Global Positioning System‐Derived Metrics and Machine Learning Models for Injury Prediction in Professional Rugby Union Players
European Journal of Sport Science · 2025-10 · 25 (10)
DOI: 10.1002/ejsc.70057 ↗Kurz gefasst
Fachartikel in der Zeitschrift European Journal of Sport Science, online erschienen am 24.09.2025. Verfasst von Xiangyu Ren und 7 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Adolescent Health Assessment and Exercise Intervention of Ministry of Education, Sino-French Joint Research Center of Sport Science…. Hauptthemen laut MEDLINE: Geographic Information Systems, Football, Machine Learning, Athletic Injuries. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: China Scholarship Council.
Abstract (Originalsprache)
In sports, injury prevention is a key factor for success. Although injuries are challenging to predict, new technologies and the application of data science can provide valuable insights. This study aimed to predict injury risk among professional rugby union players using machine learning (ML) models. We analyzed data from 63 professional rugby union players during three seasons, categorized them into forwards and backs, and further classified them into five specific positions (tight five, back row, scrum‐half, inside backs, outside backs). The dataset included GPS data and derived metrics such as total workload in the 1, 2, and 3 weeks prior to injury, acute‐to‐chronic workload ratio over different time windows, monotony, and strain. Injury prediction was assessed separately for different player positions using five ML classification models: logistic regression, naïve Bayes (NB), support vector machine, random forest (RF), and eXtreme gradient boosting (XGBoost). RF performed best for forwards overall, with XGBoost excelling in the tight five and SVM in the back row, whereas among backs, RF led for inside backs and NB for outside backs. Additionally, feature importance plots were used to examine the impact of various factors on injury occurrence. In conclusion, our ML‐based approach can effectively predict injuries, with average F 1 scores up to 0.66 (± 0.14), particularly when applying a combination of GPS‐derived metrics. Additionally, key characteristics indicative of injury for players in various positions have been successfully identified. These findings underscored the potential of ML to enhance injury prediction and inform tailored training strategies for athletes.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Key Laboratory of Adolescent Health Assessment and Exercise Intervention of Ministry of Education, Sino-French Joint Research Center of Sport Science, College of Physical Education and Health, East China Normal Universi…
- Movement, Sport, Health Laboratory, University of Rennes 2, Bruz, France.
- Department of Sports Sciences and Physical Education, École normale supérieure de Rennes, Bruz, France.
- Rugby Club Vannes, French Rugby Federation, Vannes, France.
- Laboratory of Movement, Balance, Performance and Health (MEPS, EA-4445), University of Pau and Pays de l'Adour, Tarbes, France.
- Faculty of Information Technology, University of Jyväskylä, Jyväskylä, Finland.
ORCID-Profile: Xiangyu Ren, Kilian Philippe
Förderung
- China Scholarship Council
Zitieren
APA
Ren, X., Boisbluche, S., Philippe, K., Demy, M., Äyrämö, S., Rautiainen, I., Ding, S., & Prioux, J. (2025). Global Positioning System‐Derived Metrics and Machine Learning Models for Injury Prediction in Professional Rugby Union Players. European Journal of Sport Science, 25(10). https://doi.org/10.1002/ejsc.70057
Vancouver
Ren X, Boisbluche S, Philippe K, Demy M, Äyrämö S, Rautiainen I, et al. Global Positioning System‐Derived Metrics and Machine Learning Models for Injury Prediction in Professional Rugby Union Players. European Journal of Sport Science. 2025;25(10). doi:10.1002/ejsc.70057
BibTeX
@article{Ren2025,
author = {Ren, Xiangyu and Boisbluche, Simon and Philippe, Kilian and Demy, Mathieu and Äyrämö, Sami and Rautiainen, Ilkka and Ding, Shuzhe and Prioux, Jacques},
title = {Global Positioning System‐Derived Metrics and Machine Learning Models for Injury Prediction in Professional Rugby Union Players},
journal = {European Journal of Sport Science},
year = {2025},
volume = {25},
number = {10},
doi = {10.1002/ejsc.70057}
}
EUVIMED