LLM ensemble PREVIA predicts future PTSD risk from emergency department trauma narratives with expert-level accuracy

Post-traumatic stress disorder affects numerous trauma survivors following emergency department discharge, making this encounter vital for early risk stratification. Yet emergency clinicians face severe time constraints, making existing screening tools impractical. We introduce PREVIA, a clinically-informed large language model ensemble, that predicts post-traumatic stress disorder risk from unstructured patient trauma narratives, collected in response to a routine-care question asked in the emergency department, by extracting early post-traumatic stress symptoms, peri-traumatic symptoms, risk, and protective factors. Within an ongoing longitudinal study, we included N = 145 patients across two New York City level-1 trauma centers within 24 hours of trauma and assessed post-traumatic stress disorder 1-month post-trauma. In this work, PREVIA accurately forecasts post-traumatic stress disorder (AUROC = 78.49% ± 5.75%, sensitivity=95.4% ± 3.99%, precision=46.76% ± 8.66%), performs comparably to an emergency clinician specialized in post-traumatic stress disorder on 30 randomly selected patients (PREVIA: AUROC = 84.39%, sensitivity=100.00%, precision=50.00%; clinician: AUROC = 83.86%, sensitivity=88.89%, precision=50.00%), and generates interpretable explanations without additional clinical burden. These initial findings support PREVIA’s potential as a scalable emergency department screener for timely, targeted interventions, and warrant validation in larger, independent cohorts. PTSD screening is rarely feasible in busy emergency departments. Here, the authors show that a scalable AI ensemble can predict 1-month PTSD risk from a single routine-care question, a first step toward low-burden implementation at point of care.