Machine learning approaches to injury risk prediction in sport: a scoping review with evidence synthesis
A variety of different ML models have been applied to the prediction of sports-related injuries. While several studies report strong predictive performance, their clinical utility can be limited, with wide prediction windows or broad definitions of injury. The efficacy of ML is hampered by small datasets and numerous methodological heterogeneities (cohort sizes, definition of injury and dependent variables), which were common across the reviewed studies.
Authors
- Eamonn Delahunt (ORCID: https://orcid.org/0000-0001-5449-5932)
- Nicol van Dyk (ORCID: https://orcid.org/0000-0002-0724-5997)
- Aonghus Lawlor (ORCID: https://orcid.org/0000-0002-6160-4639)
- Cailbhe Doherty (ORCID: https://orcid.org/0000-0002-5284-856X)
- Christopher Leckey (ORCID: https://orcid.org/0000-0001-5614-3252)
Institutions
- University College Dublin (IE)
- Irish Rugby Football Union (IE)
- University of Pretoria (ZA)
Publication Details
- Journal
- British Journal of Sports Medicine
- Published
- 2024-11-29
- DOI
- https://doi.org/10.1136/bjsports-2024-108576
- Citations
- 53
- Primary Topic
- Sports injuries and prevention
- Type
- article
- Field-Weighted Citation Impact
- 25.32
Funders
- Irish Research Council