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

Aug 6, 2026

Upload by Ivy

Heart failure in children under five years of age is associated with a high in-hospital mortality risk, while existing pediatric tools provide limited specificity for this subgroup. A retrospective cohort study analyzed 630 hospitalized children with heart failure (2013–2024) and used Boruta to select seven key predictors from 67 variables. Six machine learning models were trained, with XGBoost chosen and interpreted using SHAP, and validated externally in 73 additional cases.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages14

Reading Time35 min

AccessFree to download

Introduction

Study objective and clinical need

Rationale for machine learning in pediatric HF

Methods

Data source and cohort selection

Predictor selection and model development

Model interpretation and validation

Results

Predictive performance

Key predictors identified by SHAP

Conclusion

TYPE Original Research PUBLISHED 26 May 2025 DOI 10.3389/fped.2025.1608334 EDITED BY Yoshihide Mitani, Mie University, Japan REVIEWED BY Federico Gutierrez-Larraya, University Hospital La Paz, Spain Kottaimalai Ramaraj, Kalasalingam University, India *CORRESPONDENCE You Chen [donny666@sina.com](donny666@sina.com) RECEIVED 08 April 2025 ACCEPTED 12 May 2025 PUBLISHED 26 May 2025 CITATION Lv H, Sun F, Yuan T, Shen H, Baheti L and Chen Y (2025) Development and validation of a machine learning model for in-hospital mortality prediction in children under 5 years with heart failure. Front. Pediatr. 13:1608334 . doi: 10.3389/fped.2025.1608334 COPYRIGHT © 2025 Lv, Sun, Yuan, Shen, Baheti and Chen. 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) and the copyright owner(s) 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. Development and validation of a machine learning model for in-hospital mortality prediction in children under 5 years with heart failure Huasheng Lv1, Fengyu Sun2, Teng Yuan1, Haoliang Shen1, Lazaiyi Baheti1 and You Chen1* 1Department of Cardiology, The First Afﬁliated Hospital of Xinjiang Medical University, Urumqi, China, 2Department of Pediatrics, Xinjiang Medical University, Urumqi, China Background: Heart 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. Methods: We 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. Results: The 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. Conclusion: This 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. KEYWORDS pediatric heart failure, in-hospital mortality, machine learning, risk prediction, interpretability 1 Introduction For Heart failure (HF) in pediatric populations represents a signiﬁcant global health challenge, contributing substantially to mortality rates among children under ﬁve years of age worldwide (1) . In young children, the most common underlying etiologies of HF include congenital heart disease and cardiomyopathy (2) . Although the overall incidence of pediatric HF is relatively low—estimated between 0.9 and 7.4 cases per 100,000 children annually—the condition carries a markedly high morbidity and mortality burden. Reported in-hospital mortality rates among pediatric HF patients range from 7% to as high as 26%, particularly in younger children or those with complex comorbidities (3, 4) . In the United States alone, more than 14,000 pediatric Frontiers in Pediatrics 01 [frontiersin.org](frontiersin.org) hospitalizations annually are attributed to heart failure, highlighting its substantial clinical impact rela

FAQs

Why is a specialized mortality prediction model needed for children under five with heart failure?

Because existing pediatric risk scores lack specificity for heart failure in this age group, the study addresses the need for more reliable and interpretable prediction models. It focuses on children under five at heightened risk of rapid deterioration.

How was the final model interpreted?

The selected XGBoost model was interpreted using SHAP, supporting the clinical relevance of key variables driving predictions.

What were the model’s validation results and top predictors?

The XGBoost model showed high discrimination with AUC values of 0.916 (training), 0.851 (internal validation), and 0.846 (external validation). The leading predictors included NT-proBNP, pH, PCT, LDH, WBC, creatinine, and platelet count.

Aug 6, 2026

Upload by Ivy