Related Experiment Video
Updated: Oct 6, 2025
A Pediatric Concussion Model in Mice: Closed Head Injury with Long-Term Disorders (CHILD)
Published on: February 7, 2025
Pediatric severe traumatic brain injury mortality prediction determined with machine learning-based modeling
Mark Daley1, Saoirse Cameron2, Saptharishi Lalgudi Ganesan2
1Computer Science, Western University, London, ON N6A 3K7, Canada; The Vector Institute for Artificial Intelligence, Toronto, ON M5G 1M1, Canada.
Insights
Machine learning accurately predicts mortality in pediatric severe traumatic brain injury (sTBI) using six key variables. This prognostic tool aids in guiding treatment and end-of-life discussions for improved patient care.
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.
Introduction:
Severe traumatic brain injury (sTBI) is a leading cause of mortality in children. As clinical prognostication is important in guiding optimal care and decision making, our goal was to create a highly discriminative sTBI outcome prediction model for mortality.
Methods:
Machine learning and advanced analytics were applied to the patient admission variables obtained from a comprehensive pediatric sTBI database. Demographic and clinical data, head CT imaging abnormalities and blood biochemical data from 196 children and adolescents admitted to a tertiary pediatric intensive care unit (PICU) with sTBI were integrated using feature ranking by way of a forest of randomized decision trees, and a model was generated from a reduced number of admission variables with maximal ability to discriminate outcome.
Results:
In total, 36 admission variables were analyzed using feature ranking with variable weighting to determine their predictive importance for mortality following sTBI. Reduction analysis utilizing Borata feature selection resulted in a parsimonious six-variable model with a mortality classification accuracy of 82%. The final admission variables that predicted mortality were: partial thromboplastin time (22%); motor Glasgow Coma Scale (21%); serum glucose (16%); fixed pupil(s) (16%); platelet count (13%) and creatinine (12%). Using only these six admission variables, a t-distributed stochastic nearest neighbor embedding algorithm plot demonstrated visual separation of sTBI patients that lived or died, with high mortality predictive ability of this model on the validation dataset (AUC = 0.90) which was confirmed with a conventional area-under-the-curve statistical approach on the total dataset (AUC = 0.91; P < 0.001).
Conclusions:
Machine learning-based modeling identified the most clinically important prognostic factors resulting in a pragmatic, high performing prognostic tool for pediatric sTBI with excellent discriminative ability to predict mortality risk with 82% classification accuracy (AUC = 0.90). After external multicenter validation, our prognostic model might help to guide treatment decisions, aggressiveness of therapy and prepare family members and caregivers for timely end-of-life discussions and decision making.
Level Of Evidence:
III; Prognostic.
