Journal DOI 10.68956/journal.human-performance-futures

Creative Commons source reading · Movement biomechanics and kinetics

Machine learning applications in sport: a scoping review

Antonia Cattle; Kathryn Johnston; Alexander B. T. McAuley; Adam Kelly; Joseph Baker

Originally published in Front Psychol · 2026-05-25

From the article

Selected source text. JournalOS removes markup and shortens excerpts where indicated. The full article provides the complete context.

Abstract

Machine learning (ML) applications continue to grow in popularity across the sport industry, offering new opportunities for performance enhancement, injury prevention, and decision-making. The present scoping review examined the landscape of ML applications in sport by analyzing 270 peer-reviewed studies published between 2002 and 2024. ML was applied across 12 broad subject areas, with computer science, biomechanics, and sport psychology emerging as the most common domains of application. Key applications included action recognition, injury prediction/prevention, and athlete selection/talent identification. While ML models have demonstrated promising accuracy, their practical utility was often limited by issues of data quality, interpretability, and accessibility for end users such as athletes, coaches, and sport interest-holders.…

Results

Initially, our search yielded 5,419 articles. After duplicate removal, 5,052 articles remained for title and abstract screening. After the first round of screening 666 articles remained to be assessed for full text eligibility. Once all articles were assessed, conflicts were resolved, and grey areas and tentative inclusions were discussed, 270 articles met our final inclusion criteria. A summary of this process is presented in Figure 1 and our article database can be viewed via this link: http://bit.ly/44Jyk8X. A total of 44 countries were represented in these articles, with China having the largest number of studies (n = 33), representing 12.22%, followed by the United States of America (n = 31; 11.48%), Germany (n = 27; 10%), Australia (n = 26; 9.63%), and Canada (n = 15; 5.55%). When looking at the types of samples used across the…

Discussion

This scoping review aimed to summarize the evolving application of ML in sport and examine its potential value for athletes, coaches, and sport interest-holders. A secondary objective was to identify key research areas, highlight gaps in the literature, and explore the challenges and opportunities associated with ML technologies. The findings from the 270 included articles reflect a broad and growing interest in ML applications across diverse sporting contexts. The following sections synthesize prominent and emerging research areas, discuss implications for practice and identify priorities for future research.

Editorial reading guide

  • How was movement measured, and what error or calibration information is reported?
  • Can the finding transfer from the tested task and population to the intended sport setting?