Machine Learning for Childhood Obesity Risk Prediction: A Critical Review of Design and Validation Practices, with a Translational Framework for Peruvian Schoolchildren
Authors:
- William J. Marin-RodriguezWilliam J. Marin-Rodriguez
- Víctor H. Guadalupe-MoriVGVíctor H. Guadalupe-Mori
- Rubén A. Rayme-SerranoRRRubén A. Rayme-Serrano
- Jenny M. Zavaleta-OliverJZJenny M. Zavaleta-Oliver
- Sandy S. Altamirano-CáceresSASandy S. Altamirano-Cáceres
- Alexia F. Geldres-ChávezAGAlexia F. Geldres-Chávez
- Marcelo R. Bedoya-OstolazaMBMarcelo R. Bedoya-Ostolaza
Preprint
- 6 October 2026
- preprint
- Published by MDPI AG in Preprints.org
Abstract
Machine-learning methods are increasingly applied to childhood obesity risk assessment, yet feature selection, validation strategy, calibration, and benchmarking against simpler models remain inconsistently reported. This critical review examines thirteen primary model-development studies (predominantly pediatric), distinguishing genuinely prospective prediction from cross-sectional classification: only four used baseline predictors to forecast a later outcome in the same children. Two systematic reviews corroborate these concerns; this review extends that evidence by integrating target-leakage analysis with digital-health usability evidence into a pre-specified, falsifiable implementation framework. Identified concerns include target leakage from outcome-constitutive anthropometric predictors, limited independent or temporal validation, sparse calibration reporting, and inconsistent superiority of machine learning over logistic regression. We also review digital-health interventions and usability assessment via the System Usability Scale. Building on these findings, we propose a two-phase translational framework for Peruvian schoolchildren, specifying VIANEV as the primary individual-level dataset with area-level contextual enrichment from ENDES and INS/MINSA. We would evaluate candidate models (logistic regression, decision trees, random forest, XGBoost) through nested cross-validation with training-fold-only preprocessing, a sealed external validation set treated as a deployment gate, calibration and subgroup-fairness assessment, and pre-specified stopping criteria. The framework guides future development of transparent, context-sensitive, school-based decision-support systems while explicitly distinguishing cross-sectional risk classification from prospective prediction.Keywords
All Related Versions
- Version 1, 2026-10-06, Preprints
- Published version: Algorithms, 19 (11), 958.
This publication has 38 references indexed in Scilit:
- Comparing logistic regression and machine learning for obesity risk prediction: A systematic review and meta-analysisInternational Journal of Medical Informatics, 2025
- Predicting the onset of overweight in Chinese high school students: a machine-learning approach in a one-year prospective cohort studyEndocrine, 2024
- Prediction models for children/adolescents with obesity/overweight: A systematic review and meta-analysisPreventive Medicine, 2023
- Leakage and the reproducibility crisis in machine-learning-based sciencePatterns, 2023
- Ultra-processed food consumption and the incidence of obesity in two cohorts of Latin-American young children: A longitudinal studyJournal of Pediatric Nursing, 2023
- Effectiveness of mobile health interventions targeting parents to prevent and treat childhood Obesity: Systematic reviewPreventive Medicine Reports, 2022
- A machine learning approach for obesity risk predictionCurrent Research in Behavioral Sciences, 2021
- Prediction of early childhood obesity with machine learning and electronic health record dataInternational Journal of Medical Informatics, 2021
- Dataset for estimation of obesity levels based on eating habits and physical condition in individuals from Colombia, Peru and MexicoData in Brief, 2019
- Minimum sample size for developing a multivariable prediction model: PART II ‐ binary and time‐to‐event outcomesStatistics in Medicine, 2018