Journal article
Yuxin Cai, Aditya A. Shanghavi, Ranjana K. Mehta
Proceedings of the Human Factors and Ergonomics Society Annual Meeting, 2026
Proceedings of the Human Factors and Ergonomics Society Annual Meeting, 2026
Cite
Cite
APA
Click to copy
Cai, Y., Shanghavi, A. A., & Mehta, R. K. (2026). Identifying Robust Predictors of Operational Fatigue in Emergency Medical Services Providers: A Machine Learning Approach. Proceedings of the Human Factors and Ergonomics Society Annual Meeting. https://doi.org/10.1177/10711813261498776
Chicago/Turabian
Click to copy
Cai, Yuxin, Aditya A. Shanghavi, and Ranjana K. Mehta. “Identifying Robust Predictors of Operational Fatigue in Emergency Medical Services Providers: A Machine Learning Approach.” Proceedings of the Human Factors and Ergonomics Society Annual Meeting (2026).
MLA
Click to copy
Cai, Yuxin, et al. “Identifying Robust Predictors of Operational Fatigue in Emergency Medical Services Providers: A Machine Learning Approach.” Proceedings of the Human Factors and Ergonomics Society Annual Meeting, 2026, doi:10.1177/10711813261498776.
BibTeX Click to copy
@article{cai2026a,
title = {Identifying Robust Predictors of Operational Fatigue in Emergency Medical Services Providers: A Machine Learning Approach},
year = {2026},
journal = {Proceedings of the Human Factors and Ergonomics Society Annual Meeting},
doi = {10.1177/10711813261498776},
author = {Cai, Yuxin and Shanghavi, Aditya A. and Mehta, Ranjana K.}
}
Abstract
Fatigue in emergency medical services (EMS) providers is associated with impaired performance and safety risk, yet data-driven fatigue modeling in EMS remains limited. This study investigated the feasibility of predicting operational fatigue using multimodal wearable physiological, behavioral, and contextual data obtained from 11 EMS providers during a 5-day real-world field data collection. Features were extracted from 6-hour retrospective temporal windows preceding fatigue assessments and used to train Logistic Regression, Random Forest, XGBoost, and CatBoost models. Logistic Regression achieved the best predictive performance (AUROC = 0.87), demonstrating reliable discrimination between high- and low-fatigue states. Feature importance analyses identified robust fatigue predictors across models, including time of day, cumulative work exposure, dispatched call volume, and slope-based pulse rate features. Findings suggest that operational fatigue in EMS reflects interacting circadian, workload-related, behavioral, and physiological processes and supports the feasibility of scalable wearable-based fatigue monitoring in safety-critical operational environments.