Machine learning-based prediction of bronchiolitis in children under two years: a multicenter study within a single
Raoof Nopour1, Saeed Barzegari2, Mostafa Shanbehzadeh3
1Social Determinants of Health Research Center, Semnan University of Medical Sciences, Semnan, Iran. nopour.r70@gmail.com.
Insights
Machine learning accurately predicts infant bronchiolitis risk using clinical and socioeconomic data. Interpretable AI identifies high-risk infants for early intervention and resource allocation.
Area of Science:
- Pediatric Medicine
- Computational Biology
- Public Health
Background:
- Bronchiolitis is a major cause of infant hospitalization, posing a challenge for early risk prediction.
- Traditional models struggle with complex interactions and lack clinical transparency.
Purpose of the Study:
- Develop, validate, and interpret machine learning (ML) models for predicting infant bronchiolitis risk.
- Utilize clinical and socioeconomic determinants for enhanced predictive accuracy.
Main Methods:
- Retrospective analysis of 1,260 children across 5 pediatric centers.
- Applied 8 ML algorithms, including ensemble methods, with rigorous data preprocessing and imputation.
- Evaluated performance using AUC, confusion matrices, Decision Curve Analysis (DCA), and calibration plots.
- Employed Explainable AI (XAI) with Shapley Additive exPlanations (SHAP) for model interpretation.
Main Results:
- XGBoost model achieved an AUC of 0.863, outperforming base learners.
- DCA and calibration plots confirmed XGBoost's superior clinical utility and accuracy.
- SHAP analysis revealed overcrowding, malnutrition, and maternal smoking as key predictors.
Conclusions:
- Integrated XGBoost and SHAP offer a robust, transparent framework for early bronchiolitis prediction.
- The model supports early triage and resource allocation for high-risk infants.
- Facilitates a shift towards precision pediatric medicine through interpretable AI.
Background:
Bronchiolitis is a leading cause of hospitalization in infants, yet early and accurate risk prediction remains a clinical challenge. Traditional models often lack the complexity to capture nonlinear interactions or the transparency required for clinical trust.
Objective:
This multicenter study aimed to develop, validate, and interpret machine learning (ML) models for predicting bronchiolitis risk in children under two years of age using clinical and socioeconomic determinants.
Methods:
In this retrospective study, data from 1,260 children (529 with bronchiolitis and 731 without) were collected at 5 pediatric centers within a single metropolitan area, from January 2023 through December 2024. Seventeen predictors were analyzed. After rigorous preprocessing and K-NN imputation, eight ML algorithms, including four base learners and four ensemble methods, were developed. Model performance was evaluated using AUC and metrics derived from confusion matrices. Clinical utility was assessed via Decision Curve Analysis (DCA) and calibration plots. Explainable AI (XAI) was implemented using Shapley Additive exPlanations (SHAP) to interpret model decisions.
Results:
XGBoost achieved an AUC of 0.863 [0.828-0.897] in the test set, demonstrating higher predictive performance than base learners such as NB (AUC: 0.583 [0.529-0.638]). DCA and calibration plots confirmed that XGBoost provides superior net benefit and calibration performance across a range of threshold probabilities. SHAP analysis identified overcrowding, severe acute malnutrition, and maternal smoking as the most influential predictors, highlighting the critical role of socioeconomic and environmental factors in disease susceptibility.
Conclusion:
The integration of XGBoost with SHAP values provides a robust, transparent, and clinically actionable framework for early prediction of bronchiolitis based on variables available at initial clinical presentation. By identifying high-risk infants through interpretable AI, this model supports early triage and optimized resource allocation, fostering the transition toward precision pediatric medicine.
Clinical Trial Number:
Not applicable.