness and escape. Nat Rev Immunol. 2021;21(10):626–36. Amaya F, Shimamoto S, Matsuda M, Kageyama K, Sawa T. Preoperative anesthesia clinic in Japan: a nationwide survey of the current practice of preoperative anesthesia assessment. J Anesth. 2015;29(2):175–9. Applegate RL 2nd, Gildea B, Patchin R, et al. Telemedicine pre-anesthesia evaluation: a randomized pilot trial. Telemed J E Health. 2013;19(3):211–6. Wong DT, Kamming D, Salenieks ME, Go K, Kohm C, Chung F. Preadmission anesthesia consultation using telemedicine technology: a pilot study. Anesthesiology. 2004;100(6):1605–7. Mullen-Fortino M, Rising KL, Duckworth J, Gwynn V, Sites FD, Hollander JE. Presurgical Assessment Using Telemedicine Technology: Impact on Efficiency, Effectiveness, and Patient Experience of Care. Telemed J E Health. 2019;25(2):137–42. Wienhold J, Mösch L, Rossaint R, et al. Teleconsultation for preoperative evaluation during the coronavirus disease 2019 pandemic: A technical and medical feasibility study. Eur J Anaesthesiol. 2021;38(12):1284–92. Goodhart IM, Andrzejowski JC, Jones GL, et al. Patient-completed, preoperative web-based anaesthetic assessment questionnaire (electronic Personal Assessment Questionnaire PreOperative): Development and validation. Eur J Anaesthesiol. 2017;34(4):221–8. Ladfors MB, Löfgren ME, Gabriel B, Olsson JH. Patient accept questionnaires integrated in clinical routine: a study by the Swedish National Register for Gynecological Surgery. Acta Obstet Gynecol Scand. 2002;81(5):437–42. Xu M, Liu H, Dai A, et al. Dynamic and interpretable deep learning model for predicting respiratory failure following cardiac surgery. BMC Anesthesiol. 2025;25(1):394. Jiang F, Jiang Y, Zhi H, et al. Artificial intelligence in healthcare: past, present and future. Stroke Vasc Neurol. 2017;2(4):230–43. Yin J, Ngiam KY, Teo HH. Role of Artificial Intelligence Applications in Real-Life Clinical Practice: Systematic Review. J Med Internet Res. 2021;23(4):e25759. Wijnberge M, Geerts BF, Hol L, et al. Effect of a Machine Learning-Derived Early Warning System for Intraoperative Hypotension vs Standard Care on Depth and Duration of Intraoperative Hypotension During Elective Noncardiac Surgery: The HYPE Randomized Clinical Trial. JAMA. 2020;323(11):1052–60. Hatib F, Jian Z, Buddi S, et al. Machine-learning Algorithm to Predict Hypotension Based on High-fidelity Arterial Pressure Waveform Analysis. Anesthesiology. 2018;129(4):663–74. Haghighi SJ, Komeili M, Hatzinakos D, Beheiry HE. 40-Hz ASSR for Measuring Depth of Anaesthesia During Induction Phase. IEEE J Biomed Health Inf. 2018;22(6):1871–82. Santanen OA, Svartling N, Haasio J, Paloheimo MP. Neural nets and prediction of the recovery rate from neuromuscular block. Eur J Anaesthesiol. 2003;20(2):87–92. Cuendet GL, Schoettker P, Yüce A, et al. Facial Image Analysis for Fully Automatic Prediction of Difficult Endotracheal Intubation. IEEE Trans Biomed Eng. 2016;63(2):328–39. Yang XY, Wang LT, Li GD, et al. Artificial intelligence using deep neural network learning for automatic location of the interscalene brachial plexus in ultrasound images. Eur J Anaesthesiol. 2022;39(9):758–65. Christie SA, Conroy AS, Callcut RA, Hubbard AE, Cohen MJ. Dynamic multi-outcome prediction after injury: Applying adaptive machine learning for precision medicine in trauma. PLoS ONE. 2019;14(4):e0213836. van Hoorn BT, Tromp DJ, van Rees RCM, et al. Effectiveness of a digital vs face-to-face preoperative assessment: A randomized, noninferiority clinical trial. J Clin Anesth. 2023;90:111192. Dripps RD, Lamont A, Eckenhoff JE. The role of anesthesia in surgical mortality. JAMA. 1961;178:261–6. Strassberger-Nerschbach N, Magyaros F, Maria W, et al. Quality comparison of remote anesthetic consultation versus on-site consultation in children with sedation for a magnetic resonance imaging examination-A randomized controlled trial. Paediatr Anaesth. 2023;33(8):647–56. Howell M, Hood AJ, Jayne DG. Use of a patient completed iPad questionnaire to improve pre-operative assessment. J Clin Monit Comput. 2017;31(1):221–5. Additional Declarations No competing interests reported. Supplementary Files CONSORT2025editablechecklist.docx SupplementaryTable1.Anesthesiaassessmenteffectquestionnaire.docx SupplementaryTable2.Anesthesiaassessmentqualityauditquestionnaire.docx Cite Share Download PDF Status: Under Review Version 1 posted Reviewers agreed at journal 13 May, 2026 Reviews received at journal 09 May, 2026 Reviewers agreed at journal 09 May, 2026 Editor invited by journal 24 Apr, 2026 Reviewers invited by journal 10 Sep, 2025 Editor assigned by journal 02 Sep, 2025 Submission checks completed at journal 30 Aug, 2025 First submitted to journal 30 Aug, 2025 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-7364932","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":514369428,"identity":"90679027-61c6-4191-aa6f-8857e8562f13","order_by":0,"name":"Jiangtao Qi","email":"","orcid":"","institution":"Huashan Hospital","correspondingAuthor":false,"prefix":"","firstName":"Jiangtao","middleName":"","lastName":"Qi","suffix":""},{"id":514369429,"identity":"c5b835d5-6413-4a89-a591-a3157a04e98f","order_by":1,"name":"Jingjing Shen","email":"","orcid":"","institution":"Huashan Hospital","correspondingAuthor":false,"prefix":"","firstName":"Jingjing","middleName":"","lastName":"Shen","suffix":""},{"id":514369430,"identity":"21ce4cba-e8b9-420f-90be-5e8532d70181","order_by":2,"name":"Yiqi Wu","email":"","orcid":"","institution":"Huashan Hospital","correspondingAuthor":false,"prefix":"","firstName":"Yiqi","middleName":"","lastName":"Wu","suffix":""},{"id":514369431,"identity":"02a715bb-97ee-4fdd-8426-8680db8efb43","order_by":3,"name":"Shuchi Zhang","email":"","orcid":"","institution":"Tongji Hospital","correspondingAuthor":false,"prefix":"","firstName":"Shuchi","middleName":"","lastName":"Zhang","suffix":""},{"id":514369432,"identity":"305e5350-a8ac-4b2c-8248-4be3fe797fa2","order_by":4,"name":"Daojie Xu","email":"","orcid":"","institution":"Huashan Hospital","correspondingAuthor":false,"prefix":"","firstName":"Daojie","middleName":"","lastName":"Xu","suffix":""},{"id":514369433,"identity":"e313d876-56ff-49df-a38b-e21678f4ebf8","order_by":5,"name":"Yingwei Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3ElEQVRIiWNgGAWjYBACgwNgyoafgSEBxGAmWkuaZAOpWg6TouX42cOvedvOSxgcT372gKHCOrGB/ewBvFrMzuSlWfO23ZYwOPPM3IDhTHpiA09eAn4tB3LMjHm33a4zuJFgJsHYdjixQYLHAL+W829AWs5JGNxI/ybB+I8ILfY3cowf8247ANSSA7SlgQgtljfemDHO/ZcsIXnmTZlEwrF04zaeHPxaDM7nGH94c8ZOgu94+jaJDzXWsv3sZ/BrAQI2KR4YMwHEJaQeCJg//iBC1SgYBaNgFIxgAACYDEq1viCEVQAAAABJRU5ErkJggg==","orcid":"","institution":"Huashan Hospital","correspondingAuthor":true,"prefix":"","firstName":"Yingwei","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2025-08-13 12:23:34","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7364932/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7364932/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":91830619,"identity":"2487929b-380b-4fb3-9b65-11cbf8b373ba","added_by":"auto","created_at":"2025-09-22 09:05:24","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":552492,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.docx","url":"https://assets-eu.researchsquare.com/files/rs-7364932/v1/e91f0cd4d078b1459d80821e.docx"},{"id":91831957,"identity":"e4f2d1d1-1ce2-48fc-a825-79db99487ad8","added_by":"auto","created_at":"2025-09-22 09:13:24","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7792,"visible":true,"origin":"","legend":"","description":"","filename":"92dafec62f4b4322b9768346c5148f4e.json","url":"https://assets-eu.researchsquare.com/files/rs-7364932/v1/88f8f00c2f84d5da5ae836a2.json"},{"id":91829867,"identity":"31b3f590-7f69-4c5b-9467-0dbbc4e574f2","added_by":"auto","created_at":"2025-09-22 08:57:24","extension":"docx","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":31206,"visible":true,"origin":"","legend":"","description":"","filename":"CONSORT2025editablechecklist.docx","url":"https://assets-eu.researchsquare.com/files/rs-7364932/v1/344535ea69ab9bd44cb3a10f.docx"},{"id":91830624,"identity":"9f5b62ad-bb91-4818-8e64-e939fff25aba","added_by":"auto","created_at":"2025-09-22 09:05:25","extension":"docx","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":12173,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryTable1.Anesthesiaassessmenteffectquestionnaire.docx","url":"https://assets-eu.researchsquare.com/files/rs-7364932/v1/9fd2202c43037914951442e4.docx"},{"id":91830621,"identity":"f2ea8306-6b6d-4580-a9b8-33fd78d7de3e","added_by":"auto","created_at":"2025-09-22 09:05:24","extension":"docx","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":14959,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryTable2.Anesthesiaassessmentqualityauditquestionnaire.docx","url":"https://assets-eu.researchsquare.com/files/rs-7364932/v1/e0bb382e8d366c6b01f7c9df.docx"},{"id":91829872,"identity":"048006fa-13b7-4712-8bc3-7791c9766a0e","added_by":"auto","created_at":"2025-09-22 08:57:24","extension":"xml","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":116552,"visible":true,"origin":"","legend":"","description":"","filename":"92dafec62f4b4322b9768346c5148f4e1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7364932/v1/c9d2e75fd2ce7ec7e73a7109.xml"},{"id":91829869,"identity":"fa239ecf-0cde-4b1e-958b-f5da4b2bce8d","added_by":"auto","created_at":"2025-09-22 08:57:24","extension":"jpeg","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":147223,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7364932/v1/e0f2f0eefa107ea1087d7de9.jpeg"},{"id":91829868,"identity":"32a0dafa-85c0-4c44-b4a1-443ed8ff545c","added_by":"auto","created_at":"2025-09-22 