[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-447119-105":3,"detail-sidebar-cat-0-en-105":79,"doc-detail-447119-en":129},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":72,"head_meta":74,"extra_data":76,"updated_unix":78},105,"en","from-injury-to-comeback-a-systematic-review-of-machine-learning-models-predicting-return-to-sport-in-athletes","From injury to comeback - A systematic review of machine learning models predicting return to sport in athletes","","Objective: This systematic review evaluates current research using machine learning to predict return-to-sport (RTS) decisions after athletic injuries. The review characterizes machine learning model types, commonly used predictive variables, and study-level methodological features and constraints across design, model development, evaluation, and reporting. Method: Searches were conducted on 1 May 2025 in Web of Science, PubMed, and SPORTDiscus (EBSCO), with PROBAST to assess risk of bias.",{"@graph":14,"@context":71},[15,34,54],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/from-injury-to-comeback-a-systematic-review-of-machine-learning-models-predicting-return-to-sport-in-athletes/447119/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":48,"encodingFormat":47,"isAccessibleForFree":49,"interactionStatistic":50},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/from-injury-to-comeback-a-systematic-review-of-machine-learning-models-predicting-return-to-sport-in-athletes/447119.png","ImageObject",300,407,{"name":42,"@type":43},"Indoniesian Boy","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-09-29",true,{"@type":51,"interactionType":52,"userInteractionCount":4},"InteractionCounter",{"@type":53},"ViewAction",{"@type":55,"mainEntity":56},"FAQPage",[57,63,67],{"name":58,"@type":59,"acceptedAnswer":60},"What is the main objective of the systematic review?","Question",{"text":61,"@type":62},"To systematically review how machine learning is applied to predict RTS decisions after athletic injuries, including model types, predictive variables, and study methodological characteristics and limitations.","Answer",{"name":64,"@type":59,"acceptedAnswer":65},"Which databases and date were used for the literature search?",{"text":66,"@type":62},"The review searched Web of Science, PubMed, and SPORTDiscus (EBSCO) on 1 May 2025.",{"name":68,"@type":59,"acceptedAnswer":69},"What did the review find about commonly used models and performance metrics?",{"text":70,"@type":62},"ROC AUC was the most reported performance metric (82% of included studies), and Random Forest was the most widely used algorithm (55%), showing the best predictive performance in four studies.","https://schema.org",{"og:url":32,"og:type":73,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":75,"canonical":32},"index,follow",{"doc_id":77,"site_id":7},447119,1790718869,{"code":4,"msg":80,"data":81},"success",[82,86,90,94,99,104,109,113,118,121,125],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":83,"show_sort_weight":84,"slug":85},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":87,"show_sort_weight":88,"slug":89},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":91,"show_sort_weight":92,"slug":93},"Exam",70,"exam",{"id":95,"doc_module":4,"doc_module_name":25,"category_name":96,"show_sort_weight":97,"slug":98},5,"Comic",60,"comic",{"id":100,"doc_module":4,"doc_module_name":25,"category_name":101,"show_sort_weight":102,"slug":103},6,"Technology",50,"technology",{"id":105,"doc_module":4,"doc_module_name":25,"category_name":106,"show_sort_weight":107,"slug":108},7,"Healthcare",40,"healthcare",{"id":110,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":111,"slug":112},8,30,"research-report",{"id":114,"doc_module":4,"doc_module_name":25,"category_name":115,"show_sort_weight":116,"slug":117},9,"Religion & Spirituality",20,"religion-spirituality",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":119,"show_sort_weight":116,"slug":120},"World Cup","world-cup",{"id":122,"doc_module":4,"doc_module_name":25,"category_name":123,"show_sort_weight":122,"slug":124},10,"Lifestyle","lifestyle",{"id":126,"doc_module":4,"doc_module_name":25,"category_name":127,"show_sort_weight":95,"slug":128},19,"General","general",{"code":4,"msg":80,"data":130},{"doc_id":77,"user_id":131,"nickname":42,"user_avatar":132,"doc_module":4,"category_id":110,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":133,"file_id":134,"file_url":135,"file_type":136,"file_size":137,"view_count":4,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":138,"language":139,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":12,"update_tm":78,"read_time":143},962090760608,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","From injury to comeback: A systematic review of machine learning models predicting return to sport in athletes  \nDIGITAL HEALTH Volume 12: 1–17 © The Author(s) 2026 Article reuse guidelines:  \n[sagepub.com/journals-permissions](sagepub.com/journals-permissions)[ ](sagepub.com/journals-permissions)[DOI: 10.1177/20552076251408523](DOI: 10.1177/20552076251408523)[ ](DOI: 10.1177/20552076251408523)[journals.sagepub.com/home/dhj](journals.sagepub.com/home/dhj)  \nJin Yuan 1 , Zhuojia Li2, Quanwen Zeng 1 , Jun Li 1 , Anjie Wang 1 , Yong Zhang 1 and Fei Xu3   \nAbstract  \nObjective: This study aims to systematically review the current literature on the application of machine learning to predict return-to-sport (RTS) decisions after athletic injuries. The review focuses on identifying the types of machine learning models used, the commonly used predictive variables, and the methodological characteristics and limitations between studies in terms of design, model development, evaluation, and reporting.  \nMethod: A comprehensive literature search was conducted on 1 May 2025 in three electronic databases: Web of Science, PubMed, and SPORTDiscus (EBSCO). Two independent reviewers selected the retrieved studies based on predefined inclusion and exclusion criteria. The Prediction Model Risk of Bias Assessment Tool (PROBAST) was used to assess the risk of bias in the included prognostic modeling studies.  \nResults: Of the 56 studies initially identified, 11 met the inclusion and exclusion criteria. Knee injuries were the most frequently modeled injury type for RTS decision-making (n = 4). The area under the receiver operating characteristic curve (ROC AUC) was the most commonly reported performance metric, presented in 82% of the included studies. Random Forest (RF) was the most widely used machine learning algorithm, applied in six studies (55%), and demonstrated the best predictive performance in four of them, with two studies reporting an AUC greater than 0.9. Some studies employed feature importance analysis or interpretability methods (e.g. SHAP) to identify key predictive variables. However, challenges remain in translating these models into clinical practice.  \nConclusions: Machine learning techniques demonstrate promising potential for predicting RTS in athletes. Nevertheless, substantial heterogeneity across studies—particularly in RTS definitions, feature selection, and model development which limits the generalizability and clinical applicability of current models.  \nKeywords  \nReturn to sport, machine learning, systematic review, sports injury recovery, prediction models  \nReceived: 8 August 2025; accepted: 2 December 2025  \nIntroduction  \nReturn to sport (RTS) represents one of the most critical and challenging phases in an athlete’s rehabilitation process, involving complex, multistakeholder decision-making that includes the athlete, medical staff, and coaching team. Due to the high heterogeneity in injury types and recovery trajectories, 1 coupled with the current lack of consensus on optimal functional recovery standards and objective physiological RTS criteria,2 RTS decisions are often fraught with uncertainty and debate. Anterior cruciate ligament (ACL) injury, one of the most prevalent types of sports-related injuries,3 remains a central focus in sports medicine research.4 However, reinjury rates following RTS after  \nACL reconstruction remain alarmingly high.5,6 Similarly, hamstring strain injury (HSI) carries a substantial risk of  \n1 School of Physical Education, Anhui Polytechnic University, Wuhu, Anhui, China  \n2Department of Physical Education, Harbin Institute of Technology, Harbin, Heilongjiang, China  \n3School of Traditional National Sports, Harbin Sport University, Harbin, Heilongjiang, China  \nCorresponding author:  \nFei Xu, School of Traditional National Sports, Harbin Sport University, 1 Dacheng Street, Nangang District, Harbin 150008, Heilongjiang, China.  \nEmail: [tiyu108108@163.com](tiyu108108@163.com)  \nCreative","cbCaiprU9AuL5xuw","https://ap.wps.com/l/cbCaiprU9AuL5xuw","pdf",1642864,17,"English","# Abstract\n## Objective\n## Method\n## Results\n## Conclusions\n# Introduction","[{\"question\":\"What is the main objective of the systematic review?\",\"answer\":\"To systematically review how machine learning is applied to predict RTS decisions after athletic injuries, including model types, predictive variables, and study methodological characteristics and limitations.\"},{\"question\":\"Which databases and date were used for the literature search?\",\"answer\":\"The review searched Web of Science, PubMed, and SPORTDiscus (EBSCO) on 1 May 2025.\"},{\"question\":\"What did the review find about commonly used models and performance metrics?\",\"answer\":\"ROC AUC was the most reported performance metric (82% of included studies), and Random Forest was the most widely used algorithm (55%), showing the best predictive performance in four studies.\"}]","From injury to comeback - A systematic review of machine learning models predicting return to sport in athletes | PDF",43]