Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Clinical Trial
. 2025 Jul 15:381:291-297.
doi: 10.1016/j.jad.2025.04.013. Epub 2025 Apr 3.

Prediction of remission of pharmacologically treated psychotic depression: A machine learning approach

Emily Carter  1 , Samprit Banerjee  2 , George S Alexopoulos  3 , Kathleen S Bingham  4 , Patricia Marino  3 , Barnett S Meyers  3 , Benoit H Mulsant  5 , Nicholas H Neufeld  5 , Anthony J Rothschild  6 , Aristotle N Voineskos  5 , Ellen M Whyte  7 , Alastair J Flint  8 ; STOP-PD II Study Group
Affiliations
Free article
Clinical Trial

Prediction of remission of pharmacologically treated psychotic depression: A machine learning approach

Emily Carter et al. J Affect Disord. .
Free article

Abstract

Background: The combination of antidepressant and antipsychotic medication is an effective treatment for major depressive disorder with psychotic features ('psychotic depression'). The present study aims to identify sociodemographic and clinical predictors of remission of psychotic depression treated with combination pharmacotherapy and determine the accuracy of prediction models.

Methods: Two hundred and sixty-nine participants aged 18 to 85 years with psychotic depression were acutely treated with protocolized sertraline plus olanzapine for up to 12 weeks. Three cross-validated machine learning models were implemented to predict remission based on 74 sociodemographic and clinical variables measured at acute baseline. The optimal model for each method was selected by the average fold C-index. Based on the performance of each method, grouped elastic net (cox) regression was chosen to examine the association of each predictor with remission of psychotic depression.

Results: Of the 269 participants, 145 (53.9 %) experienced full remission of the depressive episode and psychotic features. Multivariable models had 65.1 % to 67.4 % accuracy in predicting remission. In the grouped elastic net (cox) regression model, longer duration of index episode, somatic or tactile hallucinations, higher burden of comorbid physical problems, and single or divorced marital status were independent predictors of longer time to remission. A higher number of lifetime depressive episodes and peripheral vascular or cardiovascular disease were predictors of shorter time to remission.

Conclusions: Future research needs to determine whether the addition of biomarkers to clinical and sociodemographic variables can improve model accuracy in predicting remission of pharmacologically-treated psychotic depression.

Keywords: Clinical trial; Machine learning; Major depressive disorder with psychotic features; Prediction; Remission; Treatment.

PubMed Disclaimer

Conflict of interest statement

Declaration of competing interest E. Carter has no disclosures. S. Banerjee has received NIA, NIMH, and NHLBI grants. G.S. Alexopoulos has received NIMH grants and has served in the speakers bureau and advisory board of Otsuka. K.S. Bingham has received grant support from the Canadian Institutes of Health Research and the University of Toronto. P. Marino received research support from the NIMH at the time this work was done. B.S. Meyers received research support from the NIMH at the time this work was done. B.H. Mulsant holds and receives support from the Labatt Family Chair in Biology of Depression in Late-Life Adults at the University of Toronto. He currently receives or has received research support during the past three years from Brain Canada, the Canadian Institutes of Health Research, the CAMH Foundation, the Patient-Centered Outcomes Research Institute (PCORI), the US National Institute of Health (NIH), Capital Solution Design LLC (software used in a study founded by CAMH Foundation), and HAPPYneuron (software used in a study founded by Brain Canada). Within the past three years, he has also been an unpaid consultant to Myriad Neuroscience. N.H Neufeld has served on an advisory board for Boehringer Ingelheim. He has received grant support from the Brain and Behavior Research Foundation, Canadian Institutes of Health Research, Physicians' Services Incorporated Foundation, Labatt Family Network for Research on the Biology of Depression and the University of Toronto. A.J. Rothschild has received, in the past three years, grant or research support from Compass Pathways, Janssen, Otsuka, and the Irving S. and Betty Brudnick Endowed Chair in Psychiatry. In the past three years, he has been a consultant to Daiichi Sankyo, Inc., Sage Therapeutics, Xenon Pharmaceuticals, and Neumora Therapeutics. He has received royalties in the past three years for the Rothschild Scale for Antidepressant Tachyphylaxis (RSAT)®, Clinical Manual for the Diagnosis and Treatment of Psychotic Depression, American Psychiatric Press, 2009, The Evidence-Based Guide to Antipsychotic Medications, American Psychiatric Press, 2010, The Evidence-Based Guide to Antidepressant Medications, American Psychiatric Press, 2012, and from UpToDate®. A.N. Voineskos has received funding from the NIMH, Canadian Institutes of Health Research, Canada Foundation for Innovation, CAMH Foundation, and the University of Toronto. E.M. Whyte has received grant support from the NIMH and HRSA. A.J. Flint has received grant support from the U.S. National Institutes of Health, Patient-Centered Outcomes Research Institute, Canadian Institutes of Health Research, Brain Canada, Ontario Brain Institute, Alzheimer's Association, AGE-WELL, the Canadian Foundation for Healthcare Improvement, and the University of Toronto.

Publication types

MeSH terms

LinkOut - more resources