08:57:24","extension":"jpeg","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":109841,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7364932/v1/0089ab94a866d6b3f0870dfc.jpeg"},{"id":91829874,"identity":"ce8af85d-f3df-4cfd-8f73-32a9649edc4a","added_by":"auto","created_at":"2025-09-22 08:57:25","extension":"jpeg","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1696470,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7364932/v1/a8ab7e9e377e2b7e425f0766.jpeg"},{"id":91829873,"identity":"6994648e-7bfe-46d8-83ed-a678ec041d4b","added_by":"auto","created_at":"2025-09-22 08:57:25","extension":"jpeg","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2393430,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7364932/v1/714f533353cb36d2fd4f599d.jpeg"},{"id":91830623,"identity":"92f8d81f-e08a-4399-8238-038ddf60bf8f","added_by":"auto","created_at":"2025-09-22 09:05:24","extension":"xml","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":111231,"visible":true,"origin":"","legend":"","description":"","filename":"92dafec62f4b4322b9768346c5148f4e1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7364932/v1/3d4e64c477b10ffe84141500.xml"},{"id":91829870,"identity":"01ec3a3d-1f41-4b39-96d3-3963e1fdddb2","added_by":"auto","created_at":"2025-09-22 08:57:24","extension":"html","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":124461,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7364932/v1/1b0353a1d3bd52fbdeeba395.html"},{"id":91831958,"identity":"6b2a69e1-4b15-4662-8aef-46dd9ae2c854","added_by":"auto","created_at":"2025-09-22 09:13:25","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":80171,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eDesign diagram of the AI-assisted anesthesia evaluation system\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7364932/v1/a7484d93c78288b0c4c67839.png"},{"id":91830617,"identity":"eda1652b-db7c-4061-b2b7-97fd596bd1da","added_by":"auto","created_at":"2025-09-22 09:05:24","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":14207,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eFlow diagram\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7364932/v1/bd9d40781d99355d1a745cf0.png"},{"id":91829856,"identity":"76405109-de7b-4b91-a240-c210ac01a034","added_by":"auto","created_at":"2025-09-22 08:57:24","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":42812,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eTest for noninferiority\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7364932/v1/f3c2402a4cac740a62122790.png"},{"id":91829864,"identity":"1d9a4dd2-96e7-4a06-b4e2-fb9eaf1bf15e","added_by":"auto","created_at":"2025-09-22 08:57:24","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":78559,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eAssessment quality, evaluation time and patient satisfaction for each group\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e(A) \u003c/strong\u003eProportion of anesthesia assessment quality for each group.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e(B) \u003c/strong\u003eEvaluation time between each group.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e(C) \u003c/strong\u003eProportion of patient satisfaction for each group.\u003c/p\u003e","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7364932/v1/37dcf77e581717aec170d828.png"},{"id":91832541,"identity":"4680784b-0312-49a8-9470-6597b5edee0b","added_by":"auto","created_at":"2025-09-22 09:21:25","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1878631,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7364932/v1/c4eb544c-6bae-471a-9ec8-56337f04dd99.pdf"},{"id":91829861,"identity":"bb91cacd-06d2-47ee-8af6-2c9b0c032598","added_by":"auto","created_at":"2025-09-22 08:57:24","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":31206,"visible":true,"origin":"","legend":"","description":"","filename":"CONSORT2025editablechecklist.docx","url":"https://assets-eu.researchsquare.com/files/rs-7364932/v1/65d2f46b1fcdd9b177e092a9.docx"},{"id":91831956,"identity":"4270d255-3166-46aa-a1ae-9d93a5841cd1","added_by":"auto","created_at":"2025-09-22 09:13:24","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":12173,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryTable1.Anesthesiaassessmenteffectquestionnaire.docx","url":"https://assets-eu.researchsquare.com/files/rs-7364932/v1/90902ee3183dda02bd995b0a.docx"},{"id":91829865,"identity":"58f3902f-7c6c-496b-8a51-5cb6ea54c1f5","added_by":"auto","created_at":"2025-09-22 08:57:24","extension":"docx","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":14959,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryTable2.Anesthesiaassessmentqualityauditquestionnaire.docx","url":"https://assets-eu.researchsquare.com/files/rs-7364932/v1/c7dc1094141b3b3576844699.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Efficacy and Efficiency of Artificial Intelligence-based Preoperative Anesthesia Evaluation: A Randomized Controlled Non-Inferiority Study","fulltext":[{"header":"Introduction","content":"\u003cp\u003ePatient safety remains a central concern in modern healthcare. A recent study in The New England Journal of Medicine reported that 23% of hospitalized patients experienced at least one adverse event, with surgical and medication-related incidents being the most frequent; notably, 22% of these were preventable\u003csup\u003e\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e\u003c/sup\u003e. Surgery offers both the promise of cure and the risk of harm\u003cem\u003e-\u003c/em\u003e it is a double-edged sword capable of resolving disease yet potentially inducing complications. Perioperative adverse event rates can reach as high as 36.8%\u003csup\u003e2\u003c/sup\u003e. Anesthesiologists play a pivotal role in perioperative safety, being responsible for risk assessment, airway management, vital signs monitoring, and pain control\u003csup\u003e\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e\u003c/sup\u003e. Among these duties, preoperative anesthesia evaluation is essential for ensuring patient safety, reducing postoperative complications, shortening hospitalization, improving clinical outcomes, and lowering healthcare costs\u003csup\u003e\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e,\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e\u003cp\u003eAnesthesia evaluation involves reviewing a patient\u0026rsquo;s medical history, physical examination, and diagnostic results to assess their overall condition, followed by tailoring an anesthesia plan to the patient\u0026rsquo;s health status and surgical requirements. The ultimate goal is to reduce perioperative morbidity and mortality while facilitating rapid recovery\u003csup\u003e\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e\u003c/sup\u003e. For anesthesiologists, this process enables optimal selection of anesthetic techniques and drugs, while from the patient\u0026rsquo;s perspective, it provides opportunities for risk discussion, reassurance, and anxiety reduction. Comprehensive evaluation improves efficiency and satisfaction while lowering complication rates\u003csup\u003e\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e\u003c/sup\u003e, whereas inadequate assessment may cause surgical delays, waste resources, and threaten patient safety\u003csup\u003e\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e\u003cp\u003eIn recent years, completing standardized anesthesia assessments for all patients has become increasingly challenging due to global population aging and the growth of outpatient surgery. Aging populations have increased the number of surgical candidates with multiple comorbidities, functional decline, reduced respiratory reserve, frailty, neurocognitive impairment, mobility limitations, and polypharmacy\u003csup\u003e\u003cspan additionalcitationids=\"CR10 CR11\" citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e\u003c/sup\u003e, necessitating more careful evaluations. Advances in surgical techniques have expanded outpatient surgery, which offers low cancellation rates, shorter waits, reduced costs, and fewer nosocomial infections\u003csup\u003e\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e,\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e\u003c/sup\u003e, but rapid turnover requires early identification and optimization of health issues.\u003c/p\u003e\u003cp\u003eAlternatives to in-person anesthesia clinics include remote telephone/video consultations and questionnaire-assisted screening. In-person clinics foster trust and allow thorough examination\u003csup\u003e\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e\u003c/sup\u003e, but require significant patient time and resources. Remote evaluations, more frequently studied abroad\u003csup\u003e\u003cspan additionalcitationids=\"CR18\" citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e\u003c/sup\u003e, improve convenience and satisfaction but often serve as supplementary methods. Wienhold et al. demonstrated the feasibility and high satisfaction of a teleconsultation-based anesthesia platform, though with high technical requirements\u003csup\u003e\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e\u003c/sup\u003e. Questionnaire-based screening has also been developed internationally to improve efficiency\u003csup\u003e\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e,\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e\u003cp\u003eThe rise of artificial intelligence (AI) and mobile health (mHealth) offers promising solutions\u003csup\u003e\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e\u003c/sup\u003e. Since the U.S. FDA\u0026rsquo;s first approval of AI for clinical use in 2018, AI has been applied in diagnosis, screening, and prediction\u003csup\u003e\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e\u003c/sup\u003e. Machine learning enables computers to process complex clinical data and assist in decision-making\u003csup\u003e\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e,\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e\u003c/sup\u003e. In anesthesia, AI has supported tasks such as predicting hypotension from arterial waveforms\u003csup\u003e\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e\u003c/sup\u003e, estimating anesthesia depth from EEG\u003csup\u003e\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e\u003c/sup\u003e, predicting neuromuscular blockade from EMG\u003csup\u003e\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e\u003c/sup\u003e, identifying difficult airways from facial image\u003csup\u003e\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e\u003c/sup\u003e, assisting ultrasound-guided nerve blocks\u003csup\u003e\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e\u003c/sup\u003e, and predicting transfusion-related acute lung injury\u003csup\u003e\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e\u003c/sup\u003e. However, existing AI-based anesthesia assessment tools remain largely hospital-bound, with limited accessibility and functionality, lacking integrated features such as voice interaction and comprehensive decision support.