Longitudinally stable, brain-based predictive models mediate the relationships between childhood cognition and socio-demographic, psychological and genetic factors

Cognitive abilities are one of the major transdiagnostic domains in the National Institute of Mental Healths Research Domain Criteria (RDoC). Following RDoCs integrative approach, we aimed to develop brain-based predictive models for cognitive abilities that a) are developmentally stable over years during adolescence and b) account for the relationships between cognitive abilities and socio-demographic, psychological and genetic factors. For this, we leveraged the unique power of the large-scale, longitudinal data from the Adolescent Brain Cognitive Development (ABCD) study (n [~]11k) and combined MRI data across modalities (task-fMRI from three tasks, resting-state fMRI, structural MRI, DTI) using machine-learning. Our brain-based, predictive models for cognitive abilities were stable across two years during young adolescence and generalisable to different sites, partially predicting childhood cognition at around 20% of the variance. Moreover, our use of opportunistic stacking allowed the model to handle missing values, reducing the exclusion from around 80% to around 5% of the data. We found fronto-parietal networks during a working-memory task to drive childhood-cognition prediction. The brain-based, predictive models significantly, albeit partially, accounted for variance in childhood cognition due to (1) key socio-demographic and psychological factors (proportion mediated=18.65% [17.29%-20.12%]) and (2) genetic variation, as reflected by the polygenic score of cognition (proportion mediated=15.6% [11%-20.7%]). Thus, our brain-based predictive models for cognitive abilities facilitate the development of a robust, transdiagnostic research tool for cognition at the neural level in keeping with the RDoCs integrative framework. Key PointsO_LIUsing opportunistic stacking and multimodal MRI, we developed brain-based predictive models for childrens cognitive abilities that were longitudinally stable, generalisable to different sites and robust against missing data. C_LIO_LIOur brain-based models were able to partially mediate the relationships of childhood cognitive abilities with the socio-demographic, psychological and genetic factors. C_LIO_LIOur approach should pave the way for future researchers to employ multimodal MRI as a tool for the brain-based indicator of cognitive abilities, according to the integrative RDoC framework. C_LI