Pediatric severe traumatic brain injury mortality prediction determined with machine learning-based modeling

Area of Science:

• Pediatric critical care medicine
• Neuroscience
• Medical informatics

Background:

• Severe traumatic brain injury (sTBI) is a significant cause of mortality in children.
• Accurate prognostication is crucial for guiding clinical care and decision-making in pediatric sTBI.
• Developing a precise outcome prediction model for pediatric sTBI mortality is essential.

Purpose of the Study:

• To develop a highly discriminative machine learning model for predicting mortality in pediatric sTBI.
• To identify key admission variables that are most predictive of mortality in pediatric sTBI patients.
• To create a pragmatic prognostic tool for clinical use.

Main Methods:

• Applied machine learning and advanced analytics to a pediatric sTBI database.
• Integrated demographic, clinical, head CT imaging, and blood biochemical data from 196 pediatric patients.
• Utilized feature ranking and Boruta feature selection to identify a parsimonious set of predictive variables.

Main Results:

• A six-variable model achieved 82% mortality classification accuracy.
• Key predictors included partial thromboplastin time, motor Glasgow Coma Scale, serum glucose, fixed pupils, platelet count, and creatinine.
• The model demonstrated high predictive ability with an AUC of 0.90 on validation and 0.91 on the total dataset.

Conclusions:

• Machine learning identified critical prognostic factors for pediatric sTBI mortality.
• The developed model is a pragmatic and high-performing prognostic tool with excellent discriminative ability.
• This tool may assist in treatment decisions, therapy aggressiveness, and facilitate end-of-life discussions.