Cross-trial prediction of treatment outcome in depression: A machine learning approach

Adam Mourad Chekroud, Ryan Joseph Zotti, Zarrar Shehzad, Ralitza Gueorguieva, Marcia K. Johnson, Madhukar H. Trivedi, Tyrone D. Cannon, John Harrison Krystal, Philip Robert Corlett

Research output: Contribution to journalArticle

134 Citations (Scopus)

Abstract

Background: Antidepressant treatment efficacy is low, but might be improved by matching patients to interventions. At present, clinicians have no empirically validated mechanisms to assess whether a patient with depression will respond to a specific antidepressant. We aimed to develop an algorithm to assess whether patients will achieve symptomatic remission from a 12-week course of citalopram. Methods: We used patient-reported data from patients with depression (n=4041, with 1949 completers) from level 1 of the Sequenced Treatment Alternatives to Relieve Depression (STAR*D; ClinicalTrials.gov, number NCT00021528) to identify variables that were most predictive of treatment outcome, and used these variables to train a machine-learning model to predict clinical remission. We externally validated the model in the escitalopram treatment group (n=151) of an independent clinical trial (Combining Medications to Enhance Depression Outcomes [COMED]; ClinicalTrials.gov, number NCT00590863). Findings: We identified 25 variables that were most predictive of treatment outcome from 164 patient-reportable variables, and used these to train the model. The model was internally cross-validated, and predicted outcomes in the STAR*D cohort with accuracy significantly above chance (64·6% [SD 3·2]; p

Original languageEnglish (US)
Pages (from-to)243-250
Number of pages8
JournalThe Lancet Psychiatry
Volume3
Issue number3
DOIs
StatePublished - Mar 1 2016

Fingerprint

Citalopram
Antidepressive Agents
Machine Learning
Clinical Trials
Therapeutics

ASJC Scopus subject areas

  • Psychiatry and Mental health
  • Biological Psychiatry

Cite this

Chekroud, A. M., Zotti, R. J., Shehzad, Z., Gueorguieva, R., Johnson, M. K., Trivedi, M. H., ... Corlett, P. R. (2016). Cross-trial prediction of treatment outcome in depression: A machine learning approach. The Lancet Psychiatry, 3(3), 243-250. https://doi.org/10.1016/S2215-0366(15)00471-X

Cross-trial prediction of treatment outcome in depression : A machine learning approach. / Chekroud, Adam Mourad; Zotti, Ryan Joseph; Shehzad, Zarrar; Gueorguieva, Ralitza; Johnson, Marcia K.; Trivedi, Madhukar H.; Cannon, Tyrone D.; Krystal, John Harrison; Corlett, Philip Robert.

In: The Lancet Psychiatry, Vol. 3, No. 3, 01.03.2016, p. 243-250.

Research output: Contribution to journalArticle

Chekroud, AM, Zotti, RJ, Shehzad, Z, Gueorguieva, R, Johnson, MK, Trivedi, MH, Cannon, TD, Krystal, JH & Corlett, PR 2016, 'Cross-trial prediction of treatment outcome in depression: A machine learning approach', The Lancet Psychiatry, vol. 3, no. 3, pp. 243-250. https://doi.org/10.1016/S2215-0366(15)00471-X
Chekroud, Adam Mourad ; Zotti, Ryan Joseph ; Shehzad, Zarrar ; Gueorguieva, Ralitza ; Johnson, Marcia K. ; Trivedi, Madhukar H. ; Cannon, Tyrone D. ; Krystal, John Harrison ; Corlett, Philip Robert. / Cross-trial prediction of treatment outcome in depression : A machine learning approach. In: The Lancet Psychiatry. 2016 ; Vol. 3, No. 3. pp. 243-250.
@article{04bf9ec1cc7a4c6b97451b35975165dc,
title = "Cross-trial prediction of treatment outcome in depression: A machine learning approach",
abstract = "Background: Antidepressant treatment efficacy is low, but might be improved by matching patients to interventions. At present, clinicians have no empirically validated mechanisms to assess whether a patient with depression will respond to a specific antidepressant. We aimed to develop an algorithm to assess whether patients will achieve symptomatic remission from a 12-week course of citalopram. Methods: We used patient-reported data from patients with depression (n=4041, with 1949 completers) from level 1 of the Sequenced Treatment Alternatives to Relieve Depression (STAR*D; ClinicalTrials.gov, number NCT00021528) to identify variables that were most predictive of treatment outcome, and used these variables to train a machine-learning model to predict clinical remission. We externally validated the model in the escitalopram treatment group (n=151) of an independent clinical trial (Combining Medications to Enhance Depression Outcomes [COMED]; ClinicalTrials.gov, number NCT00590863). Findings: We identified 25 variables that were most predictive of treatment outcome from 164 patient-reportable variables, and used these to train the model. The model was internally cross-validated, and predicted outcomes in the STAR*D cohort with accuracy significantly above chance (64·6{\%} [SD 3·2]; p",
author = "Chekroud, {Adam Mourad} and Zotti, {Ryan Joseph} and Zarrar Shehzad and Ralitza Gueorguieva and Johnson, {Marcia K.} and Trivedi, {Madhukar H.} and Cannon, {Tyrone D.} and Krystal, {John Harrison} and Corlett, {Philip Robert}",
year = "2016",
month = "3",
day = "1",
doi = "10.1016/S2215-0366(15)00471-X",
language = "English (US)",
volume = "3",
pages = "243--250",
journal = "The Lancet Psychiatry",
issn = "2215-0366",
publisher = "Elsevier Limited",
number = "3",

