Machine Learning Prediction of Obesity Development in Children With Overweight Using Longitudinal Body Composition Data
Authors' conclusion
Machine learning models demonstrated effective predictive performance for obesity in children with overweight. Incorporating standardised adiposity measures and growth velocity beyond static anthropometric data provides a robust framework for risk stratification in this high-risk population.
Study context
- Population
- Korean children aged 7–9 years with overweight (BMI between 85th and 95th percentiles)
- Participants
- 2,801 children
- Comparison
- Males vs Females
- Outcome
- Prediction of obesity (BMI ≥ 95th percentile), evaluated by AUROC
Methodological detailslongitudinal, machine learning (XGBoost), sex-stratified models, bootstrap validation, SHAP feature analysis
- Longitudinal
- Machine learning (XGBoost)
- Sex-stratified models
- Bootstrap validation
- SHAP feature analysis
Performance
As reported in the abstract
Model discrimination for obesity (AUROC)
Males
0.671
AUROC · 95% CI 0.619–0.721
Females
0.652
AUROC · 95% CI 0.589–0.700
Further findings
Obesity incidence during follow-up
Original publication
Machine Learning Prediction of Obesity Development in Children With Overweight Using Longitudinal Body Composition Data. Pediatr Obes. Published 18 March 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →