Informed Injury Prediction in Elite Football: Decision Theory meets Machine Learning

Injuries in elite sports disrupt team performance, shorten careers, and incur significant financial costs, highlighting the critical need for accurate predictions to inform optimal decisions that effectively prevent injuries. Existing approaches to injury prediction fail to account for cumulative risk, overlook injury severity, lack reliable probability calibration, and omit statistically guided decision thresholds. Here, we present a novel injury prediction framework integrating risk accumulation via survival analysis with machine learning, probability beta calibration, and statistical decision theory. Using a unique dataset spanning four seasons from FC Barcelonas womens team, we demonstrate that our framework outperforms standard classifiers, yielding superior discrimination ability. Our framework identifies fatigue-related measures as key injury predictors and incorporates flexible thresholds based on match importance and decision-maker certainty, improving player availability. Scalable and transferable to other sports, this framework bridges academic research and practical deployment, empowering sports organizations to optimize player performance and long-term outcomes.