Extended Data Fig. 2: Interpretability and stratification.

a, Sankey diagram showing the relative feature importance (SHapley Additive exPlanations [SHAP] values) for each of the proposed nonlinear XGBoost models for direct regression. b,c, Qualitative evaluation of learned latent space’s interpretability of learning important features. The t-SNE reduced latent space shows that individuals with higher BMI (b) and RHR (c) are clustered closely together in space, following our quantitative results of classifying high BMI and high-RHR individuals using these learned representations. d,e, Distribution of individuals stratified by IR class and BMI classes (d) and IR versus physical activity classes as determined by number of daily steps (e). f, Results of classification performance for various lifestyle stratifications.