\u003c/p\u003e\u003cp\u003eTo address these limitations, we developed firstly AI-assisted anesthesia evaluation system for Asian, capable of electronic assessment with external network compatibility, interactive evaluation, and clinical decision support. We subsequently initiated a single-center, randomized, parallel-group, open-label non-inferiority clinical trial to compare AI-assisted anesthesia assessment with traditional methods in terms of clinical outcomes.\u003c/p\u003e"},{"header":"Methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e\u003ch2\u003eAI-assisted anesthesia evaluation system\u003c/h2\u003e\u003cp\u003eThe AI-assisted anesthesia evaluation system was designed as a multi-layer, cross-platform architecture, integrating advanced web frameworks, high-performance databases, and intelligent external interfaces to deliver real-time, clinically relevant recommendations (Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e). Development was conducted in Visual Studio Code (Microsoft Corporation, Redmond, WA, USA), with a focus on scalability, interoperability, and seamless user experience across Android, iOS, Windows, and WeChat mini-programs.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\n\u003ch3\u003eBackend Architecture\u003c/h3\u003e\n\u003cp\u003eThe backend was implemented in Python. Two complementary frameworks\u003cem\u003e-\u003c/em\u003e Django for full-featured, high-level web development and Flask for lightweight, microservice-oriented tasks\u003cem\u003e-\u003c/em\u003e were combined to optimize both stability and flexibility.\u003c/p\u003e\u003cp\u003eData storage was designed for high concurrency and low-latency performance. PostgreSQL, a robust object-relational database, handles structured clinical and operational data, while Redis, an in-memory key\u0026ndash;value store, supports millisecond-level access to frequently queried items such as patient questionnaires and scoring scales. For unstructured data (e.g., medical images, uploaded documents), Alibaba Cloud OSS provides distributed, persistent object storage with global low-latency access.\u003c/p\u003e\u003cp\u003eNetwork communication is managed through Nginx as a reverse proxy for traffic routing and Gunicorn as a high-performance HTTP server, ensuring efficient request handling under peak loads.\u003c/p\u003e\n\u003ch3\u003eFrontend and Multi-Platform Deployment\u003c/h3\u003e\n\u003cp\u003eThe frontend was built with HTML, JavaScript, and CSS, enhanced by Vue and Uni-app frameworks. Using HBuilder, the codebase was compiled into both Android applications and WeChat mini-programs from a single source, reducing maintenance costs and ensuring consistent user experience across platforms.\u003c/p\u003e\u003cp\u003eDeployment employed Docker containerization for modular scalability, combined with Alibaba Cloud SLB load balancing for optimal availability under high query-per-second (QPS) conditions. Jenkins automated the DevOps pipeline, achieving continuous integration, delivery, and deployment. Comprehensive testing\u003cem\u003e-\u003c/em\u003e including unit, integration, system, and performance evaluations\u003cem\u003e-\u003c/em\u003e ensured stability and clinical reliability after each update.\u003c/p\u003e\n\u003ch3\u003eIntelligent External Interfaces\u003c/h3\u003e\n\u003cp\u003eThree external modules extend the system\u0026rsquo;s clinical utility. Baidu Cloud Language Service- Enables real-time speech-to-text and text-to-speech, enhancing accessibility for elderly patients. Barcode-Based Drug Identification-Integrates with a third-party pharmaceutical database for rapid medication entry via barcode scan or partial name input. Hospital Information System Integration-Provides reserved interfaces for HIS/LIS connectivity, allowing automated retrieval and synchronization of diagnostic results.\u003c/p\u003e\n\u003ch3\u003eSystem Workflow\u003c/h3\u003e\n\u003cp\u003eFollowing integration and testing, the system was packaged for multi-platform release, offering clinicians and patients an intuitive, interactive, and intelligent preoperative anesthesia evaluation tool-minimizing manual input while maximizing automation, precision, and accessibility in perioperative care.\u003c/p\u003e\u003cdiv id=\"Sec8\" class=\"Section2\"\u003e\u003ch2\u003eStudy Design\u003c/h2\u003e\u003cp\u003eThis was a single-center, randomized, controlled, parallel-group, open-label, non-inferiority trial conducted at Huashan Hospital. The study was approved by the Biomedical Ethics Committee of Huashan Hospital, and all participants provided written informed consent. The clinical registration number of the study was ChiCTR2400086869.\u003c/p\u003e\u003c/div\u003e\n\u003ch3\u003eParticipants\u003c/h3\u003e\n\u003cp\u003eWritten informed consent was obtained from all participants prior to their enrollment in this randomized controlled non-inferiority study. The study protocol was reviewed and approved by the Clinical Research Ethics Committee of Huashan Hospital, Fudan University (approval number: KY2022-917). Hospitalized patients scheduled for elective non-cardiac, non-endovascular, and non-day surgeries under general anesthesia between February 1 and March 31, 2023, were screened for eligibility. Inclusion criteria were: (1) age between 18 and 65 years; (2) undergoing elective surgery; (3) planned general anesthesia; and (4) ability to understand and sign informed consent. Exclusion criteria included: (1) patients with newly diagnosed severe conditions requiring multidisciplinary consultation prior to evaluation; (2) inability to complete anesthesia assessment after communication; or (3) concurrent participation in another clinical trial.\u003c/p\u003e\n\u003ch3\u003eRandomization and Group Allocation\u003c/h3\u003e\n\u003cp\u003eEligible patients were identified upon anesthesia appointment notification. Contact information was retrieved from the hospital information system, and consent was obtained prior to enrollment. Using SPSS 22.0 (IBM Corp., Armonk, NY, USA), a randomization list was generated containing numbers 1 to 600, which were shuffled using a randomization algorithm. Participants were assigned in a 1:1 ratio to either the control group or the intervention group based on their randomized sequence. If a patient withdrew, the number plus 600 was used as the recruitment index, with group assignment unchanged.\u003c/p\u003e\u003cdiv id=\"Sec11\" class=\"Section2\"\u003e\u003ch2\u003eIntervention\u003c/h2\u003e\u003cp\u003e\u003cstrong\u003eControl group (traditional evaluation)\u003c/strong\u003e\u003cp\u003eA trained anesthesiology resident performed standard face-to-face preoperative evaluation at the bedside. The completed evaluation was documented and provided to the attending anesthesiologist on the day of surgery.\u003c/p\u003e\u003c/p\u003e\u003cp\u003e\u003cstrong\u003eIntervention group (AI-assisted evaluation)\u003c/strong\u003e\u003cp\u003eA link to the AI-based anesthesia evaluation system (via WeChat Mini Program) was sent to patients or their caregivers. Patients were instructed to complete the self-guided assessment. The anesthesiology resident reviewed the AI-generated report prior to bedside confirmation. If the patient could not complete the evaluation independently, the resident assisted using the system interface. The finalized report was automatically forwarded to the attending anesthesiologist.\u003c/p\u003e\u003c/p\u003e\u003cp\u003eOn the day of surgery, all patients were re-evaluated by an experienced attending anesthesiologist, who also assessed the quality of the initial anesthesia evaluation report using a standardized scoring form. Additionally, patients completed a questionnaire assessing satisfaction with the anesthesia evaluation process.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec12\" class=\"Section2\"\u003e\u003ch2\u003eAnesthesia Evaluation\u003c/h2\u003e\u003cp\u003ePatient satisfaction with the evaluation process was assessed using a questionnaire that included items on patients\u0026rsquo; understanding of anesthesia procedures and any remaining concerns or anxiety (Supplementary Tables\u0026nbsp;1 and 2). Anesthesia evaluations were conducted by anesthesiology residents who had completed standardized residency training. On the day of surgery, anesthesia was administered by senior anesthesiologists holding intermediate or advanced professional titles.