Predicting Prehospital Blood Transfusion After Motor Vehicle Trauma.
Model predicted prehospital blood transfusion need after motor vehicle crashes with high accuracy
Predicting Prehospital Blood Transfusion After Motor Vehicle Trauma.
Prehospital blood transfusion (prehospital blood transfusion) improves outcomes among patients with traumatic hemorrhagic shock, yet the epidemiology and geographic distribution of patients likely to require prehospital blood transfusion remain poorly characterized.
We sought to develop predictive models for prehospital blood transfusion among motor vehicle crash (motor vehicle crash) patients using National Emergency Medical Services Information System (National Emergency Medical Services Information System) data and to estimate the national distribution of patients with a high predicted probability of receiving prehospital blood transfusion.
We conducted an observational study and retrospective cohort study using the 2024 and 2025 National Emergency Medical Services Information System data.
AUC near 1.0 means near-perfect discrimination; 0.906 shows strong prediction of transfusion need.
Among 2,078,452 eligible EMS activations, 303,383 comprised the derivation cohort.
The ridge-selected logistic regression model achieved an AUC of 0.902, sensitivity of 64.6%, and specificity of 97.3%.
Both models identified composite physiologic measures, critical hemorrhagic shock designation, and unspecified traumatic shock as significant predictors of prehospital blood transfusion.
Predictive modeling applied to National Emergency Medical Services Information System data accurately identified patients with a high probability of receiving prehospital blood transfusion following motor vehicle crash trauma.
These findings provide a framework for estimating geographic demand for prehospital blood products and may inform data-driven expansion of prehospital blood transfusion programs in trauma systems.