Related Experiment Video
Updated: Jul 1, 2026
06:52
An Inertial Measurement Unit Based Method to Estimate Hip and Knee Joint Kinematics in Team Sport Athletes on the Field
Published on: May 26, 2020
Machine learning applications in sport: a scoping review
Antonia Cattle1, Kathryn Johnston1, Alexander B T McAuley2
1Tanenbaum Institute for Science in Sport, University of Toronto, Toronto, ON, Canada.
Frontiers in Psychology
|June 10, 2026
Summary
Machine learning (ML) in sports enhances performance and prevents injuries. However, practical use is limited by data issues, emphasizing ML should support, not replace, human expertise for better athlete experiences.
Area of Science:
- Sports Science
- Computer Science
- Data Analytics
Background:
- Machine learning (ML) is increasingly utilized in sports for performance, injury prevention, and decision-making.
- A scoping review analyzed 270 studies from 2002-2024 on ML applications in the sport industry.
Purpose of the Study:
- To examine the landscape of machine learning applications in sports.
- To identify key domains and applications of ML in athletic contexts.
- To assess the practical utility and limitations of ML in sports.
Main Methods:
- Scoping review methodology.
- Analysis of 270 peer-reviewed studies.
- Categorization of ML applications across 12 subject areas.
Main Results:
- Computer science, biomechanics, and sport psychology are dominant application domains.
- Key applications include action recognition, injury prediction, and talent identification.
- ML models show promise but face challenges in data quality, interpretability, and accessibility.
Conclusions:
- ML integration in sports offers significant potential for enhancement.
- Practical usability is hindered by data quality, interpretability, and accessibility issues.
- ML should augment human expertise to improve sport and athlete development, not replace it.
