Skip to main content

ORIGINAL RESEARCH article

Front. Pediatr.
Sec. General Pediatrics and Pediatric Emergency Care
Volume 13 - 2025 | doi: 10.3389/fped.2025.1522845

Machine Learning-Based Prediction of Mortality in Pediatric Trauma Patients

Provisionally accepted
Alex Deleon Alex Deleon 1*Anish Murala Anish Murala 2Isabelle Decker Isabelle Decker 1Karthik Rajasekaran Karthik Rajasekaran 3Alvaro Moreira Alvaro Moreira 1
  • 1 Joe R. & Teresa Lozano Long School of Medicine, The University of Texas Health Science Center at San Antonio, San Antonio, United States
  • 2 Texas A and M University, College Station, Texas, United States
  • 3 University of Pennsylvania, Philadelphia, Pennsylvania, United States

The final, formatted version of the article will be published soon.

    This study aimed to develop a predictive model for mortality outcomes among pediatric trauma patients using machine learning (ML) algorithms.We extracted data on a cohort of pediatric trauma patients (18 years and younger) from the National Trauma Data Bank (NTDB). The main aim was to identify clinical and physiologic variables that could serve as predictors for pediatric trauma mortality. Data was split into a development cohort (70%) to build four ML models and then tested in a validation cohort (30%). The area under the receiver operating characteristic curve (AUC) was used to assess each model's performance.In 510,381 children, the gross mortality rate was 1.6 % (n=8,250). Most subjects were male (67%, n=342,571) and white (62%, n=315,178). The AUCs of the four models ranged from 92.7 to 97.7 with XGBoost demonstrating the highest AUC. XGBoost demonstrated the highest accuracy of 97.7%.Machine learning algorithms can be effectively utilized to build an accurate pediatric mortality prediction model that leverages variables easily obtained upon trauma admission.

    Keywords: machine learning, Trauma, Mortality, prediction, Pediatrics

    Received: 05 Nov 2024; Accepted: 08 Jan 2025.

    Copyright: © 2025 Deleon, Murala, Decker, Rajasekaran and Moreira. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Alex Deleon, Joe R. & Teresa Lozano Long School of Medicine, The University of Texas Health Science Center at San Antonio, San Antonio, United States

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.