Combining clinical variables to optimize prediction of antidepressant treatment outcomes

Iniesta, Raquel and Malki, Karim and Maier, Wolfgang and Rietschel, Marcella and Mors, Ole and Hauser, Joanna and Henigsberg, Neven and Dernovsek, Mojca Zvezdana and Souery, Daniel and Stahl, Daniel and Dobson, Richard and Aitchison, Katherine J. and Farmer, Anne and Lewis, Cathryn M. and McGuffin, Peter and Uher, Rudolf (2016) Combining clinical variables to optimize prediction of antidepressant treatment outcomes. Journal of Psychiatric Research, 78. pp. 94-102. ISSN 0022-3956

[img] PDF - Published Version
Download (535kB)


The outcome of treatment with antidepressants varies markedly across people with the same diagnosis. A clinically significant prediction of outcomes could spare the frustration of trial and error approach and improve the outcomes of major depressive disorder through individualized treatment selection. It is likely that a combination of multiple predictors is needed to achieve such prediction. We used elastic net regularized regression to optimize prediction of symptom improvement and remission during treatment with escitalopram or nortriptyline and to identify contributing predictors from a range of demographic and clinical variables in 793 adults with major depressive disorder. A combination of demographic and clinical variables, with strong contributions from symptoms of depressed mood, reduced interest, decreased activity, indecisiveness, pessimism and anxiety significantly predicted treatment outcomes, explaining 5-10% of variance in symptom improvement with escitalopram. Similar combinations of variables predicted remission with area under the curve 0.72, explaining approximately 15% of variance (pseudo R(2)) in who achieves remission, with strong contributions from body mass index, appetite, interest-activity symptom dimension and anxious-somatizing depression subtype. Escitalopram-specific outcome prediction was more accurate than generic outcome prediction, and reached effect sizes that were near or above a previously established benchmark for clinical significance. Outcome prediction on the nortriptyline arm did not significantly differ from chance. These results suggest that easily obtained demographic and clinical variables can predict therapeutic response to escitalopram with clinically meaningful accuracy, suggesting a potential for individualized prescription of this antidepressant drug.

Item Type: Article
Additional Information: © 2016 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (
MeSH: Age Factors ; Antidepressive Agents/therapeutic use ; Area Under Curve ; Body Mass Index ; Citalopram/therapeutic use ; Depressive Disorder, Major/diagnosis ; Depressive Disorder, Major/drug therapy ; Depressive Disorder, Major/epidemiology ; Depressive Disorder, Major/physiopathology ; Female ; Humans ; Machine Learning ; Male ; Nortriptyline/therapeutic use ; Personality ; Precision Medicine ; Prognosis ; Psychiatric Status Rating Scales ; Regression Analysis ; Treatment Outcome
Departments: Hrvatski institut za istraživanje mozga
Katedra za psihijatriju i psihološku medicinu
Depositing User: Martina Žužak
Status: Published
Iniesta, RaquelUNSPECIFIED
Maier, WolfgangUNSPECIFIED
Rietschel, MarcellaUNSPECIFIED
Henigsberg, NevenUNSPECIFIED
Dernovsek, Mojca ZvezdanaUNSPECIFIED
Dobson, RichardUNSPECIFIED
Aitchison, Katherine J.UNSPECIFIED
Lewis, Cathryn M.UNSPECIFIED
Date: July 2016
Date Deposited: 04 Oct 2017 09:49
Last Modified: 11 Aug 2020 07:58
Related URLs:

Actions (login required)

View Item View Item


Downloads per month over past year