\u003c/p\u003e\u003cp\u003eThe grading criteria for the completeness and accuracy of the anesthesia assessment were as follows. Grade A was defined as a fully complete anesthesia assessment with no identified errors, such as a report containing entirely accurate and comprehensive information. Grade B referred to results with one to five distinct issues, for example, a report missing two items and containing one incorrect entry. Grade C applied to results with six or more issues, such as a report missing seven items, containing two incorrect entries, and including three illegible items.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec13\" class=\"Section2\"\u003e\u003ch2\u003eOutcomes\u003c/h2\u003e\u003cp\u003e\u003cul\u003e\u003cli\u003e\u003cp\u003eThe primary outcome of this study was the accuracy of ASA (American Society of Anesthesiologists) physical status classification. Accuracy was defined as the level of agreement between the initial classification\u003cem\u003e-\u003c/em\u003e whether AI-assisted or traditional\u003cem\u003e-\u003c/em\u003e and the final classification determined by the attending anesthesiologist.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eSecondary outcomes included the accuracy and completeness of medical history collection, which was evaluated by the attending anesthesiologist using a predefined grading scale. Additionally, the time required to complete the anesthesia evaluation was recorded, measured from the beginning to the end of the assessment process, excluding the time spent on obtaining informed consent.\u003c/p\u003e\u003c/li\u003e\u003c/ul\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec14\" class=\"Section2\"\u003e\u003ch2\u003eQuality Control\u003c/h2\u003e\u003cp\u003eAll evaluators underwent standardized training prior to study initiation to ensure consistency. To reduce data loss, up-to-date contact information was maintained for all participants. Data were double-checked and entered independently by two researchers not involved in the study.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec15\" class=\"Section2\"\u003e\u003ch2\u003eSample Size Calculating\u003c/h2\u003e\u003cp\u003eFor sample size calculation, pilot data indicated an accuracy of 91% in the control group and 93% in the intervention group. Using a non-inferiority margin (Δ) of 5%, a one-sided alpha of 0.025, and 80% power, the minimum required sample size was calculated with PASS 11 software. This resulted in a target of 472 patients (236 per group). Allowing for a 10% dropout rate, the final sample size was set at 600 patients, with 300 in each group (Supplementary Table\u0026nbsp;1).\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec16\" class=\"Section2\"\u003e\u003ch2\u003eStatistical Analysis\u003c/h2\u003e\u003cp\u003eAll analyses were performed using SPSS 22.0 and and R software 4.5.1. Descriptive statistics included frequencies and percentages for categorical variables, and mean\u0026thinsp;\u0026plusmn;\u0026thinsp;standard deviation or median (interquartile range) for continuous variables. Between-group comparisons were conducted using the chi-square test or Fisher\u0026rsquo;s exact test for categorical variables, and t-tests or Wilcoxon rank-sum tests for continuous variables, depending on distribution. For ordinal outcomes, Kruskal\u0026ndash;Wallis tests were used. A two-sided P-value\u0026thinsp;\u0026lt;\u0026thinsp;0.05 was considered statistically significant.\u003c/p\u003e\u003c/div\u003e"},{"header":"Results","content":"\u003cdiv id=\"Sec18\" class=\"Section2\"\u003e\u003ch2\u003eFlowchart of the study\u003c/h2\u003e\u003cp\u003eA total of 692 patients were initially screened for eligibility. After applying exclusion criteria, 92 patients were excluded: 33 requested anesthesia consultations, 26 surgeries were cancelled, 16 were concurrently enrolled in other clinical trials, and 17 were unable to cooperate with the anesthesia assessment. Ultimately, 600 patients were enrolled and included in the final analysis, with 300 in the traditional evaluation group and 300 in the AI-assisted evaluation group (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e).\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec19\" class=\"Section2\"\u003e\u003ch2\u003eBaseline demographics and clinical characteristics\u003c/h2\u003e\u003cp\u003eClinical features of participants were presented in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e. Among all participants, 318 (53.0%) were male and 282 (47.0%) were female. ASA physical status classifications were as follows: 355 (59.2%) ASA I, 221 (36.8%) ASA II, and 24 (4.0%) ASA III. Patients were scheduled for surgeries across various departments, including neurosurgery (10.2%), general surgery (19.0%), thoracic surgery (12.0%), ENT/head and neck surgery (6.5%), urology (9.3%), pancreatic surgery (1.7%), hand surgery (21.3%), orthopedics (13.8%), and sports medicine (6.2%). Baseline demographics, ASA classifications, and surgical types were comparable between the two groups (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026gt;\u0026thinsp;0.05).\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eBaseline characteristics of the per protocol population\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"4\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCategory\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eTraditional Evaluation Group\u003c/p\u003e\u003cp\u003e(\u003cem\u003en\u003c/em\u003e\u0026thinsp;=\u0026thinsp;300)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eAI-assisted Evaluation Group\u003c/p\u003e\u003cp\u003e(\u003cem\u003en\u003c/em\u003e\u0026thinsp;=\u0026thinsp;300)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u003cem\u003eP\u003c/em\u003e value\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eSex, n (%)\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.567\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMale\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e163 (54.3%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e155 (51.7%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eFemale\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e137 (45.7%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e145 (48.3%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eAge (years), Median (IQR)\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e48.0 (35.0, 58.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e46.0 (29.0, 54.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.698\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eASA Classification by Senior Anesthesiologists\u003c/b\u003e,\u003c/p\u003e\u003cp\u003e\u003cb\u003en (%)\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.624\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eGrade I\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e173 (57.7%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e182 (60.7%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eGrade II\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e116 (38.7%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e105 (35.0%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eGrade III\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e11 (3.7%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e13 (4.3%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003ePlanned Surgical Department\u003c/b\u003e,\u003c/p\u003e\u003cp\u003e\u003cb\u003en (%)\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.733\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNeurosurgery\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e35 (11.7%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e26 (8.7%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eGeneral Surgery\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e57 (19.0%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e57 (19.0%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCardiothoracic Surgery\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e41 (13.7%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e31 (10.3%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eOtorhinolaryngology- Head and Neck Surgery\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e17 (5.7%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e22 (7.3%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eUrology\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e27 (9.0%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e29 (9.7%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePancreatic Surgery\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e5 (1.7%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e5 (1.7%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHand Surgery\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e63 (21.0%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e64 (21.3%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eOrthopedics\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e40 (13.3%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e43 (14.3%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSports Medicine\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e15 (5.0%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e23 (7.7%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec20\" class=\"Section2\"\u003e\u003ch2\u003ePrimary outcome\u003c/h2\u003e\u003cp\u003eThe accuracy of ASA classification was 91.7% (275/300) in the traditional group and 93.3% (280/300) in the AI-assisted group (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.033, Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e). The difference in accuracy was 1.6% (95% CI: -2.6\u0026ndash;5.9%), with the lower bound above the predefined non-inferiority margin of -5%. This confirmed the non-inferiority of the AI-assisted evaluation compared to traditional methods (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e).