[Skip to Navigation]
Comment & Response
February 6, 2019

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

Author Affiliations
  • 1Orygen, The National Centre of Excellence in Youth Mental Health, University of Melbourne, Melbourne, Australia
  • 2Centre for Youth Mental Health, The University of Melbourne, Melbourne, Australia
JAMA Psychiatry. 2019;76(3):339. doi:10.1001/jamapsychiatry.2018.4234

To the Editor Koutsouleris and colleagues1 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.

Add or change institution