Prevention and health care intervention of common injuries in long-distance running for college teachers.

Abstract

Background: Long-distance running is a widely practiced exercise among college faculty due to its significant benefits for maintaining physical health and overall well-being. However, frequent participation can lead to various injuries that negatively impact both health and professional performance, revealing limitations in existing injury prevention strategies.

Objective: This study aims to develop an intelligent injury prevention and healthcare intervention model to minimize common long-distance running injuries among college teachers.

Methods: A Machine Learning Prevention and Healthcare Intervention Method (ML-PHIM) was proposed. The model integrates a Wireless Sensor Network (WSN) for real-time physiological and gait data collection, Principal Component Analysis (PCA) for feature extraction, and a Support Vector Machine (SVM) for classifying injury types and severity levels. The system was implemented and tested in MATLAB using the Gait and Injury Monitoring Dataset.

Results: Simulation results demonstrated that ML-PHIM achieved an injury classification accuracy of 94%, with 97% precision and 98% recall, outperforming conventional injury detection methods.

Conclusion: The proposed ML-PHIM provides an effective and personalized solution for injury prevention and health management in long-distance running among college faculty. By reducing recovery time and enhancing physical well-being, this approach promotes healthier lifestyles and contributes to improved academic productivity.