\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eASA classification accuracy rate for each group\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"7\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003eGroup\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003eTotal (\u003cem\u003en\u003c/em\u003e)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003eCorrect\u003c/p\u003e\u003cp\u003e\u003cem\u003en\u003c/em\u003e (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003eIncorrect\u003c/p\u003e\u003cp\u003e\u003cem\u003en\u003c/em\u003e (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003eRate Difference (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\u003cp\u003eNon-Inferiority Test\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e\u003cem\u003eZ\u003c/em\u003e value\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e\u003cem\u003eP\u003c/em\u003e value\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eTraditional Assessment\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e300\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e275(91.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e25(8.3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003e1.6%\u003c/p\u003e\u003cp\u003e(-2.6%-5.9%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003e1.848\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003e\u003cb\u003e0.033\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eAI-Based Assessment\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e300\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e280(93.3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e20(6.7)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec21\" class=\"Section2\"\u003e\u003ch2\u003eSecondary outcomes\u003c/h2\u003e\u003cp\u003eEvaluation quality, measured by completeness and accuracy of the anesthesia reports, was significantly higher in the AI-assisted group. In the traditional group, 195 (65.0%) of 300 reports contained a total of 971 issues (3.2% error rate), including incomplete information (43.3%), ambiguous entries (20.7%), incorrect entries (18.0%), and missing items (21.7%). In contrast, only 99 (33.0%) of AI-assisted reports contained 337 issues (1.1% error rate), with lower frequencies of all error types (Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e).\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eError rate of the assessment report for each group\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"4\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCategory\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eTotal Occurrences,(\u003cem\u003en\u003c/em\u003e)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eReports with Issues,\u003cem\u003en\u003c/em\u003e (%)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eError Rate\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003ctr\u003e\u003cth align=\"left\" colspan=\"4\" nameend=\"c4\" namest=\"c1\"\u003e\u003cp\u003eTraditional Assessment Group\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eIncomplete information\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e715\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e130 (43.3%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e2.40%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eAmbiguous entries\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e87\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e62 (20.7%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.30%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eIncorrect entries\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e82\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e54 (18.0%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.30%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eMissing items\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e87\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e65 (21.7%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.30%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eTotal\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e971\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e195 (65.0%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e3.20%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colspan=\"4\" nameend=\"c4\" namest=\"c1\"\u003e\u003cp\u003e\u003cb\u003eAI-based Assessment Group\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eIncomplete information\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e239\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e82 (27.3%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.80%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eAmbiguous entries\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e41\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e25 (8.3%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.10%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eIncorrect entries\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e35\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e21 (7.0%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.20%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eMissing items\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e22\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e13 (4.3%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.10%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eTotal\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e337\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e99 (33.0%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1.10%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003eBased on the grading criteria for the completeness and accuracy of the anesthesia assessment, 67.0% of AI-assisted reports were rated Grade A, compared to 35.0% in the traditional group. The distribution of report quality ratings differed significantly between groups (X\u0026sup2;(2, N\u0026thinsp;=\u0026thinsp;300)\u0026thinsp;=\u0026thinsp;63.595, \u003cem\u003eP\u0026thinsp;\u0026lt;\u003c/em\u003e\u0026thinsp;0.001), favoring the AI-assisted method (Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003eA).\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003eThe anesthesia evaluation time was significantly shorter in the AI-assisted group, with a median (IQR) of 3.0 (2.0\u0026ndash;5.0) minutes, compared to the traditional group, which had a median (IQR) of 7.0 (6.0\u0026ndash;8.0) minutes (Z\u0026thinsp;=\u0026thinsp;17.25, P\u0026thinsp;\u0026lt;\u0026thinsp;0.01) (Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003eB).\u003c/p\u003e\u003cp\u003eThere were no statistically significant differences between groups regarding patients\u0026rsquo; understanding of anesthesia procedures, anesthesia-related risks, resolution of concerns, or reduction of anxiety (Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e). Overall satisfaction with the evaluation process was higher in the AI-assisted group, with 262 patients (87.3%) indicating they \"strongly agreed\" or \"agreed\" that they were satisfied, compared to 228 (76.0%) in the traditional group (\u003cem\u003eP\u0026thinsp;\u0026lt;\u003c/em\u003e\u0026thinsp;0.01) (Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003eC).\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab4\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 4\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eAnesthesia assessment effect\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"7\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eQuestion\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eStrongly Agree\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eAgree\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\u003cp\u003eNeutral\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003eDisagree\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c7\"\u003e\u003cp\u003eStrongly Disagree\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003ctr\u003e\u003cth align=\"left\" colspan=\"7\" nameend=\"c7\" namest=\"c1\"\u003e\u003cp\u003eTraditional Assessment Group\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cem\u003eI clearly understand the anesthesia procedure\u003c/em\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e71\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c4\" namest=\"c3\"\u003e\u003cp\u003e157\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e35\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e21\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e16\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cem\u003eI clearly understand the anesthesia risks\u003c/em\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e56\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c4\" namest=\"c3\"\u003e\u003cp\u003e158\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e33\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e23\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e30\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cem\u003eMy questions about anesthesia were addressed during assessment\u003c/em\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e59\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c4\" namest=\"c3\"\u003e\u003cp\u003e173\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e31\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e19\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e18\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cem\u003eI no longer have any fear or anxiety about anesthesia\u003c/em\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e45\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c4\" namest=\"c3\"\u003e\u003cp\u003e143\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e36\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e25\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e51\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cem\u003eI