Intelligent Real-Time Biomechanical Monitoring System for Injury Prevention in Endurance Athletes: A Multi-Center Validation Study

Abstract

Background: Endurance sports-related injuries represent a significant burden on athletes’ health and performance. Existing injury prevention strategies often lack personalization and real-time feedback, limiting their effectiveness. This study addresses the critical need for a dynamic, data-driven approach to mitigate injury risk. Methods: We developed and validated an intelligent real-time biomechanical monitoring system that integrates data from wearable inertial measurement unit (IMU) sensors with a machine learning-based predictive model. The system was designed to identify high-risk biomechanical patterns and provide personalized training recommendations to endurance athletes. Implementation: A multi-center, randomized controlled trial was conducted involving 156 endurance athletes (runners and cyclists) from three different training centers. The experimental group (n=78) received real-time feedback and adaptive training plans from the system, while the control group (n=78) followed standard training protocols. Results: The system demonstrated high accuracy (87.3% ± 2.1%) and sensitivity (89.2% ± 1.8%) in predicting injury risk. Over a 6-month follow-up period, the experimental group exhibited a significantly lower injury incidence rate (12.8%) compared to the control group (28.2%), representing a 54.6% relative risk reduction (p < 0.001). Key biomechanical parameters, such as knee valgus and ground reaction force, were significantly improved in the experimental group. Conclusion: The integration of wearable sensors and machine learning provides a powerful tool for real-time injury risk assessment and personalized prevention in endurance athletes. This intelligent system offers a scalable and effective solution to enhance athlete safety and optimize training, marking a significant advancement in the field of sports science and digital health.