Development of a model to predict antidepressant treatment response for depression among Veterans.
Antidepressant medication
Veterans Health Administration
clinical decision support
depression
machine learning
treatment response
Journal
Psychological medicine
ISSN: 1469-8978
Titre abrégé: Psychol Med
Pays: England
ID NLM: 1254142
Informations de publication
Date de publication:
08 2023
08 2023
Historique:
pmc-release:
01
02
2024
medline:
1
9
2023
pubmed:
31
8
2023
entrez:
31
8
2023
Statut:
ppublish
Résumé
Only a limited number of patients with major depressive disorder (MDD) respond to a first course of antidepressant medication (ADM). We investigated the feasibility of creating a baseline model to determine which of these would be among patients beginning ADM treatment in the US Veterans Health Administration (VHA). A 2018-2020 national sample of In total, 35.7% of patients responded to treatment. The prediction model had an area under the ROC curve (s.e.) of 0.66 (0.04) in the test sample. A strong gradient in probability (s.e.) of treatment response was found across three subsamples of the test sample using training sample thresholds for high [45.6% (5.5)], intermediate [34.5% (7.6)], and low [11.1% (4.9)] probabilities of response. Baseline symptom severity, comorbidity, treatment characteristics (expectations, history, and aspects of current treatment), and protective/resilience factors were the most important predictors. Although these results are promising, parallel models to predict response to alternative treatments based on data collected before initiating treatment would be needed for such models to help guide treatment selection.
Sections du résumé
BACKGROUND
Only a limited number of patients with major depressive disorder (MDD) respond to a first course of antidepressant medication (ADM). We investigated the feasibility of creating a baseline model to determine which of these would be among patients beginning ADM treatment in the US Veterans Health Administration (VHA).
METHODS
A 2018-2020 national sample of
RESULTS
In total, 35.7% of patients responded to treatment. The prediction model had an area under the ROC curve (s.e.) of 0.66 (0.04) in the test sample. A strong gradient in probability (s.e.) of treatment response was found across three subsamples of the test sample using training sample thresholds for high [45.6% (5.5)], intermediate [34.5% (7.6)], and low [11.1% (4.9)] probabilities of response. Baseline symptom severity, comorbidity, treatment characteristics (expectations, history, and aspects of current treatment), and protective/resilience factors were the most important predictors.
CONCLUSIONS
Although these results are promising, parallel models to predict response to alternative treatments based on data collected before initiating treatment would be needed for such models to help guide treatment selection.
Identifiants
pubmed: 37650342
doi: 10.1017/S0033291722001982
pii: S0033291722001982
pmc: PMC10519376
mid: NIHMS1928674
doi:
Substances chimiques
Antidepressive Agents
0
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Research Support, U.S. Gov't, Non-P.H.S.