am very satisfied with the anesthesia assessment process\u003c/em\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e70\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c4\" namest=\"c3\"\u003e\u003cp\u003e158\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e28\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e21\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e23\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colspan=\"7\" nameend=\"c7\" namest=\"c1\"\u003e\u003cp\u003e\u003cb\u003eAI-Assisted Assessment Group\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cem\u003eI clearly understand the anesthesia procedure\u003c/em\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e108\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c4\" namest=\"c3\"\u003e\u003cp\u003e92\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e35\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e45\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e20\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cem\u003eI clearly understand the anesthesia risks\u003c/em\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e68\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c4\" namest=\"c3\"\u003e\u003cp\u003e89\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e53\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e55\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e35\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cem\u003eMy questions about anesthesia were addressed during assessment\u003c/em\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e104\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c4\" namest=\"c3\"\u003e\u003cp\u003e66\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e100\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e20\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e10\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cem\u003eI no longer have any fear or anxiety about anesthesia\u003c/em\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e67\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c4\" namest=\"c3\"\u003e\u003cp\u003e225\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e63\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e37\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e16\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cem\u003eI am very satisfied with the anesthesia assessment process\u003c/em\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e43\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c4\" namest=\"c3\"\u003e\u003cp\u003e9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e"},{"header":"Discussion","content":"\u003cp\u003eIn this study, we designed a novel form of preoperative anesthesia evaluation, wherein anesthesiologists conducted assessments with the assistance of a newly developed AI-based anesthesia evaluation system. This approach was intended to maintain diagnostic accuracy while improving assessment efficiency and reducing the time burden on anesthesiologists.\u003c/p\u003e\u003cp\u003eOur findings demonstrated that the AI-assisted group achieved non-inferior performance in ASA classification accuracy compared to the traditional evaluation group, suggesting comparable capacity to identify the severity of patients\u0026rsquo; comorbidities. In addition, evaluation reports generated in the AI-assisted group were of higher quality, offering more comprehensive information to support individualized anesthetic planning. Importantly, anesthesiologists in the AI group saved an average of 4 minutes per patient during the evaluation process, and patient satisfaction was significantly higher in this group.\u003c/p\u003e\u003cp\u003eCollectively, these results indicate that AI-assisted anesthesia evaluation may serve as a clinically applicable, efficient, and high-quality alternative to traditional face-to-face assessments. Previous studies evaluating new anesthesia assessment formats have primarily focused on remote video or telephone-based consultations, with outcomes such as reduced travel time, economic cost, patient satisfaction, or surgical cancellation rate\u003csup\u003e\u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e\u003c/sup\u003e. In contrast, our AI-based system was implemented in-hospital, with anesthesiologists reviewing and confirming each evaluation. Given the confounding factors during the COVID-19 pandemic, surgical cancellation was not chosen as a primary endpoint. Instead, ASA classification was selected based on two main considerations. First, despite its limitations as a sole predictor of surgical risk, the ASA physical status system\u003cem\u003e-\u003c/em\u003e established over six decades ago\u003cem\u003e-\u003c/em\u003e remains a widely accepted tool for quantifying patients\u0026rsquo; physiological reserve and tolerance to anesthesia and surgery. Second, ASA classification is familiar to anesthesiologists, making it a reliable and credible primary outcome measure in this setting\u003csup\u003e\u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e\u003c/sup\u003e. As our assessors were well-trained in applying ASA grading, a non-inferiority design was adopted and confirmed by the results.\u003c/p\u003e\u003cp\u003eBeyond ASA classification, the completeness and quality of the evaluation report are central to the anesthetic assessment. Prior studies have shown that electronic evaluations can capture more detailed information while saving time, whereas paper records may be prone to loss, damage, or illegibility\u003cem\u003e-\u003c/em\u003e particularly when the assessment and operative anesthesiologists are not the same\u003csup\u003e\u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e35\u003c/span\u003e\u003c/sup\u003e. Our AI-based system was designed with a structured decision-tree algorithm based on standardized anesthetic assessment guidelines. It dynamically generates individualized questionnaires through follow-up prompts, based on patient-specific responses. As evidenced by our results, the AI-generated reports demonstrated significantly higher quality ratings than those from conventional face-to-face evaluations.\u003c/p\u003e\u003cp\u003eRegarding time efficiency, consistent with findings from previous studies on electronic preoperative screening, the AI-based assessment reduced overall evaluation time\u003csup\u003e\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e\u003c/sup\u003e. This improvement can be attributed to two main factors: (1) the AI system guides patients through the assessment independently, minimizing the need for item-by-item inquiries from the anesthesiologist; (2) patients can directly record their current medications via voice input or barcode scanning from a built-in pharmaceutical database. However, the average time saved was modest (4 minutes), partially because many patients were unfamiliar with smartphone operations and required additional assistance from medical staff.\u003c/p\u003e\u003cp\u003eIn terms of effectiveness, the AI-based system performed comparably to traditional evaluations in communicating anesthesia procedures, disclosing anesthesia-related risks, addressing patient concerns, and alleviating preoperative anxiety. Patient satisfaction scores were higher in the AI group, further supporting its potential as a high-quality and valuable tool for clinical anesthesia evaluation.\u003c/p\u003e\u003cp\u003eThere were several limitations in our study. This study included patients aged 18\u0026ndash;65 years and did not cover high-risk elderly populations (\u0026gt;\u0026thinsp;65 years), as these patients are typically assessed by dedicated teams in our institution, making randomization between groups impractical. Additionally, the time spent by anesthesiologists obtaining informed consent was not recorded, as many patients lacked available family members or legal proxies during the assessment process. Moreover, since the AI system had not yet integrated with the hospital\u0026rsquo;s laboratory reporting interface, anesthesiologists needed to manually retrieve test results from the hospital information system (HIS), increasing preparation time, which was not counted as part of the evaluation duration.\u003c/p\u003e"},{"header":"Conclusions","content":"\u003cp\u003eOur study was the first to present a novel AI-assisted anesthesia evaluation system for Asian and conducted a randomized controlled trial to validate its clinical value. The results showed that the clinical performance of AI-assisted anesthesia evaluation was non-inferior to that of the traditional assessment. Moreover, the AI-assisted system demonstrated additional advantages, including higher assessment quality, reduced evaluation time, and greater patient satisfaction. These findings suggest that AI-assisted anesthesia evaluation may represent a superior alternative for clinical anesthesia assessment.