{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T18:58:53Z","timestamp":1785437933315,"version":"3.56.0"},"reference-count":40,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T00:00:00Z","timestamp":1785369600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:p>Adolescent athletes (aged 13\u201318 years) face significantly elevated lower-limb injury risk compared to adult populations due to immature neuromuscular control, while existing injury risk assessment methods are broadly limited by single-modal reliance, insufficient model interpretability, and a lack of dedicated research targeting youth populations. This study proposes an interpretable multimodal machine learning framework that integrates three data modalities\u2014kinematics, physiology, and training load\u2014via feature-level concatenation, based on a cross-sectional multimodal dataset of 320 fully anonymised adolescent athletes comprising 12 feature variables acquired under standardized protocols using internationally recognized instruments, including Vicon optical motion capture, AMTI force platforms, Polar H10 heart rate monitors, Supersonic Imagine Aixplorer ultrasound elastography, and Catapult GPS trackers. Through 5-fold stratified cross-validation, the comprehensive performance of five traditional and five modern\/deep machine learning models was systematically compared in a binary injury risk stratification task. Experimental results demonstrate that logistic regression achieved the best overall performance [Accuracy = 86.9%, AUC-ROC = 0.965, F1 = 0.866, Matthews Correlation Coefficient (MCC) = 0.742]. Dual interpretability analysis was further conducted on the optimal model using a SHapley Additive exPlanations (SHAP) linear explainer and a Local Interpretable Model-Agnostic Explanations (LIME) local explainer; both methods consistently identified peak hip adduction angle (mean |SHAP| = 2.208), ankle dorsiflexion range of motion (1.426), and dynamic knee valgus angle (1.359) as the most critical injury risk predictors (Spearman \u03c1 = 0.93), in high agreement with established biomechanical findings in sports medicine. An ablation analysis of modality contributions demonstrated that the tri-modal integration achieved a substantive AUC gain over single-modality configurations, supporting the value of multimodal feature integration. We note explicitly that the binary risk label was derived from a clinically-informed weighted composite of the input features rather than from prospective injury follow-up; the framework therefore performs risk stratification with respect to this composite, and validation against true prospective injury outcomes remains an important next step. This study provides an interpretable technical framework for standardized, digitized, and stratified injury risk assessment in adolescent athletes, with important potential for clinical translation and sports injury prevention practice.<\/jats:p>","DOI":"10.3389\/fmed.2026.1848064","type":"journal-article","created":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T18:06:22Z","timestamp":1785434782000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Interpretable multimodal machine learning for injury risk stratification in adolescent athletes: integrating kinematic, physiological, and load data with SHAP\/LIME explainability"],"prefix":"10.3389","volume":"13","author":[{"given":"Linzhen","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Physical Education, Hunan University of Technology, Zhuzhou","place":["Hunan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Sports Science and Physical Education, Nanjing Normal University","place":["Nanjing, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongbing","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Sports Science and Physical Education, Nanjing Normal University","place":["Nanjing, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linjun","family":"Liu","sequence":"additional","affiliation":[{"name":"Faculty of Pharmacy, Lincoln University College, Petaling Jaya","place":["Selangor, Malaysia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianshi","family":"Wei","sequence":"additional","affiliation":[{"name":"Department of Big Data, Warsaw School of Economics","place":["Warsaw, Poland"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,30]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1136\/bjsports-2014-094322","article-title":"Protecting the health of the athlete: the challenge we face","volume":"49","author":"Verhagen","year":"2015","journal-title":"Br J Sports Med"},{"key":"B2","doi-asserted-by":"publisher","first-page":"492","DOI":"10.1177\/0363546504269591","article-title":"Biomechanical measures of neuromuscular control and valgus loading of the knee predict anterior cruciate ligament injury risk in female athletes","volume":"33","author":"Hewett","year":"2005","journal-title":"Am J Sports Med"},{"key":"B3","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1177\/0363546506293899","article-title":"Mechanisms of anterior cruciate