Langues
eng
Sous-ensembles de citation
IM
Pagination
5001-5011Subventions
Organisme : HSRD VA
ID : IK2 HX002867
Pays : United States
Organisme : NIMH NIH HHS
ID : R01 MH121478
Pays : United States
Références
J Affect Disord. 2021 Jul 1;290:227-236
pubmed: 34004405
J Affect Disord. 2021 Nov 1;294:864-867
pubmed: 34378538
Int J Geriatr Psychiatry. 2018 Dec;33(12):1596-1603
pubmed: 30035325
Lancet. 2018 Apr 7;391(10128):1357-1366
pubmed: 29477251
J Affect Disord. 2018 Dec 1;241:519-532
pubmed: 30153635
Stat Med. 2019 Sep 20;38(21):4051-4065
pubmed: 31270850
J Behav Health Serv Res. 2019 Jul;46(3):521-532
pubmed: 29948573
Front Psychiatry. 2020 May 25;11:472
pubmed: 32523557
J Clin Psychopharmacol. 2021 Sep-Oct 01;41(5):579-584
pubmed: 34183490
J Affect Disord. 2019 Jan 15;243:503-515
pubmed: 30286415
Psychol Med. 2023 Mar;53(4):1583-1591
pubmed: 37010212
Lancet. 2020 Oct 17;396(10258):1204-1222
pubmed: 33069326
J Affect Disord. 2019 May 1;250:419-424
pubmed: 30878654
Lancet Psychiatry. 2021 Jun;8(6):500-511
pubmed: 33957075
J Am Board Fam Med. 2021 Mar-Apr;34(2):268-290
pubmed: 33832996
Assessment. 2020 Jun;27(4):840-854
pubmed: 29457474
Transl Psychiatry. 2019 Apr 3;9(1):127
pubmed: 30944309
Psychiatry Investig. 2020 Mar;17(3):193-206
pubmed: 32160691
BMJ Open. 2019 Jun 17;9(6):e026712
pubmed: 31213446
Ann Intern Med. 2016 Mar 1;164(5):350-9
pubmed: 26857948
BJPsych Open. 2021 May 14;7(3):e101
pubmed: 33988121
Neuropsychiatr Dis Treat. 2018 Sep 26;14:2473-2484
pubmed: 30310285
Biol Psychiatry. 2003 Sep 1;54(5):573-83
pubmed: 12946886
Am J Psychiatry. 2018 Dec 1;175(12):1187-1198
pubmed: 30220219
J Psychiatr Res. 2019 Apr;111:59-67
pubmed: 30677646
Br J Surg. 2015 Feb;102(3):148-58
pubmed: 25627261
World Psychiatry. 2020 Feb;19(1):92-107
pubmed: 31922679
J Affect Disord. 2012 Mar;137(1-3):61-9
pubmed: 22244377
Front Psychol. 2017 Feb 21;8:233
pubmed: 28270786
Front Psychiatry. 2019 May 31;10:365
pubmed: 31214057
Dialogues Clin Neurosci. 2006;8(2):151-61
pubmed: 16889102
World Psychiatry. 2020 Oct;19(3):269-293
pubmed: 32931110
J Clin Psychiatry. 2013 Jun;74(6):595-602
pubmed: 23842011
JAMA Psychiatry. 2019 Aug 1;76(8):810-817
pubmed: 31017627
Int J Biostat. 2016 May 1;12(1):203-18
pubmed: 27227721
World Psychiatry. 2021 Jun;20(2):154-170
pubmed: 34002503
Psychol Med. 2021 May;51(7):1068-1081
pubmed: 33849685
Diagn Progn Res. 2022 Jan 11;6(1):1
pubmed: 35016734
Fam Syst Health. 2019 Mar;37(1):68-73
pubmed: 30614723
Am J Epidemiol. 2004 Apr 1;159(7):702-6
pubmed: 15033648
Neuropsychiatr Dis Treat. 2018 Aug 14;14:2087-2097
pubmed: 30147321
Hum Brain Mapp. 2019 Oct 15;40(15):4487-4507
pubmed: 31313451
Stat Med. 2014 Feb 10;33(3):517-35
pubmed: 24002997
Psychol Med. 2023 Jan;53(2):408-418
pubmed: 33952358
J Affect Disord. 2022 Feb 15;299:298-308
pubmed: 34920035
J Affect Disord. 2022 Mar 1;300:377-384
pubmed: 34953925
JAMA Psychiatry. 2021 Dec 1;78(12):1384-1390
pubmed: 34550327
JAMA Psychiatry. 2021 Nov 1;78(11):1228-1237
pubmed: 34468741
Int J Psychiatry Med. 1997;27(2):93-105
pubmed: 9565717
Acta Psychiatr Scand. 2021 May;143(5):392-405
pubmed: 33548056
Psychotherapy (Chic). 2018 Dec;55(4):473-485
pubmed: 30335459
J Affect Disord. 2021 Dec 1;295:1489-1493
pubmed: 34565598
Am Fam Physician. 2009 Jul 15;80(2):167-72
pubmed: 19621857