Application of Artificial Intelligence for Predicting Sports Injuries and Customizing Personalized Prevention...

Area of Science:

• Sports Medicine
• Data Science
• Biostatistics

Background:

• Sports injuries present a significant challenge for athletes.
• Artificial intelligence (AI), encompassing machine learning (ML) and deep learning (DL), is increasingly utilized for injury prediction and prevention.
• Contemporary research focuses on developing AI-driven predictive models and personalized prevention strategies.

Purpose of the Study:

• To conduct a scoping review of current trends in AI applications for sports injury prediction.
• To critically evaluate AI methodologies used in sports injury research.
• To identify future research directions for AI in athletic injury prevention.

Main Methods:

• Systematic search of five electronic databases (PubMed, Web of Science, IEEE Xplore, Scopus, Google Scholar).
• Inclusion of peer-reviewed studies published up to February 2026 applying AI for injury prediction/prevention in athletes.
• Adherence to PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines.

Main Results:

• Thirty-nine studies were included in the review.
• Tree-based ML algorithms were most prevalent (59%), with AUC values from 0.82 to 0.95.
• Deep learning (DL) was used in 18% of studies; integrating multi-modal data improved performance in 37%.
• AI-informed prevention strategies demonstrated injury reductions of 23%–42%.

Conclusions:

• AI models offer potential for personalized injury prevention in sports.
• Clinical utility is hindered by methodological issues: heterogeneous injury definitions, small sample sizes, and lack of external validation.
• Standardized protocols are essential to enhance the reliability and practical application of AI models in sports injury management.