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

Barnaby Nelson; Alison R. Yung; Patrick D. McGorry

doi:10.1001/jamapsychiatry.2018.4234

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

Barnaby Nelson, PhD^1,2; Alison R. Yung, MD, FRANZCP^1,2; Patrick D. McGorry, MD, PhD, FRCP, FRANZCP^1,2

Author Affiliations Article Information

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.

Full Text

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

Others Also Liked

Featured Articles

USPSTF Recommendation Statements

Blogs

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

Citation

Download citation file:

Others Also Liked

Select Your Interests