Predicting Bipolar Disorder Risk Factors in Distressed Young Adults From Patterns of Brain Activation to Reward: A Machine Learning Approach.
Biomarkers
Bipolar disorder
Machine learning
Multivariate pattern
Neuroimage
fMRI
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:
08 2019
08 2019
Historique:
received:
09
01
2019
revised:
08
04
2019
accepted:
09
04
2019
pubmed:
16
6
2019
medline:
28
3
2020
entrez:
16
6
2019
Statut:
ppublish
Résumé
The aim of this study was to apply multivariate pattern recognition to predict the severity of behavioral traits and symptoms associated with risk for bipolar spectrum disorder from patterns of whole-brain activation during reward expectancy to facilitate the identification of individual-level neural biomarkers of bipolar disorder risk. We acquired functional neuroimaging data from two independent samples of transdiagnostically recruited adults (18-25 years of age; n = 56, mean age 21.9 ± 2.2 years, 42 women; n = 36, mean age 21.2 ± 2.2 years, 24 women) during reward expectancy task performance. Pattern recognition model performance in each sample was measured using correlation and mean squared error between actual and whole-brain activation-predicted scores on behavioral traits and symptoms. In the first sample, the model significantly predicted severity of a specific hypo/mania-related symptom, heightened energy, measured by the energy manic subdomain of the Mood Spectrum Structured Interviews (r = .42, p = .001; mean squared error = 9.93, p = .001). The region with the highest contribution to the model was the left ventrolateral prefrontal cortex. Results were confirmed in the second sample (r = .33, p = .01; mean squared error = 8.61, p = .01), in which the severity of this symptom was predicted using a bilateral ventrolateral prefrontal cortical mask (r = .33, p = .009, mean squared error = 9.37, p = .04). The severity of a specific hypo/mania-related symptom was predicted from patterns of whole-brain activation in two independent samples. Given that emerging manic symptoms predispose to bipolar disorders, these findings could provide neural biomarkers to aid early identification of individual-level bipolar disorder risk in young adults.
Sections du résumé
BACKGROUND
The aim of this study was to apply multivariate pattern recognition to predict the severity of behavioral traits and symptoms associated with risk for bipolar spectrum disorder from patterns of whole-brain activation during reward expectancy to facilitate the identification of individual-level neural biomarkers of bipolar disorder risk.
METHODS
We acquired functional neuroimaging data from two independent samples of transdiagnostically recruited adults (18-25 years of age; n = 56, mean age 21.9 ± 2.2 years, 42 women; n = 36, mean age 21.2 ± 2.2 years, 24 women) during reward expectancy task performance. Pattern recognition model performance in each sample was measured using correlation and mean squared error between actual and whole-brain activation-predicted scores on behavioral traits and symptoms.
RESULTS
In the first sample, the model significantly predicted severity of a specific hypo/mania-related symptom, heightened energy, measured by the energy manic subdomain of the Mood Spectrum Structured Interviews (r = .42, p = .001; mean squared error = 9.93, p = .001). The region with the highest contribution to the model was the left ventrolateral prefrontal cortex. Results were confirmed in the second sample (r = .33, p = .01; mean squared error = 8.61, p = .01), in which the severity of this symptom was predicted using a bilateral ventrolateral prefrontal cortical mask (r = .33, p = .009, mean squared error = 9.37, p = .04).
CONCLUSIONS
The severity of a specific hypo/mania-related symptom was predicted from patterns of whole-brain activation in two independent samples. Given that emerging manic symptoms predispose to bipolar disorders, these findings could provide neural biomarkers to aid early identification of individual-level bipolar disorder risk in young adults.
Identifiants
pubmed: 31201147
pii: S2451-9022(19)30101-6
doi: 10.1016/j.bpsc.2019.04.005
pmc: PMC6682607
pii:
doi:
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
726-733Subventions
Organisme : Wellcome Trust
Pays : United Kingdom
Organisme : NIMH NIH HHS
ID : R01 MH100041
Pays : United States
Organisme : NIMH NIH HHS
ID : R37 MH100041
Pays : United States
Organisme : Wellcome Trust
ID : WT102845/Z/13/Z
Pays : United Kingdom
Informations de copyright
Copyright © 2019 Society of Biological Psychiatry. Published by Elsevier Inc. All rights reserved.
