A Real-Time Automated Machine Learning Algorithm for Predicting Mortality in Trauma Patients: Survey Says it's Ready for Prime-Time

External Validation of Predictors of Mortality in Polytrauma Patients

INTRODUCTION

The Parkland Trauma Index of Mortality (PTIM) is an integrated, machine learning 72-h mortality prediction model that automatically extracts and analyzes demographic, laboratory, and physiological data in polytrauma patients. We hypothesized that this validated model would perform equally as well at another level 1 trauma center.

METHODS

A retrospective cohort study was performed including ∼5000 adult level 1 trauma activation patients from January 2022 to September 2023. Demographics, physiologic and laboratory values were collected. First, a test set of models using PTIM clinical variables (CVs) was used as external validation, named PTIM+. Then, multiple novel mortality prediction models were developed considering all CVs designated as the Cincinnati Trauma Index of Mortality (CTIM). The statistical performance of the models was then compared.

RESULTS

PTIM CVs were found to have similar predictive performance within the PTIM + external validation model. The highest correlating CVs used in CTIM overlapped considerably with those of the PTIM, and performance was comparable between models. Specifically, for prediction of mortality within 48 h (CTIM versus PTIM): positive prediction value was 35.6% versus 32.5%, negative prediction value was 99.6% versus 99.3%, sensitivity was 81.0% versus 82.5%, specificity was 97.3% versus 93.6%, and area under the curve was 0.98 versus 0.94.

CONCLUSIONS

This external cohort study suggests that the variables initially identified via PTIM retain their predictive ability and are accessible in a different level 1 trauma center. This work shows that a trauma center may be able to operationalize an effective predictive model without undertaking a repeated time and resource intensive process of full variable selection.

Machine learning in the prediction of massive transfusion in trauma: a retrospective analysis as a proof-of-concept

PURPOSE

Early administration and protocolization of massive hemorrhage protocols (MHP) has been associated with decreases in mortality, multiorgan system failure, and number of blood products used. Various prediction tools have been developed for the initiation of MHP, but no single tool has demonstrated strong prediction with early clinical data. We sought to develop a massive transfusion prediction model using machine learning and early clinical data.

METHODS

Using the National Trauma Data Bank from 2013 to 2018, we included severely injured trauma patients and extracted clinical features available from the pre-hospital and emergency department. We subsequently balanced our dataset and used the Boruta algorithm to determine feature selection. Massive transfusion was defined as five units at 4 h and ten units at 24 h. Six machine learning models were trained on the balanced dataset and tested on the original.

RESULTS

A total of 326,758 patients met our inclusion with 18,871 (5.8%) requiring massive transfusion. Emergency department models demonstrated strong performance characteristics with mean areas under the receiver-operating characteristic curve of 0.83. Extreme gradient boost modeling slightly outperformed and demonstrated adequate predictive performance with pre-hospital data only, as well as 4-h transfusion thresholds.

CONCLUSIONS

We demonstrate the use of machine learning in developing an accurate prediction model for massive transfusion in trauma patients using early clinical data. This research demonstrates the potential utility of artificial intelligence as a clinical decision support tool.