aceSHAP-based interpretable machine learning for injury risk prediction in university football players: a multi-dimensional data analysis approach
Sports injury prediction is crucial for university football player health, yet existing research predominantly focuses on professional athletes and lacks interpretability. Using the Kaggle "University Football Injury Prediction Dataset" (800 Chinese university players), we constructed a comprehensive 18-feature evaluation system across four dimensions: basic information, training factors, physical fitness, and lifestyle habits. We systematically compared 10 machine learning algorithms. The Support Vector Machine…
SVM-based model using 18 features across four dimensions predicted injury risk in 800 university football players with 95.6% accuracy and 99.2% ROC-AUC, with SHAP identifying stress, sleep and balance as top factors.
Model was developed and tested on a single Kaggle dataset of 800 Chinese university players without external validation, limiting generalizability and preventing immediate clinical deployment.
Single-dataset design without external validation limits generalizability and requires prospective validation before clinical deployment.
Evidence
- Peer-reviewedScientific Reports2025-11-17
How should this claim be treated?
Truvace Impact Record TRV-2026-0476, v1: “SHAP-based interpretable machine learning for injury risk prediction in university football players: a multi-dimensional data analysis approach.” Truvace, 2026-07-22. /record/TRV-2026-0476 (accessed at citation time). sha256 a901f96b08cf91cb…
Calibration history
Every change to this record since certification, in the open. None yet — the reading has held since it entered the record.
Certified into the record
How to verify without trusting this page
Fetch the canonical text of any version from /api/record/TRV-2026-0476 and hash it yourself — for example shasum -a 256 on the saved canonical field. The result must equal content_hash, and each version’s text ends with prev:followed by the prior version’s hash (version 1 chains to 64 zeros). If a single character of any version had been altered since certification, the chain would not reproduce.