Références
Neuroscience. 2009 Nov 24;164(1):331-43
pubmed: 19358880
Bipolar Disord. 2008 Mar;10(2):310-22
pubmed: 18271911
J Abnorm Psychol. 2012 Feb;121(1):16-27
pubmed: 21668080
PLoS Biol. 2015 Apr 28;13(4):e1002137
pubmed: 25919291
BMC Med. 2013 May 14;11:126
pubmed: 23672542
Neuroimage. 2017 Nov 15;162:186-198
pubmed: 28877515
J Affect Disord. 2014 Sep;166:165-7
pubmed: 25012426
Br J Psychiatry. 1995 Jul;167(1):99-103
pubmed: 7551619
Neuroimage. 2015 Apr 15;110:48-59
pubmed: 25623501
Arch Gen Psychiatry. 2007 May;64(5):543-52
pubmed: 17485606
Braz J Psychiatry. 2011 Mar;33(1):64-7
pubmed: 21537723
J Abnorm Psychol. 2000 May;109(2):222-6
pubmed: 10895560
Transl Psychiatry. 2017 Apr 18;7(4):e1096
pubmed: 28418404
Front Neuroinform. 2011 Aug 22;5:13
pubmed: 21897815
Am J Psychiatry. 2010 Jul;167(7):748-51
pubmed: 20595427
Psychiatry Res. 2012 Feb 28;195(3):111-7
pubmed: 21816486
J Neurosci. 2009 Sep 23;29(38):11772-82
pubmed: 19776264
Neurosci Biobehav Rev. 2018 Mar;86:85-98
pubmed: 29366699
Bipolar Disord. 2012 May;14(3):249-60
pubmed: 22548898
Psychiatry Res. 2008 Jun 30;159(3):300-7
pubmed: 18445508
JAMA. 2005 Jul 13;294(2):218-28
pubmed: 16014596
Nature. 2011 Jul 06;475(7354):27-30
pubmed: 21734685
Arch Gen Psychiatry. 2005 Jun;62(6):617-27
pubmed: 15939839
Neuropsychopharmacology. 2014 Jan;39(2):456-63
pubmed: 23963117
Neuroimage. 2002 Jan;15(1):273-89
pubmed: 11771995
Neuroinformatics. 2018 Jan;16(1):117-143
pubmed: 29297140
Transl Psychiatry. 2017 Jul 25;7(7):e1178
pubmed: 28742077
Am J Psychiatry. 2013 May;170(5):533-41
pubmed: 23558337
J Abnorm Psychol. 1991 Aug;100(3):316-36
pubmed: 1918611
J Affect Disord. 2013 Oct;151(1):121-8
pubmed: 23810478
Trends Cogn Sci. 2004 Sep;8(9):389-91
pubmed: 15350238
J Affect Disord. 1998 Sep;50(2-3):143-51
pubmed: 9858074
Neuron. 2016 Mar 16;89(6):1343-1354
pubmed: 26948895
Neuroimage. 2017 Jan 15;145(Pt B):337-345
pubmed: 26767946
Neuroimage. 2014 Feb 15;87:96-110
pubmed: 24239590
Arch Gen Psychiatry. 2011 Mar;68(3):241-51
pubmed: 21383262
PLoS One. 2016 Jan 05;11(1):e0117603
pubmed: 26731403
Int J Dev Neurosci. 2010 Oct;28(6):481-9
pubmed: 20600789
Neuroimage. 2010 Jul 15;51(4):1405-13
pubmed: 20347044
Depress Anxiety. 2006;23(4):220-35
pubmed: 16550540
Soc Psychiatry Psychiatr Epidemiol. 2013 Oct;48(10):1601-10
pubmed: 23754681
J Affect Disord. 2003 Jan;73(1-2):133-46
pubmed: 12507746
PLoS Med. 2016 Jun 21;13(6):e1002049
pubmed: 27328301
Neuroimage. 2017 Apr 15;150:23-49
pubmed: 28143776
Compr Psychiatry. 2002 Jan-Feb;43(1):69-73
pubmed: 11788923
J Psychopathol Behav Assess. 1999 Dec 1;21(4):275-292
pubmed: 21765591
Cereb Cortex. 2010 Mar;20(3):534-48
pubmed: 19520764
Annu Rev Clin Psychol. 2012;8:243-67
pubmed: 22077912
Cogn Emot. 2013;27(6):1091-104
pubmed: 23472965