Multidimensional Analysis of Early Adiposity Rebound Determinants in Children: Two Key “1000 Days”
Study context
- Population
- Parent-offspring trios in the Ma'anshan Birth Cohort (MABC), serial BMI from birth through school age; early adiposity rebound (early AR (EAR)) = adiposity rebound (AR) timing ≤ sex-specific 25th percentile (≤ 55.46 months in boys, ≤ 60.54 months in girls)
- Participants
- 2,072 parent-offspring trios
- Outcome
- Determinants of early adiposity rebound (EAR) and a predictive model
Methodological detailsMa'anshan Birth Cohort, linear mixed models for individual growth curves, 10 machine learning techniques and SHAP, 65 potential factors from maternal, pregnancy, paternal and offspring sources
- Ma'anshan Birth Cohort
- Linear mixed models for individual growth curves
- 10 machine learning techniques and SHAP
- 65 potential factors from maternal, pregnancy, paternal and offspring sources
Main finding
As reported in the abstract
Categorical boosting model (best of 10 ML models), AUC training
0.764
95% CI 0.733–0.795
Categorical boosting model, AUC testing
0.721
95% CI 0.669–0.773
Observational data: associations, not effects.
Original publication
Multidimensional Analysis of Early Adiposity Rebound Determinants in Children: Two Key “1000 Days”. Obesity (Silver Spring). Published 19 August 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →