Diagnostic and Predictive Neuroimaging Biomarkers for Posttraumatic Stress Disorder.
Machine learning
Major depressive disorder
Posttraumatic stress disorder
Resting-state functional MRI
Support vector machine
Treatment outcome
fMRI classification
Journal
Biological psychiatry. Cognitive neuroscience and neuroimaging
ISSN: 2451-9030
Titre abrégé: Biol Psychiatry Cogn Neurosci Neuroimaging
Pays: United States
ID NLM: 101671285
Informations de publication
Date de publication:
07 2020
07 2020
Historique:
received:
21
12
2019
revised:
29
03
2020
accepted:
30
03
2020
pubmed:
9
6
2020
medline:
10
3
2021
entrez:
9
6
2020
Statut:
ppublish
Résumé
Comorbidity between posttraumatic stress disorder (PTSD) and major depressive disorder (MDD) has been commonly overlooked by studies examining resting-state functional connectivity patterns in PTSD. The current study used a data-driven approach to identify resting-state functional connectivity biomarkers to 1) differentiate individuals with PTSD (with or without MDD) from trauma-exposed healthy control subjects (TEHCs), 2) compare individuals with PTSD alone with those with comorbid PTSD+MDD, and 3) explore the clinical utility of the identified biomarkers by testing their associations with clinical symptoms and treatment response. Resting-state magnetic resonance images were obtained from 51 individuals with PTSD alone, 52 individuals with PTSD+MDD, and 76 TEHCs. Of the 103 individuals with PTSD, 55 were enrolled in prolonged exposure treatment. A support vector machine model was used to identify resting-state functional connectivity biomarkers differentiating individuals with PTSD (with or without MDD) from TEHCs and differentiating individuals with PTSD alone from those with PTSD+MDD. The associations between the identified features and symptomatology were tested with Pearson correlations. The support vector machine model achieved 70.6% accuracy in discriminating between individuals with PTSD and TEHCs and achieved 76.7% accuracy in discriminating between individuals with PTSD alone and those with PTSD+MDD for out-of-sample prediction. Within-network connectivity in the executive control network, prefrontal network, and salience network discriminated individuals with PTSD from TEHCs. The basal ganglia network played an important role in differentiating individuals with PTSD alone from those with PTSD+MDD. PTSD scores were inversely correlated with within-executive control network connectivity (p < .001), and executive control network connectivity was positively correlated with treatment response (p < .001). Results suggest that unique brain-based abnormalities differentiate individuals with PTSD from TEHCs, differentiate individuals with PTSD from those with PTSD+MDD, and demonstrate clinical utility in predicting levels of symptomatology and treatment response.
Sections du résumé
BACKGROUND
Comorbidity between posttraumatic stress disorder (PTSD) and major depressive disorder (MDD) has been commonly overlooked by studies examining resting-state functional connectivity patterns in PTSD. The current study used a data-driven approach to identify resting-state functional connectivity biomarkers to 1) differentiate individuals with PTSD (with or without MDD) from trauma-exposed healthy control subjects (TEHCs), 2) compare individuals with PTSD alone with those with comorbid PTSD+MDD, and 3) explore the clinical utility of the identified biomarkers by testing their associations with clinical symptoms and treatment response.
METHODS
Resting-state magnetic resonance images were obtained from 51 individuals with PTSD alone, 52 individuals with PTSD+MDD, and 76 TEHCs. Of the 103 individuals with PTSD, 55 were enrolled in prolonged exposure treatment. A support vector machine model was used to identify resting-state functional connectivity biomarkers differentiating individuals with PTSD (with or without MDD) from TEHCs and differentiating individuals with PTSD alone from those with PTSD+MDD. The associations between the identified features and symptomatology were tested with Pearson correlations.
RESULTS
The support vector machine model achieved 70.6% accuracy in discriminating between individuals with PTSD and TEHCs and achieved 76.7% accuracy in discriminating between individuals with PTSD alone and those with PTSD+MDD for out-of-sample prediction. Within-network connectivity in the executive control network, prefrontal network, and salience network discriminated individuals with PTSD from TEHCs. The basal ganglia network played an important role in differentiating individuals with PTSD alone from those with PTSD+MDD. PTSD scores were inversely correlated with within-executive control network connectivity (p < .001), and executive control network connectivity was positively correlated with treatment response (p < .001).
CONCLUSIONS
Results suggest that unique brain-based abnormalities differentiate individuals with PTSD from TEHCs, differentiate individuals with PTSD from those with PTSD+MDD, and demonstrate clinical utility in predicting levels of symptomatology and treatment response.
Identifiants
pubmed: 32507508
pii: S2451-9022(20)30080-X
doi: 10.1016/j.bpsc.2020.03.010
pmc: PMC7354213
mid: NIHMS1584183
pii:
doi:
Substances chimiques
Biomarkers
0
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
688-696Subventions
Organisme : NIMH NIH HHS
ID : K01 MH122774
Pays : United States
Organisme : NIMH NIH HHS
ID : T32 MH020004
Pays : United States
Organisme : NIMH NIH HHS
ID : R01 MH072833
Pays : United States
Organisme : NIMH NIH HHS
ID : R01 MH105355
Pays : United States
Organisme : NHLBI NIH HHS
ID : P01 HL051971
Pays : United States
Organisme : NIMH NIH HHS
ID : R01 MH111596
Pays : United States
Organisme : NIGMS NIH HHS
ID : P20 GM104357
Pays : United States
Organisme : NIGMS NIH HHS
ID : U54 GM115428
Pays : United States
Informations de copyright
Copyright © 2020 Society of Biological Psychiatry. Published by Elsevier Inc. All rights reserved.
