Predicting time to clearance of sport-related concussions using machine learning
DIGITAL HEALTH · 2026-02 · 12
DOI: 10.1177/20552076261450858 ↗Kurz gefasst
Fachartikel in der Zeitschrift DIGITAL HEALTH, online erschienen am 20.05.2026. Verfasst von Megan Tran und 4 weiteren Autor:innen. Beteiligte Einrichtung: Bellini College of Artificial Intelligence, Cybersecurity, and Computing, University of South Florida, Tampa, FL, USA. Die Arbeit nennt 124 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Florida Department of State - Center for Neuromusculoskeletal Research.
Abstract (Originalsprache)
Objective
To evaluate whether integrating longitudinal clinical data improves machine learning (ML)-based prediction of time to medical clearance following sport-related concussion (SRC) and to identify clinical features most strongly associated with classification of either ‘prolonged’ recovery ( ≥ 30 days) or ‘normal’ recovery (< 30 days).
Methods
A retrospective cohort of 217 athletes (mean age 26.94 years) from the USF Concussion Center (2021–2025) was analyzed. Six ML classifiers were trained on Visit 1 features ( n = 48) and combined Visit 1 + Visit 2 features ( n = 95). Internal validation was performed using Leave-One-Out Cross-Validation (LOOCV).
Results
Prolonged recovery occurred in 81.1% of the cohort. Adding Visit 2 features improved accuracy in 66% of models, with XGBoost achieving the highest accuracy (0.84, +5% gain over Visit 1). Specificity remained low (0.00–0.34) due to class imbalance. VOR Vertical Headache and its change score were the most frequent predictors of prolonged recovery, present in 81% and 100% of models, respectively. Treatment presence between visits emerged as the strongest predictor of normal recovery.
Conclusions
Longitudinal clinical data modestly improves ML-based SRC recovery predictions. Vestibulo-oculomotor symptoms - particularly headache provoked during vertical VOR testing - are robust prognostic indicators. These findings support the utility of granular VOMS subscores for early risk stratification and targeted rehabilitation. External validation is required before clinical deployment. Code: https://github.com/MeganTran6023/Sport-Related-Concussions_Machine-Learning . IRB: USF STUDY003514.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Bellini College of Artificial Intelligence, Cybersecurity, and Computing, University of South Florida, Tampa, FL, USA.
- Morsani College of Medicine - Department of Orthopaedics & Sports Medicine, University of South Florida, Tampa, FL, USA.
- Morsani College of Medicine - Department of Neurosurgery, Brain, & Spine, University of South Florida, Tampa, FL, USA.
- College of Engineering - Department of Medical Engineering, University of South Florida, Tampa, FL, USA.
- Morsani College of Medicine - Center for Neuromusculosketal Research, University of South Florida, Tampa, FL, USA.
ORCID-Profile: Megan Tran, Byron Moran, Nathan D Schilaty, John Michael Templeton
Förderung
- Florida Department of State - Center for Neuromusculoskeletal Research
Zitieren
APA
Tran, M., Holler, J., Moran, B., Schilaty, N. D., & Templeton, J. M. (2026). Predicting time to clearance of sport-related concussions using machine learning. DIGITAL HEALTH, 12. https://doi.org/10.1177/20552076261450858
Vancouver
Tran M, Holler J, Moran B, Schilaty ND, Templeton JM. Predicting time to clearance of sport-related concussions using machine learning. DIGITAL HEALTH. 2026;12. doi:10.1177/20552076261450858
BibTeX
@article{Tran2026,
author = {Tran, Megan and Holler, Jessica and Moran, Byron and Schilaty, Nathan D and Templeton, John Michael},
title = {Predicting time to clearance of sport-related concussions using machine learning},
journal = {DIGITAL HEALTH},
year = {2026},
volume = {12},
doi = {10.1177/20552076261450858}
}
EUVIMED