Survival Prediction in Traumatic Brain Injury Patients Using Machine Learning Algorithms

Abstract

Abstract Predicting treatment outcomes in traumatic brain injury (TBI) patients is challenging worldwide. The present study aimed to achieve the most accurate machine learning algorithms to predict the outcomes of TBI treatment by evaluating demographic features, laboratory data, imaging indices, and clinical features. We used data from 3347 patients admitted to a tertiary trauma centre in Iran from 2016 to 2021. After the exclusion of incomplete data, 1653 patients remained. We used machine learning algorithms such as Random Forest (RF) and Decision Tree (DT) with ten-fold cross-validation to develop the best prediction model. Our findings reveal that among different variables included in this study, the motor component of the Glasgow Coma Scale, condition of pupils, and condition of cisterns were the most reliable features for predicting in-hospital mortality, while the patients’ age takes the place of cisterns condition when considering the long-term survival of TBI patients. Also, we found that the RF algorithm is the best model to predict the short-term mortality of TBI patients. However, the generalized linear model (GLM) algorithm had the best performance (with an accuracy rate of 82.03 ± 2.34) in predicting the long-term survival of patients. Our results showed that using appropriate markers, and machine learning algorithms can provide a reliable prediction of TBI patients’ survival in the short- and long-term with reliable and easily accessible features of patients.