Effective injury forecasting in soccer with GPS training data and machine learning

• DOI: 10.1371/journal.pone.0201264
• Publication Date: 2018-07-25T13:44:01Z
• Authors: Alessio Rossi; Luca Pappalardo; Paolo Cintia; F. Marcello Iaia; Javier Fernàndez; Daniel Medina
• Keywords: Adult; Male; FOS: Computer and information sciences; Soccer Analytics; Science; Machine Learning (stat.ML); Athletic Performance; Sports Medicine; Statistics - Applications; Machine Learning; Young Adult; 03 medical and health sciences; 0302 clinical medicine; Statistics - Machine Learning; Risk Factors; Adult; Athletic Injuries; Athletic Performance; Exercise; Geographic Information Systems; Humans; Male; Risk Factors; Soccer; Sports Medicine; Young Adult; Machine Learning; Soccer; Injury Forecasting; H.2.8; Humans; Applications (stat.AP); Injury Prediction; Exercise; Q; Data Science; R; Sports Science; 62-07; Athletic Injuries; Geographic Information Systems; Medicine; Applied Data Science; Sports Analytics; Research Article

Injuries have a great impact on professional soccer, due to their large influence team performance and the considerable costs of rehabilitation for players. Existing studies in literature provide just preliminary understanding which factors mostly affect injury risk, while an evaluation potential statistical models forecasting injuries is still missing. In this paper, we propose multi-dimensional approach soccer that based GPS measurements machine learning. By using tracking technology, collect data describing training workload players club during season. We then construct forecaster show it both accurate interpretable by providing set case interest practitioners. Our opens novel perspective prevention, simple practical rules evaluating interpreting complex relations between risk soccer.