ligament injury in basketball: video analysis of 39 cases","volume":"35","author":"Krosshaug","year":"2007","journal-title":"Am J Sports Med"},{"key":"B4","first-page":"510","article-title":"The effect of a movement control exercise programme on injury risk score and the biomechanics of a landing task","volume":"41","author":"Dempsey","year":"2007","journal-title":"Br J Sports Med"},{"key":"B5","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1136\/bjsports-2015-095788","article-title":"The training-injury prevention paradox: should athletes be training smarter and harder?","volume":"50","author":"Gabbett","year":"2016","journal-title":"Br J Sports Med"},{"key":"B6","doi-asserted-by":"crossref","first-page":"1043","DOI":"10.1161\/01.CIR.93.5.1043","article-title":"Heart rate variability: standards of measurement, physiological interpretation and clinical use","volume":"93","year":"1996","journal-title":"Circulation"},{"key":"B7","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1097\/JSM.0b013e3180592a48","article-title":"A dynamic model of etiology in sport injury: the recursive nature of risk and causation","volume":"17","author":"Meeuwisse","year":"2007","journal-title":"Clin J Sport Med"},{"key":"B8","doi-asserted-by":"publisher","first-page":"1309","DOI":"10.1136\/bjsports-2015-095850","article-title":"Complex systems approach for sports injuries: moving from risk factor identification to injury pattern recognition","volume":"50","author":"Bittencourt","year":"2016","journal-title":"Br J Sports Med"},{"key":"B9","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1613\/jair.1.12228","article-title":"A survey on the explainability of supervised machine learning","volume":"70","author":"Burkart","year":"2021","journal-title":"J Artif Intell Res"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3561048","article-title":"Explainable AI (XAI): core ideas, techniques, and solutions","volume":"55","author":"Dwivedi","year":"2023","journal-title":"ACM Comput Surv"},{"key":"B11","doi-asserted-by":"publisher","first-page":"1135","DOI":"10.1145\/2939672.2939778","article-title":"\u201cWhy Should I Trust You?","author":"Ribeiro","year":"2016"},{"key":"B12","doi-asserted-by":"publisher","first-page":"2400304","DOI":"10.1002\/aisy.202400304","article-title":"A perspective on explainable artificial intelligence methods: SHAP and LIME","volume":"7","author":"Salih","year":"2025","journal-title":"Adv Intell Syst"},{"key":"B13","doi-asserted-by":"publisher","first-page":"e70056","DOI":"10.1111\/cts.70056","article-title":"Practical guide to SHAP analysis: explaining supervised machine learning model predictions in drug development","volume":"17","author":"Ponce-Bobadilla","year":"2024","journal-title":"Clin Transl Sci"},{"key":"B14","doi-asserted-by":"publisher","first-page":"785","DOI":"10.1145\/2939672.2939785","article-title":"XGBoost: a scalable tree boosting system","author":"Chen","year":"2016","journal-title":"Proc. 22nd ACM SIGKDD int. conf. knowledge discovery and data mining."},{"key":"B15","first-page":"3146","article-title":"LightGBM: a highly efficient gradient boosting decision tree","volume-title":"Advances in Neural Information Processing Systems","author":"Ke","year":"2017"},{"key":"B16","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"B17","doi-asserted-by":"publisher","first-page":"459","DOI":"10.6000\/1927-5129.2017.13.76","article-title":"Classification techniques in machine learning: applications and issues","volume":"13","author":"Soofi","year":"2017","journal-title":"J Basic Appl Sci"},{"key":"B18","first-page":"1063","article-title":"Analysis of a random forests model","volume":"13","author":"Biau","year":"2012","journal-title":"J Mach Learn Res"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1937","DOI":"10.1007\/s10462-020-09896-5","article-title":"A comparative analysis of gradient boosting algorithms","volume":"54","author":"Bent\u00e9jac","year":"2021","journal-title":"Artif Intell Rev"},{"key":"B20","doi-asserted-by":"publisher","first-page":"45029","DOI":"10.1038\/s41598-025-28786-w","article-title":"A dynamic weighted ensemble learning framework for cardiovascular risk prediction in type 2 diabetes: a comparative study with SHAP-based interpretability","volume":"15","author":"Yuan","year":"2025","journal-title":"Sci Rep"},{"key":"B21","first-page":"4765","article-title":"A unified approach to interpreting model predictions","volume-title":"Advances in Neural Information Processing Systems","author":"Lundberg","year":"2017"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.03888","author":"Lundberg","year":"2019","journal-title":"Consistent Individualized Feature Attribution for Tree Ensembles"},{"key":"B23","first-page":"6638","article-title":"CatBoost: unbiased boosting with categorical features","volume-title":"Advances in Neural Information Processing Systems","author":"Prokhorenkova","year":"2018"},{"key":"B24","doi-asserted-by":"publisher","first-page":"44471","DOI":"10.1038\/srep44471","article-title":"Heart rate variability indicates