I-Corps: Translation Potential of Real-Time Injury Prediction in Sports Using Machine Learning and Biomechanical Data

This I-Corps project is based on the development of an injury risk prediction tool to prevent non-contact injuries in high-intensity sports such as soccer. Non-contact injuries, such as anterior cruciate ligament (ACL) tears, are a leading cause of time-loss injuries in collegiate and professional athletes and often have long-term physical and financial impacts. Traditional approaches to injury prevention rely on historical or post-injury data and are often inadequate due to limited customization and delayed response. This technology addresses these limitations by providing real-time, personalized risk assessments using wearable technology and advanced analytics. The solution may reduce injury rates, improve player well-being, enable longer athletic careers, and provide cost savings for teams, universities, and insurers. This technology may streamline data analysis, enhance communication among coaching staff, and offer an actionable dashboard for decision-making, leading to better training plans and fewer injuries.

This I-Corps project utilizes experiential learning coupled with a first-hand investigation of the industry ecosystem to assess the translation potential of a machine learning-based platform that integrates biomechanical, physiological, and performance data to detect and prevent injuries in athletes. The core technology includes statistical and machine learning models trained on real-world movement and workload data from athletes, enabling the system to generate real-time injury risk alerts. Currently, traditional methods such as acute to chronic workload ratios are limited in scope and accuracy. This technology continuously processes multimodal sensor inputs and delivers individualized, actionable insights. The platform leverages live data streams from global positioning systems (GPS), force plates, and subjective fatigue reports, and applies validated algorithms to identify early signs of musculoskeletal overload. Research has shown promising results in both lab and field environments. This solution is a scalable tool that can be embedded in existing athlete monitoring systems to help coaches, trainers, and medical staff take proactive steps in injury prevention. In addition, this technology may allow the evaluation of how injury risks are identified and managed in sports.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

Award Number: 2534759
Principal Investigator: Payam Parsa
Funds Obligated: $50,000
State: CA