# Identifying Trigger Cues for Hospital Blood Transfusions Based on Ensemble Learning Methods

## TL;DR

This study identifies key factors to predict which trauma patients need blood transfusions early in hospital, to guide prehospital decisions and improve survival.

## Contribution

A novel prehospital transfusion algorithm is developed using ensemble learning methods and clinically relevant factors.

## Key findings

- A simple algorithm using SBP, lactate, Shock Index, and AIS of chest predicted hospital transfusion needs with high sensitivity and specificity.
- Prenatal lactate concentration was identified as a decisive factor for transfusion requirements using Bayesian analysis.
- Conventional thresholds for transfusion triggers were found to be less sensitive than the algorithm's thresholds.

## Abstract

Traumatic shock is the leading cause of preventable death with most patients dying within the first 6 hours. This underscores the importance of prehospital interventions, and growing evidence suggests prehospital transfusion improves survival. Optimizing transfusion triggers in the prehospital setting is key to improving outcomes for patients in hemorrhagic shock. Our objective was to identify factors associated with early in-hospital transfusion requirements available to prehospital clinicians in the field to develop a simple algorithm for prehospital transfusion, particularly for patients with occult shock.

We included trauma patients transported by a single critical care transport service to a level I trauma center between 2012 and 2019. We used logistic regression, Fast and Frugal Trees (FFTs), and Bayesian analysis to identify factors associated with early in-hospital blood transfusion as a potential trigger for prehospital transfusion.

We included 2,157 patients transported from the scene or emergency department (ED) of whom 207 (9.60%) required blood transfusion within 4 hours of admission. The mean age was 47 (IQR = 28–62) and 1,480 (68.6%) patients were male. From 13 clinically relevant factors for early hospital transfusions, four were incorporated into the FFT in following order: 1) SBP, 2) prehospital lactate concentration, 3) Shock Index, 4) AIS of chest (sensitivity = 0.81, specificity = 0.71). The chosen thresholds were similar to conventional ones. Using conventional thresholds resulted in lower model sensitivity. Consistently, prehospital lactate was among most decisive factors of hospital transfusions identified by Bayesian analysis (OR = 2.31; 95% CI 1.55–3.37).

Using an ensemble of frequentist statistics, Bayesian analysis and machine learning, we developed a simple, clinically relevant, prehospital algorithm to help identify patients requiring transfusion within 4 hours of hospital arrival.