Background Artificial Intelligence (AI), particularly machine learning, is being increasingly implemented in sports science to enhance sports performance and prevent injuries during sports participation. Machine learning methods, such as supervised learning, deep learning, and ensemble approaches, are widely used to predict outcomes, assess biomechanics, evaluate tactics, and monitor training loads. Objectives This study aims to synthesise existing evidence on the application of artificial intelligence in sports performance and injury. With a focus on the methodological approach, classify gaps for future research studies. Method: for this study, databases like PubMed, Science Direct, Web of Science, and IEEE Xplore, following PRISMA guidelines, included a number of peer-reviewed articles employing Machine learning techniques in sports performance and injury prevention, which were included and analysed for methodological applications and reported outcomes. The systematic review highlights that machine learning, mainly supervised learning, deep learning, and ensemble methods, dominate current studies. AI indicates a high level of predictive accuracy in performance analysis (e.g., outcome prediction) and injury prevention (e.g detecting risky movements). Sports performance metrics usually reported include precision, recall, accuracy, and F-score. Conclusion Artificial Intelligence, particularly machine learning methods, embraces significant potential in improving sports performance and preventing sports injuries. However, improvements in methodological parts, large sample studies, and frameworks of ethics are essential to make sure reliable, transparent, and responsible integration of artificial intelligence in sports activities and practices.
Wilson et al. (Fri,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: