Abstract
Background and Objectives: Elderly trauma patients face unique physiological challenges that often lead to undertriage under the current guidelines. The present study aimed to develop machine-learning (ML)-based, age-specific triage guidelines to improve predictions for intensive care unit (ICU) admissions and in-hospital mortality. Materials and Methods: A total of 274,347 trauma cases transported via Emergency Medical System (EMS)-119 in Seoul (2020-2022) were analyzed. Physiological indicators (e.g., systolic blood pressure; saturation of partial pressure oxygen; and alert, verbal, pain, unresponsiveness scale) were incorporated. Bayesian optimization was used to fine-tuned models for sensitivity and specificity, emphasizing the F2 score to minimize undertriage. Results: Compared with the current guidelines, the alternative guidelines achieved superior sensitivity for ICU admissions (0.728 vs. 0.541) and in-hospital mortality (0.815 vs. 0.599). Subgroup analyses across injury severities, including traumatic brain and chest injuries, confirmed the enhanced performance of the alternative guidelines. Conclusions: ML-based, age-specific triage guidelines improve the sensitivity of triage decisions, reduce undertriage, and optimize elderly trauma care. Implementing these guidelines can significantly enhance patient outcomes and resource allocation in emergency settings.