\u003c/p\u003e"},{"header":"Abbreviations","content":"\u003cdiv class=\"DefinitionList\"\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eACT\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eAnesthesia Control Tower\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eAI\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eArtificial Intelligence\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eASA\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eAmerican Society of Anesthesiologists\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eCDSS\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eClinical Decision Support System\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eCOVID-19\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eCoronavirus Disease 2019\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eEHR\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eElectronic Health Record\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eERAS\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eEnhanced Recovery After Surgery\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eGSMA\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eGroupe Speciale Mobile Association\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eIOT\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eInternet of things\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eIT\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eInformation Technology\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eMDIDSs\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eMedical Device Interface Data Sheets\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003emHealth\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eMobile Health\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003ePACU\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003ePost-Anesthesia Care Unit\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003ePCMH\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003ePatient-Centered Medical Home\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003ePHR\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003ePersonal health record\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eQPS\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eQueries Per Second\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eStaRI\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eStandards for Reporting Implementation Studies\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eSUS\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eSystem Usability Scale\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003c/div\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eFunding\u003c/strong\u003e\u003cstrong\u003e：\u003c/strong\u003eThis work was supported by the Foundation of Shanghai Municipal Science and Technology Medical Innovation Research Project (23Y21900600 to Yingwei Wang), the Foundation of Shanghai Municipal Key Clinical Specialty (shslczdzk06901 to Yingwei Wang), the Foundation of Shanghai Municipal Science and Technology Commission (22ZR1409600 to Daojie Xu).\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthors\u0026rsquo; contributions: Jiangtao Qi:\u0026nbsp;\u003c/strong\u003eFormal analysis, Validation, Writing- original draft.\u003cstrong\u003eJingjing Shen\u003c/strong\u003e\u003cstrong\u003e:\u003c/strong\u003e Methodology, Validation, Writing- review \u0026amp; editing.\u0026nbsp;\u003cstrong\u003eYiqi Wu\u003c/strong\u003e\u003cstrong\u003e:\u003c/strong\u003e Methodology, Resources.\u0026nbsp;\u003cstrong\u003eShuchi Zhang\u003c/strong\u003e\u003cstrong\u003e:\u003c/strong\u003e Methodology.\u0026nbsp;\u003cstrong\u003eDaojie Xu\u003c/strong\u003e\u003cstrong\u003e:\u003c/strong\u003e Funding acquisition, Investigation, Writing- review \u0026amp; editing.\u0026nbsp;\u003cstrong\u003eYingwei Wang\u003c/strong\u003e\u003cstrong\u003e:\u0026nbsp;\u003c/strong\u003eProject administration, Resources.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthics approval and consent to participate:\u0026nbsp;\u003c/strong\u003eThis study was conducted in accordance with the ethical principles of the Declaration of Helsinki. This study was approved by the Clinical Research Ethics Committee of Huashan Hospital (KY2022-917).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData and materials availability:\u0026nbsp;\u003c/strong\u003eData and materials generated that are relevant to the results are included in this article. Other data are available from the corresponding author upon reasonable request.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eDeclaration of Interest statement\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAll authors have declared no conflicts of interest.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003ePresentation (for original articles only)\u003c/strong\u003e\u003cstrong\u003e:\u003c/strong\u003e None.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eStudy design:\u0026nbsp;\u003c/strong\u003eRandomized Controlled Trial\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eRegistry:\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003echictr.org.cn.\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003eClinical trial number:\u003c/strong\u003e\u003cstrong\u003e\u0026nbsp;ChiCTR2400086869.\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003eRegistration date:\u003c/strong\u003e\u003cstrong\u003e\u0026nbsp;12 July 2024.\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003eRetrospectively registered\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent to Publish declaration:\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003eNot Applicable.\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent to Participate declaration:\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003eWritten informed consent was obtained from all participants prior to their enrollment in this randomized controlled non-inferiority study. The study protocol was reviewed and approved by the Clinical Research Ethics Committee of Huashan Hospital, Fudan University (approval number: KY2022-917).\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCONSORT 2025 Statement:\u003c/strong\u003e\u003cstrong\u003e\u0026nbsp;This study was conducted and reported in accordance with the Consolidated Standards of Reporting Trials (CONSORT) guidelines.\u003c/strong\u003e\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eBates DW, Levine DM, Salmasian H, et al. The Safety of Inpatient Health Care. N Engl J Med. 2023;388(2):142\u0026ndash;53.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eWang Y, Eldridge N, Metersky ML, et al. National trends in patient safety for four common conditions, 2005\u0026ndash;2011. N Engl J Med. 2014;370(4):341\u0026ndash;51.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eWacker J, Staender S. The role of the anesthesiologist in perioperative patient safety. Curr Opin Anaesthesiol. 2014;27(6):649\u0026ndash;56.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eAl Talalwah N, McIltrot KH. Cancellation of Surgeries: Integrative Review. J Perianesth Nurs. 2019;34(1):86\u0026ndash;96.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eFischer SP. Development and effectiveness of an anesthesia preoperative evaluation clinic in a teaching hospital. Anesthesiology. 1996;85(1):196\u0026ndash;206.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eZambouri A. Preoperative evaluation and preparation for anesthesia and surgery. Hippokratia. 2007;11(1):13\u0026ndash;21.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eGebremedhn EG, Nagaratnam V. Assessment of patient satisfaction with the preoperative anesthetic evaluation. Patient Relat Outcome Meas. 2014;5:105\u0026ndash;10.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSeim AR, Fagerhaug T, Ryen SM, et al. Causes of cancellations on the day of surgery at two major university hospitals. Surg Innov. 2009;16(2):173\u0026ndash;80.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003ePeden CJ, Campbell M, Aggarwal G. Quality, safety, and outcomes in anaesthesia: what's to be done? An international perspective. Br J Anaesth. 2017;119(suppl1):i5\u0026ndash;14.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMonk TG, Weldon BC, Garvan CW, et al. Predictors of cognitive dysfunction after major noncardiac surgery. Anesthesiology. 2008;108(1):18\u0026ndash;30.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eRivera R, Antognini JF. Perioperative drug therapy in elderly patients. Anesthesiology. 2009;110(5):1176\u0026ndash;81.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eTurrentine FE, Wang H, Simpson VB, Jones RS. Surgical risk factors, morbidity, and mortality in elderly patients. J Am Coll Surg. 2006;203(6):865\u0026ndash;77.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eCullen KA, Hall MJ, Golosinskiy A. Ambulatory surgery in the United States, 2006. Natl Health Stat Rep 2009(11):1\u0026ndash;25.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSmith I, Cooke T, Jackson I, Fitzpatrick R. Rising to the challenges of achieving day surgery targets. Anaesthesia. 2006;61(12):1191\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eTregoning JS, Flight KE, Higham SL, Wang Z, Pierce BF. Progress of the COVID-19 vaccine effort: viruses, vaccines and variants versus efficacy, effectiveness and escape. Nat Rev Immunol. 2021;21(10):626\u0026ndash;36.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eAmaya F, Shimamoto S, Matsuda M, Kageyama K, Sawa T. Preoperative anesthesia clinic in Japan: a nationwide survey of the current practice of preoperative anesthesia assessment. J Anesth. 2015;29(2):175\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eApplegate RL 2nd, Gildea B, Patchin R, et al. Telemedicine pre-anesthesia evaluation: a randomized pilot trial. Telemed J E Health. 2013;19(3):211\u0026ndash;6.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eWong DT, Kamming D, Salenieks ME, Go K, Kohm C, Chung F. Preadmission anesthesia consultation using telemedicine technology: a pilot study. Anesthesiology. 2004;100(6):1605\u0026ndash;7.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMullen-Fortino M, Rising KL, Duckworth J, Gwynn V, Sites FD, Hollander JE. Presurgical Assessment Using Telemedicine Technology: Impact on Efficiency, Effectiveness, and Patient Experience of Care. Telemed J E Health. 2019;25(2):137\u0026ndash;42.