| AI-POWERED ASSESSMENT FOR ACL INJURY RISK AND PREVENTION IN ATHLETES |
| Paper ID : 1767-SPORTCONGRESS |
| Authors |
|
Sina Lagzi * 1 Student Research Committee, Ahvaz Jundishapur University of Medical Sciences, Ahvaz, Iran
2 Rehabilitation Research Center, Ahvaz Jundishapur University of Medical Sciences, Ahvaz, Iran |
| Abstract |
| Introduction: Anterior cruciate ligament (ACL) injury is one of the most common and serious injuries among athletes, often resulting in prolonged recovery and a high risk of re-injury. Effective prevention is therefore essential to preserve athletic performance and long-term joint health. Preventing ACL injuries requires a detailed understanding of biomechanical risk factors, including dynamic knee valgus, poor neuromuscular control, and asymmetrical loading during jumping or cutting movements. Recently, artificial intelligence (AI) has emerged as a promising tool for identifying these risk factors more accurately and efficiently. Methods: This literature review examined studies applying AI—particularly machine learning and computer vision—to ACL injury prevention. Machine learning models analyze large datasets of biomechanical or sensor-based information to identify movement patterns associated with increased injury risk, while computer vision techniques extract visual features directly from video recordings to detect risky movement mechanics. These approaches can be used independently or combined to provide a comprehensive framework for objective movement screening and predictive modeling in both clinical and athletic settings. Results: Recent studies indicate that AI algorithms can automatically classify movement quality, estimate joint angles, and detect high-risk kinematics using simple video recordings or wearable sensors. These technologies allow large-scale screening of athletes without the need for expensive laboratory equipment, offering potential for early detection and targeted preventive interventions. However, challenges remain, including standardizing datasets, ensuring model interpretability, and validating algorithms across diverse populations and sports. Conclusion: AI has significant potential to advance ACL injury prevention by making biomechanical assessment more accessible, objective, and data-driven. Future research should focus on developing transparent, generalizable models and integrating AI-based assessment into real-world sports environments to enable individualized risk monitoring and optimize training programs. |
| Keywords |
| Anterior Cruciate Ligament, Injury Prevention, Artificial Intelligence, Machine Learning, Computer Vision |
| Status: Abstract Accepted (Poster Presentation) |
