Skip to content
DraconiticResearch
Search Sources API
201,683 studies31 sourcesUpdated 20 min ago
Peer-reviewedCC BY-NC-ND 4.0NPJ Digital Medicine

Injury prediction in elite women’s football: an integrative machine learning-based decision-support framework

  • Manuel Huth1,2
  • Berta Canal-Simón3,4
  • Eva Ferrer5,6
  • Gil Rodas5,6,7
  • Xavier Yanguas5
  • Jan Hasenauer1,2
  • Juan R. González3,8,9
9 affiliations
  1. 1Life and Medical Sciences (LIMES) Institute, University of Bonn, Bonn, Germany
  2. 2Bonn Center for Mathematical Life Sciences, University of Bonn, Bonn, Germany
  3. 3Barcelona Institute for Global Health (ISGlobal), Barcelona, Spain
  4. 4Made of Genes, Barcelona, Spain
  5. 5Medical Department of Football Club Barcelona (FIFA Medical Centre of Excellence), and Barça Innovation Hub of Football Club Barcelona, Barcelona, Spain
  6. 6Sports and Exercise Medicine Unit, Hospital Clinic and Sant Joan de Déu, Barcelona, Spain
  7. 7Leitat technological Center, Terrassa, Spain
  8. 8CIBER in Epidemiology and Public Health (CIBERESP), Barcelona, Spain
  9. 9Department of Mathematics, Universitat Autònoma de Barcelona (UAB), Barcelona, Spain
Read full textPDFDOICite

Abstract

Injuries in elite sports disrupt team performance, shorten careers, and incur significant financial costs, highlighting the critical need for accurate predictions to inform optimal decisions that effectively prevent injuries. Existing approaches to injury prediction fail to account for cumulative risk, overlook injury severity, lack reliable probability calibration, and omit statistically guided decision thresholds. Here, we present a novel injury prediction framework integrating risk accumulation via survival analysis with machine learning, probability beta calibration, and statistical decision theory. Using a unique dataset spanning four seasons from FC Barcelona’s women’s team, we demonstrate that our framework outperforms standard classifiers, yielding superior discrimination ability. Our framework identifies fatigue-related measures as key injury predictors and incorporates flexible thresholds based on match importance and decision-maker certainty, improving player availability. Scalable and transferable to other sports, this framework bridges academic research and practical deployment, empowering sports organizations to optimize player performance and long-term outcomes.

Related

  1. Explainable machine learning for breast cancer prediction in resource-constrained settings: A multi-algorithmic framework integrating shap-based transparency with clinical decision support
    Oluwaseun Adebayo Bamodu, Sumaiya Nezam, Chen-Chih Chung
    PLOS Digital HealthPeer-reviewedCC BY 4.0Full textOncologyPLOS
  2. Identifying and formulating appropriate clinical problems for clinical prediction models and AI decision support: the RIVU-AI framework.
    Jeff Choi, Jayson Marwaha, Gary S Collins
    BMJ digital health & AIPeer-reviewedCC BY-NCFull textEpidemiology & public healthEurope PMCPMC
  3. KT-CBHNET: a spatio-temporal deep learning framework for interpretable ECG signal classification for cardiovascular disease prediction
    Krantee Singh, Vasudev Dehalwar
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textCardiovascular medicineCrossref
  4. Leakage-aware machine learning for data-driven performance prediction of metal–organic framework systems
    Nidal H. Abu-Hamdeh, Mohammed N. Ajour, Ahmad H. Milyani +2
    Frontiers in medicinePeer-reviewedCC BYFull textGeneral medicineEurope PMC
  5. Triage models for surgical decision-making in patients with shoulder pain: an integrative review
    Samah Hassan, Kenneth J. Faber, Joy C. MacDermid
    Pain reportsPeer-reviewedCC BY-NC-NDFull textGeneral medicineEurope PMC

Cite

BibTeXRIS
BibTeX
@article{huth2026injury,
  title = {{Injury prediction in elite women’s football: an integrative machine learning-based decision-support framework}},
  author = {Manuel Huth and Berta Canal-Simón and Eva Ferrer and Gil Rodas and Xavier Yanguas and Jan Hasenauer and Juan R. González},
  journal = {NPJ Digital Medicine},
  year = {2026},
  month = jul,
  doi = {10.1038/s41746-026-02937-3},
  url = {https://doi.org/10.1038/s41746-026-02937-3},
  note = {CC BY-NC-ND 4.0},
}
RIS
TY  - JOUR
TI  - Injury prediction in elite women’s football: an integrative machine learning-based decision-support framework
AU  - Manuel Huth
AU  - Berta Canal-Simón
AU  - Eva Ferrer
AU  - Gil Rodas
AU  - Xavier Yanguas
AU  - Jan Hasenauer
AU  - Juan R. González
PY  - 2026
DA  - 2026/07/08
JO  - NPJ Digital Medicine
DO  - 10.1038/s41746-026-02937-3
UR  - https://doi.org/10.1038/s41746-026-02937-3
AB  - Injuries in elite sports disrupt team performance, shorten careers, and incur significant financial costs, highlighting the critical need for accurate predictions to inform optimal decisions that effectively prevent injuries. Existing approaches to injury prediction fail to account for cumulative risk, overlook injury severity, lack reliable probability calibration, and omit statistically guided decision thresholds. Here, we present a novel injury prediction framework integrating risk accumulation via survival analysis with machine learning, probability beta calibration, and statistical decision theory. Using a unique dataset spanning four seasons from FC Barcelona’s women’s team, we demonstrate that our framework outperforms standard classifiers, yielding superior discrimination ability. Our framework identifies fatigue-related measures as key injury predictors and incorporates flexible thresholds based on match importance and decision-maker certainty, improving player availability. Scalable and transferable to other sports, this framework bridges academic research and practical deployment, empowering sports organizations to optimize player performance and long-term outcomes.
SN  - 2398-6352
ER  -