Cannabis has been identified as one of the major risk factors for developing psychosis. Recent studies show that up to 50 % of all patients with cannabis-induced psychosis (CIP) continue to develop a permanent form of a psychotic disorder. Therefore, the aim of the present project is to set up a longitudinal, multimodal neuroimaging study of patients with CIP, including structural and functional neuroimaging at baseline as well as a follow up to record the clinical outcome of patients. By employing novel machine learning tools on such multimodal, longitudinal data, we hope to shed light on the neurobiological basis of cannabis-induced psychosis and to develop clinical tools that allow personalised prediction of outcome in individual patients.