Building machine learning prediction models for wellbeing using predictors from the exposome and genome in a population cohort

Using longitudinal data of a large population cohort (Netherlands Twin Register; collected 1991-2022), we aim to build machine learning prediction models for adult wellbeing from the exposome and genome, and identify the most predictive factors (Ns between 702 and 5874). The specific exposome was captured by parent- and self-reports of psychosocial factors from childhood to adulthood, the genome by polygenic scores, and the general exposome by linkage of participants’ postal codes to objective, registry-based exposures. Not the genome (R2 = -.007) but the general exposome (R2 = .047) and especially the specific exposome (R2 = .702) were predictive of wellbeing in an independent test set. The genome and general exposome did not improve prediction beyond the specific exposome. Risk/protective factors such as optimism, personality, social support, and neighborhood housing characteristics were most predictive. Our findings highlight the importance of longitudinal monitoring and promises of different data modalities for wellbeing prediction.