Integration of biomechanical and psychophysiological data into a model for predicting athletes' injuries using lstm networks

Modern high-performance sports place increasing demands on athletes’ physical, technical, and psychological preparedness, intensifying the challenge of sports injuries and overtraining. Traditional monitoring methods often lack predictive precision, hindering timely identification of injury risks.This study develops and compares three LSTM-based models for predicting injury risk in runners: one leveraging biomechanical parameters, another using psychophysiological indicators, and an integrated model combining both. Models were developed using data from digital twins of two professional runners, incorporating physiological (heart rate, heart rate variability, lactate levels), biomechanical (joint angles, step symmetry, accelerations), and psychophysiological (sleep quality, fatigue, cognitive responses) metrics. The integrated model demonstrated superior performance, achieving an Accuracy of 0.89, F1-score of 0.87, and AUC-ROC of 0.91. SHAP analysis identified key predictors, including step symmetry, tibial shock, reduced heart rate variability, sleep quality decline, and subjective fatigue. These findings highlight the enhanced predictive power of integrating diverse data types, offering a robust foundation for personalized injury prevention systems in sports.

1. Kakouris N. Yener N, Fong DTR. A systematic review of running-related musculoskeletal injuries in runners. Journal of Sport and Health Science. 2021;10(5):513–522. DOI: 10.1016/j.jshs.2021.04.001

2. Lopes AD, Hespanhol Junior LC. Yeung SS, Costa LOP. What are the Main Running-Related Musculoskeletal Injuries?: A Systematic Review. Sports Medicine. 2012;42(10):P. 891–905. DOI: 10.1007/BF03262301

3. Burke A, Dillon S, O’Connor S, Whyte EF, Gore S, Moran KA. Aetiological Factors of Running-Related Injuries: A 12 Month Prospective “Running Injury Surveillance Centre” (RISC) Study. Sports Medicine – Open. 2023;9(1):46. DOI: 10.1186/s40798-023-00589-1

4. Amendolara A, Pfister D, Settelmayer M, Shah M, Wu V, Donnelly S, et al. An Overview of Machine Learning Applications in Sports Injury Prediction. Cureus. 2023;15(9):e46170. DOI: 10.7759/cureus.46170

5. Leckey C, van Dyk N, Doherty C, Lawlor A, Delahunt E. Machine learning approaches to injury risk prediction in sport: a scoping review with evidence synthesis. British Journal of Sports Medicine. 2025;59(7):491–500. DOI: 10.1136/bjsports-2024-108576

6. Ye X. Huang Y, Bai Z, Wang Y. A novel approach for sports injury risk prediction: based on time-series image encoding and deep learning. Frontiers in Physiology. 2023;14:1174525. DOI: 10.3389/fphys.2023.1174525

7. Solonets AV, Snarsky AS. Application of artificial intelligence for predicting injury risk in athletes: an approach using recurrent neural networks. System analysis and applied information science. 2025;2:11–16. (In Russ.). DOI: 10.21122/2309-4923-2025-2-11-16

8. Majumdar A, Bakirov R, Hodges D, Scott S, Rees T. Machine Learning for Understanding and Predicting Injuries in Football. Sports Medicine – Open. 2022;8(1):73. DOI: 10.1186/s40798-022-00465-4

9. Lundberg S, Lee S. A Unified Approach to Interpreting Model Predictions. arXiv. 2017;arXiv:1705.07874v2. DOI: 10.48550/arXiv.1705.07874

10. Hou J, Tian Z. Application of recurrent neural network in predicting athletes' sports achievement. The Journal of Supercomputing. 2022;78(1):5507–5525. DOI: 10.1007/s11227-021-04082-y

11. Bahr R, Krosshaug T. Understanding injury mechanisms: A key component of preventing injuries in sport. British Journal of Sports Medicine. 2005;39(6):324–329. DOI: 10.1136/bjsm.2005.018341