Pattern recognition analyses of brain activation elicited by happy and neutral faces in unipolar and bipolar depression

Janaina Mourão-Miranda, Jorge R.C. Almeida, Stefanie Hassel, Leticia de Oliveira, Amelia Versace, Andre F. Marquand, Joao R. Sato, Michael Brammer, Mary L. Phillips

Research output: Contribution to journalArticle

Abstract

Objectives: Recently, pattern recognition approaches have been used to classify patterns of brain activity elicited by sensory or cognitive processes. In the clinical context, these approaches have been mainly applied to classify groups of individuals based on structural magnetic resonance imaging (MRI) data. Only a few studies have applied similar methods to functional MRI (fMRI) data.
Methods: We used a novel analytic framework to examine the extent to which unipolar and bipolar depressed individuals differed on discrimination between patterns of neural activity for happy and neutral faces. We used data from 18 currently depressed individuals with bipolar I disorder (BD) and 18 currently depressed individuals with recurrent unipolar depression (UD), matched on depression severity, age, and illness duration, and 18 age- and gender ratio-matched healthy comparison subjects (HC). fMRI data were analyzed using a general linear model and Gaussian process classifiers.
Results: The accuracy for discriminating between patterns of neural activity for happy versus neutral faces overall was lower in both patient groups relative to HC. The predictive probabilities for intense and mild happy faces were higher in HC than in BD, and for mild happy faces were higher in HC than UD (all p < 0.001). Interestingly, the predictive probability for intense happy faces was significantly higher in UD than BD (p = 0.03).
Conclusions: These results indicate that patterns of whole-brain neural activity to intense happy faces were significantly less distinct from those for neutral faces in BD than in either HC or UD. These findings indicate that pattern recognition approaches can be used to identify abnormal brain activity patterns in patient populations and have promising clinical utility as techniques that can help to discriminate between patients with different psychiatric illnesses.
Original languageEnglish
Pages (from-to)451-460
Number of pages10
JournalBipolar Disorders
Volume14
Issue number4
DOIs
Publication statusPublished - Jun 2012

Fingerprint

Activation Analysis
Depressive Disorder
Bipolar Disorder
Healthy Volunteers
Brain
Magnetic Resonance Imaging
Psychiatry
Linear Models
Depression

Bibliographical note

Open Access

Keywords

  • magnetic resonance imaging
  • functional neuroimaging
  • bipolar disorder
  • humans
  • linear models
  • brain
  • predictive value of tests
  • depressive disorder
  • facial expression
  • adult
  • case-control studies
  • middle aged
  • automated pattern recognition
  • adolescent
  • female
  • male
  • depression
  • fMRI
  • Gaussian process
  • patient classification
  • pattern recognition

