Machine Learning in Physical Education, Sports, and Recreation: Opportunities, Challenges, and Ethical Considerations – A Systematic Review

Introduction: Machine learning, a subfield of artificial intelligence, is rapidly transforming the landscape of sports science. It enables more informed decision-making across various sectors, including healthcare, agriculture, and, notably, sports. This study aims to investigate how machine learning can improve athletic performance, injury prevention, and coaching efficacy. Methods: This systematic review utilized a comprehensive search strategy across 510 articles to identify studies focused on machine learning (ML) in the fields of physical education, sports, and recreation. A total of 36 studies met the inclusion criteria and were thoroughly reviewed for their relevance to the outcomes within the search scope. The search commenced in January 2025 and continued through July 2025. It covered several databases, including PubMed, Scopus, Web of Science, ScienceDirect, and the Cochrane Library. The focus was on publications from 2015 to 2025, using keywords such as “artificial intelligence,” “athletic performance,” “coaching efficacy,” “injury prevention,” and “machine learning.” Results: The results demonstrate that machine learning significantly enhances athletic performance, injury prevention, and coaching effectiveness. It facilitates tailored training and data-driven decision-making, which lead to improved skill development and rehabilitation outcomes. In the realm of physical education, machine learning supports personalized instruction that increases student engagement. However, challenges remain, including issues with data integrity, high computing costs, and a shortage of expertise. Ethical concerns—particularly related to privacy, bias, and transparency—require immediate attention. While machine learning has the potential to transform both sports and education, it must be implemented appropriately to ensure fairness, accuracy, and accessibility for all users. Conclusions: The outcome indicates that machine learning enhances physical education and athletics by improving performance analysis, reducing injury risk, and enabling coaches to personalize training. Although there are challenges such as data quality and ethical concerns, the effective use of machine learning can significantly support athlete development. The combination of machine learning with coaching and educational methods fosters inclusive, data-driven strategies that improve skill acquisition, ensure safety, and promote the long-term well-being of athletes.