Longitudinal Prediction of BMI using Explainable AI: Integrating Polygenic Scores, Maternal, Early-Life and Familial Factors

Background/ObjectivesThis study aimed to predict body mass index (BMI) trajectories from childhood to early adulthood using explainable artificial intelligence, integrating polygenic scores (PGS), maternal, early-life, and familial factors to identify key predictors of obesity risk and inform prevention strategies. Subjects/MethodsWe analysed longitudinal data from the Raine Study Gen2 cohort, recruiting 2 868 participants. This observational study, without randomization or case-control design, collected BMI measurements at ages 8, 10, 14, 17, 20, 23, and 27 years. We applied Kolmogorov-Arnold Networks (KAN) alongside conventional machine learning models, integrating epidemiological variables (maternal and paternal anthropometrics, parental education, early-life skinfold measurements) with seven BMI-related PGS. The analysis spanned from childhood to early adulthood, with no intervention administered. ResultsThe KAN model, combining epidemiological and PGS data, achieved predictive performance with R{superscript 2} ranging from 0.81 at age 8 to 0.34 at age 27. BMI z-score at age 5 was the dominant predictor in early years, with PGS influence increasing post-adolescence. Maternal and paternal anthropometric measures, parental education, and early-life skinfold measurements were significant contributors. The interpretable KAN model revealed the dynamic interplay of genetic and environmental factors, with early-life BMI z-score and PGS emerging as key drivers of BMI trajectories across life stages. ConclusionsThese findings highlight the dynamic interplay of genetic and environmental factors across life stages, underscoring the potential of early-life BMI as a biomarker for obesity risk. Our interpretable model offers actionable insights for targeted obesity prevention strategies.