emotional value during pro-social economic laboratory decisions with large external validity","volume":"7","author":"Fooken","year":"2017","journal-title":"Sci Rep"},{"key":"B25","doi-asserted-by":"publisher","first-page":"108727","DOI":"10.1016\/j.biopsycho.2023.108727","article-title":"Change in heart rate variability with increasing time-on-task as a marker for mental fatigue: a systematic review","volume":"185","author":"Csath\u00f3","year":"2024","journal-title":"Biol Psychol"},{"key":"B26","doi-asserted-by":"publisher","first-page":"594880","DOI":"10.3389\/fnins.2020.594880","article-title":"A critical review of ultra-short-term heart rate variability norms research","volume":"14","author":"Shaffer","year":"2020","journal-title":"Front Neurosci"},{"key":"B27","doi-asserted-by":"publisher","first-page":"990235","DOI":"10.3389\/fpubh.2022.990235","article-title":"A measurement method for mental health based on dynamic multimodal feature recognition","volume":"10","author":"Xu","year":"2022","journal-title":"Front Public Health"},{"key":"B28","doi-asserted-by":"publisher","first-page":"8943","DOI":"10.1038\/s41598-025-92399-6","article-title":"Multimodal machine learning for deception detection using behavioral and physiological data","volume":"15","author":"Joshi","year":"2025","journal-title":"Sci Rep"},{"key":"B29","first-page":"5998","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"key":"B30","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1007\/s44443-025-00401-y","article-title":"MSTDP: a multi-scale temporal deep learning framework for just-in-time software defect prediction with cross-attention fusion","volume":"38","author":"Liu","year":"2026","journal-title":"J King Saud Univ Comput Inf Sci"},{"key":"B31","doi-asserted-by":"publisher","first-page":"1997","DOI":"10.1109\/TCE.2025.3634160","article-title":"SwarmSense-DNN: a trustworthy and decentralized neural framework for proactive anomaly defense in consumer IoT","volume":"72","author":"Yang","year":"2026","journal-title":"IEEE Trans Consum Electron."},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2509.05913","author":"Rahman","year":"2025","journal-title":"A Fine-Grained Attention and Geometric Correspondence Model for Musculoskeletal Risk Classification in Athletes Using Multimodal Visual and Skeletal Features"},{"key":"B33","doi-asserted-by":"crossref","DOI":"10.1145\/3307339.3343255","article-title":"Explanation of machine learning models using improved Shapley additive explanation","volume-title":"Proc. 10th ACM int. conf. bioinformatics, computational biology and health informatics.","author":"Nohara","year":"2019"},{"key":"B34","doi-asserted-by":"publisher","first-page":"1525606","DOI":"10.3389\/fpsyg.2025.1525606","article-title":"Predicting honest behavior based on Eysenck personality traits and gender: an explainable machine learning study using SHAP analysis","volume":"16","author":"Meng","year":"2025","journal-title":"Front Psychol"},{"key":"B35","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1016\/j.tbs.2022.07.003","article-title":"Predicting the travel mode choice with interpretable machine learning techniques: a comparative study","volume":"29","author":"Tamim Kashifi","year":"2022","journal-title":"Travel Behav Soc"},{"key":"B36","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1515\/ijb-2019-0061","article-title":"A machine learning-based approach for estimating and testing associations with multivariate outcomes","volume":"17","author":"Benkeser","year":"2021","journal-title":"Int J Biostat"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-025-02240-7","article-title":"The structure-preserving spectral graph neural network for dual kinase inhibitors and synergy scoring in gastric cancer","author":"Zhang","year":"2025","journal-title":"npj Digit Med"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2026.3675966","article-title":"Consumer-electronics-oriented safe interaction-aware motion planning for ramp driving with perception uncertainty quantification","author":"Tian","year":"2026","journal-title":"IEEE Trans Consum Electron"},{"key":"B39","first-page":"3323","article-title":"Large-scale linear support vector regression","volume":"13","author":"Ho","year":"2012","journal-title":"J Mach Learn Res"},{"key":"B40","doi-asserted-by":"publisher","first-page":"1100","DOI":"10.1177\/1745691617693393","article-title":"Choosing prediction over explanation in psychology: lessons from machine learning","volume":"12","author":"Yarkoni","year":"2017","journal-title":"Perspect Psychol Sci"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1848064\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T18:06:24Z","timestamp":1785434784000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1848064\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,30]]},"references-count":40,"alternative-id":["10.3389\/fmed.2026.1848064"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1848064","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,30]]},"article-number":"1848064"}}