Machine learning-based prediction of mortality in pediatric trauma patients.

IF 2.1 3区医学 Q2 PEDIATRICS

Frontiers in Pediatrics Pub Date : 2025-02-27 eCollection Date: 2025-01-01 DOI:10.3389/fped.2025.1522845

Alex Deleon, Anish Murala, Isabelle Decker, Karthik Rajasekaran, Alvaro Moreira

{"title":"Machine learning-based prediction of mortality in pediatric trauma patients.","authors":"Alex Deleon, Anish Murala, Isabelle Decker, Karthik Rajasekaran, Alvaro Moreira","doi":"10.3389/fped.2025.1522845","DOIUrl":null,"url":null,"abstract":"Background: This study aimed to develop a predictive model for mortality outcomes among pediatric trauma patients using machine learning (ML) algorithms.Methods: 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.Results: 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%.Conclusion: Machine learning algorithms can be effectively utilized to build an accurate pediatric mortality prediction model that leverages variables easily obtained upon trauma admission.","PeriodicalId":12637,"journal":{"name":"Frontiers in Pediatrics","volume":"13 ","pages":"1522845"},"PeriodicalIF":2.1000,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11905922/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers in Pediatrics","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.3389/fped.2025.1522845","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"PEDIATRICS","Score":null,"Total":0}

引用次数: 0

Abstract

Background: This study aimed to develop a predictive model for mortality outcomes among pediatric trauma patients using machine learning (ML) algorithms.

Methods: 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.

Results: 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%.

Conclusion: Machine learning algorithms can be effectively utilized to build an accurate pediatric mortality prediction model that leverages variables easily obtained upon trauma admission.

查看原文本刊更多论文

求助全文

约1分钟内获得全文求助全文

来源期刊

Frontiers in Pediatrics Medicine-Pediatrics, Perinatology and Child Health

CiteScore

3.60

自引率

7.70%

发文量

2132

审稿时长

14 weeks

期刊介绍： Frontiers in Pediatrics (Impact Factor 2.33) publishes rigorously peer-reviewed research broadly across the field, from basic to clinical research that meets ongoing challenges in pediatric patient care and child health. Field Chief Editors Arjan Te Pas at Leiden University and Michael L. Moritz at the Children''s Hospital of Pittsburgh are supported by an outstanding Editorial Board of international experts. This multidisciplinary open-access journal is at the forefront of disseminating and communicating scientific knowledge and impactful discoveries to researchers, academics, clinicians and the public worldwide. Frontiers in Pediatrics also features Research Topics, Frontiers special theme-focused issues managed by Guest Associate Editors, addressing important areas in pediatrics. In this fashion, Frontiers serves as an outlet to publish the broadest aspects of pediatrics in both basic and clinical research, including high-quality reviews, case reports, editorials and commentaries related to all aspects of pediatrics.