42. Identification and External Validation of a Problem Cannabis Use Neural Network

Cannabis is widely used and associated with clinically significant harms for a subset of users. Here, we (1) apply connectome-based predictive modelling (CPM)—a data-driven, whole-brain, machine-learning approach—to identify a neuromarker of problem-level cannabis use in a non-clinical sample of adolescents/emerging adults, and (2) validate the identified network in an independent clinical sample of individuals entering treatment for cannabis use.