Machine learning approaches to injury risk prediction in sport: a scoping review with evidence synthesis

In plain language

This scoping review examined the application of various machine learning (ML) models for predicting sports-related injuries. While some studies reported strong predictive performance, the clinical utility of these models was often limited due to factors such as wide prediction windows or broad definitions of injury. The overall effectiveness of ML in this area is hampered by small datasets and significant methodological inconsistencies across studies, including variations in cohort sizes and the definitions of injuries and dependent variables. These issues were identified as common challenges throughout the reviewed literature.

Key takeaways

Machine learning models are used to predict sports-related injuries.
Despite some strong predictive performance, the clinical usefulness of these models is often limited.
Limitations include wide prediction windows and broad definitions of injury.
Small datasets and methodological inconsistencies hinder the efficacy of machine learning in this field.
These challenges were prevalent across the studies examined in the review.

Why it matters

Understanding the current limitations of machine learning in sports injury prediction is crucial for researchers and developers. It highlights the need for more robust data, standardised methodologies, and clinically relevant outcome measures to create truly effective prevention tools.

Commercialisation angle

The abstract does not indicate a direct application pathway for a specific technology. Instead, it identifies significant challenges, such as small datasets and methodological inconsistencies, that currently limit the clinical utility of machine learning models for sports injury prediction. Addressing these issues is essential for future development of commercially viable injury prevention tools.

AI-generated from the published abstract. Always read the original work before citing.

Abstract

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.

Research topics

Sports injuries and prevention
Injury Epidemiology and Prevention
Cardiovascular Effects of Exercise

Discussion

Discuss this research

Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.

No discussion yet. Open the first thread.

New to MARATTO™? Create a free account.