As the level of athletic competition rises and health awareness grows, the physical condition of athletes is receiving more and more public attention. During high-intensity training and competitions, athletes inevitably sustain injuries and contract illnesses. One of the primary research topics in sports medicine is effectively and scientifically tracking athletes' injury risks and proactively identifying potential hazards. Therefore, to continuously enhance athletic performance, it is essential to establish a comprehensive, scientific athlete health management system. However, existing sports injury monitoring programs have drawbacks, such as lengthy cycles and high costs, which make it difficult to implement precise injury monitoring activities widely. This study combines wearable monitoring devices with machine learning algorithms to create an analytical framework based on track and field athletes' movement patterns. Simultaneously, wearable devices map movement displacement curves and monitor the three-dimensional biomechanics of athletes' lower-body movements. The goal is to develop a high-precision, low-cost system for monitoring athletes' injury probabilities. Experimental results demonstrate the system's superior computational efficiency and advantages in testing and training time. The system delivers high testing accuracy at a low cost and provides timely preventive recommendations for athletes, making it suitable for widespread adoption.

Machine Learning Algorithms, Wearable Devices, Health Monitoring, Sports Injury Assessment