Références
Neuroimage. 2009 Mar;45(1 Suppl):S199-209
pubmed: 19070668
Depress Anxiety. 2016 Apr;33(4):289-99
pubmed: 27038410
Neuropsychopharmacology. 2014 Feb;39(3):681-7
pubmed: 24064470
F1000Res. 2013 Dec 30;2:289
pubmed: 25309726
Depress Anxiety. 2016 May;33(5):384-91
pubmed: 26864570
Depress Anxiety. 2014 Jun;31(6):494-505
pubmed: 24894802
J Psychiatr Res. 2018 Sep;104:58-64
pubmed: 29982083
Neuropsychopharmacology. 2014 Jan;39(2):351-9
pubmed: 23929546
Psychol Med. 2014 Jul;44(9):1927-36
pubmed: 24168716
Neuroimage. 2012 Apr 2;60(2):940-51
pubmed: 22297204
Brain Connect. 2012;2(3):125-41
pubmed: 22642651
Psychol Med. 2012 May;42(5):1037-47
pubmed: 22059690
Acta Psychiatr Scand. 2010 Jan;121(1):33-40
pubmed: 19426163
Cogn Affect Behav Neurosci. 2017 Apr;17(2):422-436
pubmed: 27966102
Brain Imaging Behav. 2020 Feb;14(1):186-199
pubmed: 30382529
Biol Psychiatry. 2009 Dec 15;66(12):1083-90
pubmed: 19640506
Trends Cogn Sci. 2011 Oct;15(10):483-506
pubmed: 21908230
Sci Rep. 2017 Oct 3;7(1):12625
pubmed: 28974724
Arch Gen Psychiatry. 2005 Jun;62(6):617-27
pubmed: 15939839
Biol Psychiatry. 2009 Oct 1;66(7):656-64
pubmed: 19589502
Can J Psychiatry. 2013 Sep;58(9):499-508
pubmed: 24099497
Depress Anxiety. 2017 Jul;34(7):641-650
pubmed: 28030757
Depress Anxiety. 2016 Jul;33(7):592-605
pubmed: 26918313
Magn Reson Med. 2009 Dec;62(6):1619-28
pubmed: 19859933
J Trauma Stress. 2013 Jun;26(3):299-309
pubmed: 23696449
Psychol Med. 2014 Jan;44(1):195-203
pubmed: 23551879
JAMA Psychiatry. 2015 Jun;72(6):603-11
pubmed: 25785575
J Psychiatry Neurosci. 2012 Jul;37(4):241-9
pubmed: 22313617
Depress Anxiety. 2001;13(3):132-56
pubmed: 11387733
Neuron. 2004 Sep 16;43(6):897-905
pubmed: 15363399
Acta Psychiatr Scand. 2015 Jul;132(1):29-38
pubmed: 25572430
Hum Brain Mapp. 2015 Jan;36(1):99-109
pubmed: 25137414
Curr Opin Psychol. 2015 Aug 1;4:114-118
pubmed: 26258159
PLoS One. 2013 Dec 13;8(12):e81957
pubmed: 24349161
Hum Brain Mapp. 2015 Jun;36(6):2118-31
pubmed: 25664619
J Affect Disord. 2019 Jun 15;253:18-25
pubmed: 31009844
Eur J Psychotraumatol. 2019 Feb 13;10(1):1568133
pubmed: 30788062
Neurosci Biobehav Rev. 2012 Apr;36(4):1140-52
pubmed: 22305994
J Psychiatry Neurosci. 2009 May;34(3):187-94
pubmed: 19448848
Psychosom Med. 2012 Nov-Dec;74(9):904-11
pubmed: 23115342
Transl Psychiatry. 2015 Mar 24;5:e533
pubmed: 25803496
Front Behav Neurosci. 2019 May 07;13:89
pubmed: 31133831
J Gen Intern Med. 2007 Jun;22(6):711-8
pubmed: 17503104
Perspect Psychol Sci. 2013 Nov;8(6):651-62
pubmed: 26173229
Front Neurosci. 2016 Jun 24;10:292
pubmed: 27445664
Psychol Med. 2019 Sep;49(12):2049-2059
pubmed: 30306886
Brain Imaging Behav. 2019 Oct;13(5):1453-1467
pubmed: 30191514
Neuropsychopharmacology. 2013 Sep;38(10):1889-98
pubmed: 23673864
J Clin Psychol. 2006 Jul;62(7):815-35
pubmed: 16703602
J Subst Abuse Treat. 2018 Mar;86:45-51
pubmed: 29415850
Neurosci Biobehav Rev. 2015 Oct;57:328-49
pubmed: 26254595
Front Psychiatry. 2011 Nov 14;2:62
pubmed: 22102841