}

TY - JOUR

T1 - Cross-trial prediction of treatment outcome in depression

T2 - A machine learning approach

AU - Chekroud, Adam Mourad

AU - Zotti, Ryan Joseph

AU - Shehzad, Zarrar

AU - Gueorguieva, Ralitza

AU - Johnson, Marcia K.

AU - Trivedi, Madhukar H.

AU - Cannon, Tyrone D.

AU - Krystal, John Harrison

AU - Corlett, Philip Robert

PY - 2016/3/1

Y1 - 2016/3/1

N2 - Background: Antidepressant treatment efficacy is low, but might be improved by matching patients to interventions. At present, clinicians have no empirically validated mechanisms to assess whether a patient with depression will respond to a specific antidepressant. We aimed to develop an algorithm to assess whether patients will achieve symptomatic remission from a 12-week course of citalopram. Methods: We used patient-reported data from patients with depression (n=4041, with 1949 completers) from level 1 of the Sequenced Treatment Alternatives to Relieve Depression (STAR*D; ClinicalTrials.gov, number NCT00021528) to identify variables that were most predictive of treatment outcome, and used these variables to train a machine-learning model to predict clinical remission. We externally validated the model in the escitalopram treatment group (n=151) of an independent clinical trial (Combining Medications to Enhance Depression Outcomes [COMED]; ClinicalTrials.gov, number NCT00590863). Findings: We identified 25 variables that were most predictive of treatment outcome from 164 patient-reportable variables, and used these to train the model. The model was internally cross-validated, and predicted outcomes in the STAR*D cohort with accuracy significantly above chance (64·6% [SD 3·2]; p

AB - Background: Antidepressant treatment efficacy is low, but might be improved by matching patients to interventions. At present, clinicians have no empirically validated mechanisms to assess whether a patient with depression will respond to a specific antidepressant. We aimed to develop an algorithm to assess whether patients will achieve symptomatic remission from a 12-week course of citalopram. Methods: We used patient-reported data from patients with depression (n=4041, with 1949 completers) from level 1 of the Sequenced Treatment Alternatives to Relieve Depression (STAR*D; ClinicalTrials.gov, number NCT00021528) to identify variables that were most predictive of treatment outcome, and used these variables to train a machine-learning model to predict clinical remission. We externally validated the model in the escitalopram treatment group (n=151) of an independent clinical trial (Combining Medications to Enhance Depression Outcomes [COMED]; ClinicalTrials.gov, number NCT00590863). Findings: We identified 25 variables that were most predictive of treatment outcome from 164 patient-reportable variables, and used these to train the model. The model was internally cross-validated, and predicted outcomes in the STAR*D cohort with accuracy significantly above chance (64·6% [SD 3·2]; p

UR - http://www.scopus.com/inward/record.url?scp=84959571586&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84959571586&partnerID=8YFLogxK

U2 - 10.1016/S2215-0366(15)00471-X

DO - 10.1016/S2215-0366(15)00471-X

M3 - Article

C2 - 26803397

AN - SCOPUS:84959571586

VL - 3

SP - 243

EP - 250

JO - The Lancet Psychiatry

JF - The Lancet Psychiatry

SN - 2215-0366

IS - 3

ER -