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eWienhold J, M\u0026ouml;sch L, Rossaint R, et al. Teleconsultation for preoperative evaluation during the coronavirus disease 2019 pandemic: A technical and medical feasibility study. Eur J Anaesthesiol. 2021;38(12):1284\u0026ndash;92.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eGoodhart IM, Andrzejowski JC, Jones GL, et al. Patient-completed, preoperative web-based anaesthetic assessment questionnaire (electronic Personal Assessment Questionnaire PreOperative): Development and validation. Eur J Anaesthesiol. 2017;34(4):221\u0026ndash;8.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLadfors MB, L\u0026ouml;fgren ME, Gabriel B, Olsson JH. Patient accept questionnaires integrated in clinical routine: a study by the Swedish National Register for Gynecological Surgery. Acta Obstet Gynecol Scand. 2002;81(5):437\u0026ndash;42.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eXu M, Liu H, Dai A, et al. Dynamic and interpretable deep learning model for predicting respiratory failure following cardiac surgery. BMC Anesthesiol. 2025;25(1):394.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eJiang F, Jiang Y, Zhi H, et al. Artificial intelligence in healthcare: past, present and future. Stroke Vasc Neurol. 2017;2(4):230\u0026ndash;43.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eYin J, Ngiam KY, Teo HH. Role of Artificial Intelligence Applications in Real-Life Clinical Practice: Systematic Review. J Med Internet Res. 2021;23(4):e25759.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eWijnberge M, Geerts BF, Hol L, et al. Effect of a Machine Learning-Derived Early Warning System for Intraoperative Hypotension vs Standard Care on Depth and Duration of Intraoperative Hypotension During Elective Noncardiac Surgery: The HYPE Randomized Clinical Trial. JAMA. 2020;323(11):1052\u0026ndash;60.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHatib F, Jian Z, Buddi S, et al. Machine-learning Algorithm to Predict Hypotension Based on High-fidelity Arterial Pressure Waveform Analysis. Anesthesiology. 2018;129(4):663\u0026ndash;74.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHaghighi SJ, Komeili M, Hatzinakos D, Beheiry HE. 40-Hz ASSR for Measuring Depth of Anaesthesia During Induction Phase. IEEE J Biomed Health Inf. 2018;22(6):1871\u0026ndash;82.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSantanen OA, Svartling N, Haasio J, Paloheimo MP. Neural nets and prediction of the recovery rate from neuromuscular block. Eur J Anaesthesiol. 2003;20(2):87\u0026ndash;92.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eCuendet GL, Schoettker P, Y\u0026uuml;ce A, et al. Facial Image Analysis for Fully Automatic Prediction of Difficult Endotracheal Intubation. IEEE Trans Biomed Eng. 2016;63(2):328\u0026ndash;39.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eYang XY, Wang LT, Li GD, et al. Artificial intelligence using deep neural network learning for automatic location of the interscalene brachial plexus in ultrasound images. Eur J Anaesthesiol. 2022;39(9):758\u0026ndash;65.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eChristie SA, Conroy AS, Callcut RA, Hubbard AE, Cohen MJ. Dynamic multi-outcome prediction after injury: Applying adaptive machine learning for precision medicine in trauma. PLoS ONE. 2019;14(4):e0213836.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003evan Hoorn BT, Tromp DJ, van Rees RCM, et al. Effectiveness of a digital vs face-to-face preoperative assessment: A randomized, noninferiority clinical trial. J Clin Anesth. 2023;90:111192.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eDripps RD, Lamont A, Eckenhoff JE. The role of anesthesia in surgical mortality. JAMA. 1961;178:261\u0026ndash;6.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eStrassberger-Nerschbach N, Magyaros F, Maria W, et al. Quality comparison of remote anesthetic consultation versus on-site consultation in children with sedation for a magnetic resonance imaging examination-A randomized controlled trial. Paediatr Anaesth. 2023;33(8):647\u0026ndash;56.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHowell M, Hood AJ, Jayne DG. Use of a patient completed iPad questionnaire to improve pre-operative assessment. J Clin Monit Comput. 2017;31(1):221\u0026ndash;5.\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"bmc-anesthesiology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bane","sideBox":"Learn more about [BMC Anesthesiology](http://bmcanesthesiol.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/bane","title":"BMC Anesthesiology","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Artificial intelligence, Anesthesia assessment, Randomized controlled trial, Noninferiority","lastPublishedDoi":"10.21203/rs.3.rs-7364932/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7364932/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cem\u003e\u003cstrong\u003eStudy Objective:\u003c/strong\u003e\u003c/em\u003e\u003cstrong\u003e \u003c/strong\u003eTo evaluate the clinical effectiveness and feasibility of a novel AI-assisted anesthesia evaluation system compared with conventional preoperative anesthesia assessments.\u003c/p\u003e\n\u003cp\u003e\u003cem\u003e\u003cstrong\u003eDesign: \u003c/strong\u003e\u003c/em\u003eSingle-center, randomized, parallel-group, open-label, non-inferiority trial.\u003c/p\u003e\n\u003cp\u003e\u003cem\u003e\u003cstrong\u003ePatients: \u003c/strong\u003e\u003c/em\u003e600 adult patients scheduled for elective non-cardiac surgery under general anesthesia were randomly assigned to AI-assisted assessment group or traditional in-person anesthesia evaluation group.\u003c/p\u003e\n\u003cp\u003e\u003cem\u003e\u003cstrong\u003eMeasurements: \u003c/strong\u003e\u003c/em\u003eThe primary outcome was the accuracy of ASA (American Society of Anesthesiologists) physical status classification. Secondary outcomes included the quality and completeness of medical history documentation, assessment duration, and patient satisfaction.\u003c/p\u003e\n\u003cp\u003e\u003cem\u003e\u003cstrong\u003eMain Results: \u003c/strong\u003e\u003c/em\u003eThe AI-assisted group achieved non-inferior accuracy in ASA classification compared to the traditional group (93.3% [280/300] vs. 91.7% [275/300], \u003cem\u003eP\u003c/em\u003e = 0.033). The difference in accuracy was 1.6% (95% CI: -2.6% to 5.9%), with the lower bound above the predefined non-inferiority margin of -5%. The AI system demonstrated significantly higher documentation quality, including fewer missing items (4.3% vs. 21.7%) and incorrect entries (7.0% vs. 18.0%). Assessment time was markedly shorter in the AI group (3.0 [2.0-5.0] vs. 7.0 [6.0-8.0] minutes, \u003cem\u003eP \u0026lt;\u003c/em\u003e0.001), and overall patient satisfaction was significantly higher (87.3% [262/300] vs. 76.0% [228/300], \u003cem\u003eP \u0026lt;\u003c/em\u003e0.01).\u003c/p\u003e\n\u003cp\u003e\u003cem\u003e\u003cstrong\u003eConclusions: \u003c/strong\u003e\u003c/em\u003e\u003cstrong\u003eThe \u003c/strong\u003eAI-assisted anesthesia evaluation system was non-inferior to traditional assessment in ASA classification accuracy while offering superior efficiency, documentation quality, and patient satisfaction. This AI-based approach may represent a scalable and effective alternative for preoperative anesthesia evaluations across diverse clinical settings.\u003c/p\u003e\n\u003cp\u003e\u003cem\u003e\u003cstrong\u003eRegistry:\u003c/strong\u003e\u003c/em\u003e\u003cstrong\u003echictr.org.cn, TRN: ChiCTR2400086869, Registration date: 12 July 2024. Retrospectively registered\u003c/strong\u003e\u003c/p\u003e","manuscriptTitle":"Efficacy and Efficiency of Artificial Intelligence-based Preoperative Anesthesia Evaluation: A Randomized Controlled Non-Inferiority Study","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-22 08:57:20","doi":"10.21203/rs.3.rs-7364932/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"119166986326275812471450264999195589994","date":"2026-05-13T18:42:25+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-09T15:28:24+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"15691340220758537507732759263469353640","date":"2026-05-09T04:43:55+00:00","index":"hide","fulltext":""},{"type":"editorInvited","content":"","date":"2026-04-24T20:59:36+00:00","index":"","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-10T18:55:32+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-02T05:31:49+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-08-30T11:21:28+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Anesthesiology","date":"2025-08-30T11:18:46+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-anesthesiology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bane","sideBox":"Learn more about [BMC Anesthesiology](http://bmcanesthesiol.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/bane","title":"BMC Anesthesiology","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"ca640cd8-1e66-4fa7-a757-138a76e429f6","owner":[],"postedDate":"September 22nd, 2025","published":true,"recentEditorialEvents":[{"type":"reviewerAgreed","content":"119166986326275812471450264999195589994","date":"2026-05-13T18:42:25+00:00","index":60,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-09T15:28:24+00:00","index":55,"fulltext":""},{"type":"reviewerAgreed","content":"15691340220758537507732759263469353640","date":"2026-05-09T04:43:55+00:00","index":54,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-09-22T08:57:20+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-22 08:57:20","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7364932","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7364932","identity":"rs-7364932","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}