Prognosis prediction in traumatic brain injury patients using machine learning algorithms

Predicting treatment outcomes in traumatic brain injury (TBI) patients is challenging worldwide. The present study aimed to achieve the most accurate machine learning (ML) 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 ML 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, the condition of pupils, and the 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 showed 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 with further development, ML has the potential to predict TBI patients' survival in the short- and long-term.

Automated summary

Predicting treatment outcomes in traumatic brain injury (TBI) patients using machine learning algorithms was investigated in this study. Demographic features, laboratory data, imaging indices, and clinical features were evaluated using data from 3347 TBI patients in Iran. The motor component of the Glasgow coma scale, pupils condition, and cisterns condition were found to be reliable features for predicting in-hospital mortality, while age replaced cisterns condition for long-term survival prediction. The random forest algorithm was the best model for short-term mortality prediction, while the generalized linear model algorithm showed the best performance in predicting long-term survival.