Importance of Variable Selection in Multimodal Prediction Models in Patients at Clinical High Risk for Psychosis and Recent-Onset Depression

To the Editor Koutsouleris and colleagues present a sophisticated and valuable analysis of functional outcomes in patients at clinical high risk for psychosis and recent-onset depression. Three machine learning prediction models (a clinical model, a neuroimaging model, and a combined model) were trained to predict social and role-functioning outcomes in these 2 samples. The models were also compared with expert rater prognosis of functional outcomes.

Source: JAMA Psychiatry - February 6, 2019 Category: Psychiatry Source Type: research