Assessing the utility of a sliding-windows deep neural network approach for risk prediction of trauma patients

Abstract

The risks of post trauma complications are regulated by the injury, comorbidities, and the clinical trajectories, yet prediction models are often limited to single time-point data. We hypothesize that deep learning prediction models can be used for risk prediction using additive data after trauma using a sliding windows approach. Using the American College of Surgeons Trauma Quality Improvement Program (ACS TQIP) database, we developed three deep neural network models, for sliding-windows risk prediction. Output variables included early- and late mortality and any of 17 complications. As patients moved through the treatment trajectories, performance metrics increased. Models predicted early- and late mortality with ROC AUCs ranging from 0.980 to 0.994 and 0.910 to 0.972, respectively. For the remaining 17 complications, the mean performance ranged from 0.829 to 0.912. In summary, the deep neural networks achieved excellent performance in the sliding windows risk stratification of trauma patients.

Prospective and External Validation of Prognostic Machine Learning Models for Short- and Long-Term Mortality Among Acutely Admitted Patients Based on Blood Tests.

“…Various scores and indices based on simple linear relationship have been proposed and used to predict mortality; however, their accuracy is only moderate 4,8,10 . In recent years, applying ML to healthcare data has surpassed these traditional methods, offering enhanced accuracy in predicting outcomes for various patient groups, including those with conditions like cardiac disease 11 , COVID-19 12 , trauma 13 , sepsis 14 , and those in intensive care units (ICU) 15 . While ML algorithms offer signi cant advantages, their integration into clinical practice presents challenges, primarily due to the incorporation of numerous clinical and non-clinical variables.…”