Related Experiment Video
Updated: Jun 12, 2025
An R-Based Landscape Validation of a Competing Risk Model
Published on: September 16, 2022
Development and validation of a machine learning model for in-hospital mortality prediction in children under 5 years
Huasheng Lv1, Fengyu Sun2, Teng Yuan1
1Department of Cardiology, The First Affiliated Hospital of Xinjiang Medical University, Urumqi, China.
Insights
A new machine learning model accurately predicts in-hospital mortality in young children with heart failure (HF). This tool aids early risk stratification for better pediatric HF outcomes.
Area of Science:
- Pediatric Cardiology
- Computational Biology
- Biomedical Informatics
Background:
- Heart failure (HF) in children under five presents a high mortality risk.
- Current pediatric risk tools lack specificity for this age group.
- Reliable, interpretable prediction models for pediatric HF are critically needed.
Purpose of the Study:
- To develop and validate a machine learning model for predicting in-hospital mortality in young children with heart failure.
- To identify key predictors of mortality in this population.
Main Methods:
- Retrospective analysis of 630 pediatric HF cases (2013-2024).
- Feature selection using the Boruta algorithm identified seven key predictors.
- Extreme Gradient Boosting (XGB) model developed and interpreted using SHAP; externally validated on 73 cases.
Main Results:
- The XGB model demonstrated high predictive performance (AUC: 0.916 training, 0.851 internal, 0.846 external validation).
- Key predictors identified: NT-proBNP, pH, PCT, LDH, WBC, creatinine, and platelet count.
- SHAP analysis confirmed the clinical significance of these predictors.
Conclusions:
- A reliable and interpretable machine learning model for predicting pediatric HF mortality has been developed.
- This model can facilitate early risk stratification and timely interventions.
- The model shows potential to improve outcomes for high-risk pediatric HF patients.
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.
More Related Videos
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
07:15Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
