Development and validation of a machine learning model for in-hospital mortality prediction in children under 5 years with heart failure

BackgroundHeart failure (HF) in children under five years of age carries a high risk of in-hospital mortality, yet existing pediatric risk assessment tools lack specificity for this population. There is a pressing need for reliable, interpretable prediction models tailored to pediatric HF.MethodsWe...

Full description

Saved in:
Bibliographic Details
Main Authors: Huasheng Lv, Fengyu Sun, Teng Yuan, Haoliang Shen, Lazaiyi Baheti, You Chen
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-05-01
Series:Frontiers in Pediatrics
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fped.2025.1608334/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850254584193220608
author Huasheng Lv
Fengyu Sun
Teng Yuan
Haoliang Shen
Lazaiyi Baheti
You Chen
author_facet Huasheng Lv
Fengyu Sun
Teng Yuan
Haoliang Shen
Lazaiyi Baheti
You Chen
author_sort Huasheng Lv
collection DOAJ
description BackgroundHeart failure (HF) in children under five years of age carries a high risk of in-hospital mortality, yet existing pediatric risk assessment tools lack specificity for this population. There is a pressing need for reliable, interpretable prediction models tailored to pediatric HF.MethodsWe retrospectively analyzed 630 hospitalized children under five with heart failure from 2013 to 2024. After excluding those with uncorrected congenital heart disease or terminal comorbidities, 67 variables were assessed, and seven key predictors were identified using the Boruta algorithm. Six machine learning models were developed; the Extreme Gradient Boosting (XGB) model was selected and interpreted using SHAP. External validation included 73 additional cases.ResultsThe XGB model achieved high predictive performance (AUC: 0.916 training, 0.851 internal validation, 0.846 external validation). The top predictors were NT-proBNP, pH, PCT, LDH, WBC, creatinine, and platelet count. SHAP analysis confirmed the clinical relevance of these variables.ConclusionThis study presents a reliable, interpretable machine learning model for predicting in-hospital mortality in young children with heart failure. It holds promise for early risk stratification and timely intervention, potentially improving outcomes in this high-risk population.
format Article
id doaj-art-c9cd1bf3cdac42f5a750e05c7edc59d6
institution OA Journals
issn 2296-2360
language English
publishDate 2025-05-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Pediatrics
spelling doaj-art-c9cd1bf3cdac42f5a750e05c7edc59d62025-08-20T01:57:05ZengFrontiers Media S.A.Frontiers in Pediatrics2296-23602025-05-011310.3389/fped.2025.16083341608334Development and validation of a machine learning model for in-hospital mortality prediction in children under 5 years with heart failureHuasheng Lv0Fengyu Sun1Teng Yuan2Haoliang Shen3Lazaiyi Baheti4You Chen5Department of Cardiology, The First Affiliated Hospital of Xinjiang Medical University, Urumqi, ChinaDepartment of Pediatrics, Xinjiang Medical University, Urumqi, ChinaDepartment of Cardiology, The First Affiliated Hospital of Xinjiang Medical University, Urumqi, ChinaDepartment of Cardiology, The First Affiliated Hospital of Xinjiang Medical University, Urumqi, ChinaDepartment of Cardiology, The First Affiliated Hospital of Xinjiang Medical University, Urumqi, ChinaDepartment of Cardiology, The First Affiliated Hospital of Xinjiang Medical University, Urumqi, ChinaBackgroundHeart failure (HF) in children under five years of age carries a high risk of in-hospital mortality, yet existing pediatric risk assessment tools lack specificity for this population. There is a pressing need for reliable, interpretable prediction models tailored to pediatric HF.MethodsWe retrospectively analyzed 630 hospitalized children under five with heart failure from 2013 to 2024. After excluding those with uncorrected congenital heart disease or terminal comorbidities, 67 variables were assessed, and seven key predictors were identified using the Boruta algorithm. Six machine learning models were developed; the Extreme Gradient Boosting (XGB) model was selected and interpreted using SHAP. External validation included 73 additional cases.ResultsThe XGB model achieved high predictive performance (AUC: 0.916 training, 0.851 internal validation, 0.846 external validation). The top predictors were NT-proBNP, pH, PCT, LDH, WBC, creatinine, and platelet count. SHAP analysis confirmed the clinical relevance of these variables.ConclusionThis study presents a reliable, interpretable machine learning model for predicting in-hospital mortality in young children with heart failure. It holds promise for early risk stratification and timely intervention, potentially improving outcomes in this high-risk population.https://www.frontiersin.org/articles/10.3389/fped.2025.1608334/fullpediatric heart failurein-hospital mortalitymachine learningrisk predictioninterpretability
spellingShingle Huasheng Lv
Fengyu Sun
Teng Yuan
Haoliang Shen
Lazaiyi Baheti
You Chen
Development and validation of a machine learning model for in-hospital mortality prediction in children under 5 years with heart failure
Frontiers in Pediatrics
pediatric heart failure
in-hospital mortality
machine learning
risk prediction
interpretability
title Development and validation of a machine learning model for in-hospital mortality prediction in children under 5 years with heart failure
title_full Development and validation of a machine learning model for in-hospital mortality prediction in children under 5 years with heart failure
title_fullStr Development and validation of a machine learning model for in-hospital mortality prediction in children under 5 years with heart failure
title_full_unstemmed Development and validation of a machine learning model for in-hospital mortality prediction in children under 5 years with heart failure
title_short Development and validation of a machine learning model for in-hospital mortality prediction in children under 5 years with heart failure
title_sort development and validation of a machine learning model for in hospital mortality prediction in children under 5 years with heart failure
topic pediatric heart failure
in-hospital mortality
machine learning
risk prediction
interpretability
url https://www.frontiersin.org/articles/10.3389/fped.2025.1608334/full
work_keys_str_mv AT huashenglv developmentandvalidationofamachinelearningmodelforinhospitalmortalitypredictioninchildrenunder5yearswithheartfailure
AT fengyusun developmentandvalidationofamachinelearningmodelforinhospitalmortalitypredictioninchildrenunder5yearswithheartfailure
AT tengyuan developmentandvalidationofamachinelearningmodelforinhospitalmortalitypredictioninchildrenunder5yearswithheartfailure
AT haoliangshen developmentandvalidationofamachinelearningmodelforinhospitalmortalitypredictioninchildrenunder5yearswithheartfailure
AT lazaiyibaheti developmentandvalidationofamachinelearningmodelforinhospitalmortalitypredictioninchildrenunder5yearswithheartfailure
AT youchen developmentandvalidationofamachinelearningmodelforinhospitalmortalitypredictioninchildrenunder5yearswithheartfailure