Cite this

Mourão-Miranda, J., Almeida, J. R. C., Hassel, S., de Oliveira, L., Versace, A., Marquand, A. F., ... Phillips, M. L. (2012). Pattern recognition analyses of brain activation elicited by happy and neutral faces in unipolar and bipolar depression. Bipolar Disorders, 14(4), 451-460. https://doi.org/10.1111/j.1399-5618.2012.01019.x
Mourão-Miranda, Janaina ; Almeida, Jorge R.C. ; Hassel, Stefanie ; de Oliveira, Leticia ; Versace, Amelia ; Marquand, Andre F. ; Sato, Joao R. ; Brammer, Michael ; Phillips, Mary L. / Pattern recognition analyses of brain activation elicited by happy and neutral faces in unipolar and bipolar depression. In: Bipolar Disorders. 2012 ; Vol. 14, No. 4. pp. 451-460.
@article{26318dcc93494afa83ea76464b819207,
title = "Pattern recognition analyses of brain activation elicited by happy and neutral faces in unipolar and bipolar depression",
abstract = "Objectives: Recently, pattern recognition approaches have been used to classify patterns of brain activity elicited by sensory or cognitive processes. In the clinical context, these approaches have been mainly applied to classify groups of individuals based on structural magnetic resonance imaging (MRI) data. Only a few studies have applied similar methods to functional MRI (fMRI) data. Methods: We used a novel analytic framework to examine the extent to which unipolar and bipolar depressed individuals differed on discrimination between patterns of neural activity for happy and neutral faces. We used data from 18 currently depressed individuals with bipolar I disorder (BD) and 18 currently depressed individuals with recurrent unipolar depression (UD), matched on depression severity, age, and illness duration, and 18 age- and gender ratio-matched healthy comparison subjects (HC). fMRI data were analyzed using a general linear model and Gaussian process classifiers. Results: The accuracy for discriminating between patterns of neural activity for happy versus neutral faces overall was lower in both patient groups relative to HC. The predictive probabilities for intense and mild happy faces were higher in HC than in BD, and for mild happy faces were higher in HC than UD (all p < 0.001). Interestingly, the predictive probability for intense happy faces was significantly higher in UD than BD (p = 0.03). Conclusions: These results indicate that patterns of whole-brain neural activity to intense happy faces were significantly less distinct from those for neutral faces in BD than in either HC or UD. These findings indicate that pattern recognition approaches can be used to identify abnormal brain activity patterns in patient populations and have promising clinical utility as techniques that can help to discriminate between patients with different psychiatric illnesses.",
keywords = "magnetic resonance imaging, functional neuroimaging, bipolar disorder, humans, linear models, brain, predictive value of tests, depressive disorder, facial expression, adult, case-control studies, middle aged, automated pattern recognition, adolescent, female, male, depression, fMRI, Gaussian process, patient classification, pattern recognition",
author = "Janaina Mour{\~a}o-Miranda and Almeida, {Jorge R.C.} and Stefanie Hassel and {de Oliveira}, Leticia and Amelia Versace and Marquand, {Andre F.} and Sato, {Joao R.} and Michael Brammer and Phillips, {Mary L.}",
note = "Open Access",
year = "2012",
month = "6",
doi = "10.1111/j.1399-5618.2012.01019.x",
language = "English",
volume = "14",
pages = "451--460",
journal = "Bipolar Disorders",
issn = "1398-5647",
publisher = "Blackwell",
number = "4",

}

Mourão-Miranda, J, Almeida, JRC, Hassel, S, de Oliveira, L, Versace, A, Marquand, AF, Sato, JR, Brammer, M & Phillips, ML 2012, 'Pattern recognition analyses of brain activation elicited by happy and neutral faces in unipolar and bipolar depression', Bipolar Disorders, vol. 14, no. 4, pp. 451-460. https://doi.org/10.1111/j.1399-5618.2012.01019.x

Pattern recognition analyses of brain activation elicited by happy and neutral faces in unipolar and bipolar depression. / Mourão-Miranda, Janaina; Almeida, Jorge R.C.; Hassel, Stefanie; de Oliveira, Leticia; Versace, Amelia; Marquand, Andre F.; Sato, Joao R.; Brammer, Michael; Phillips, Mary L.

In: Bipolar Disorders, Vol. 14, No. 4, 06.2012, p. 451-460.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Pattern recognition analyses of brain activation elicited by happy and neutral faces in unipolar and bipolar depression

AU - Mourão-Miranda, Janaina

AU - Almeida, Jorge R.C.

AU - Hassel, Stefanie

AU - de Oliveira, Leticia

AU - Versace, Amelia

AU - Marquand, Andre F.

AU - Sato, Joao R.

AU - Brammer, Michael

AU - Phillips, Mary L.

N1 - Open Access

PY - 2012/6

Y1 - 2012/6

N2 - Objectives: Recently, pattern recognition approaches have been used to classify patterns of brain activity elicited by sensory or cognitive processes. In the clinical context, these approaches have been mainly applied to classify groups of individuals based on structural magnetic resonance imaging (MRI) data. Only a few studies have applied similar methods to functional MRI (fMRI) data. Methods: We used a novel analytic framework to examine the extent to which unipolar and bipolar depressed individuals differed on discrimination between patterns of neural activity for happy and neutral faces. We used data from 18 currently depressed individuals with bipolar I disorder (BD) and 18 currently depressed individuals with recurrent unipolar depression (UD), matched on depression severity, age, and illness duration, and 18 age- and gender ratio-matched healthy comparison subjects (HC). fMRI data were analyzed using a general linear model and Gaussian process classifiers. Results: The accuracy for discriminating between patterns of neural activity for happy versus neutral faces overall was lower in both patient groups relative to HC. The predictive probabilities for intense and mild happy faces were higher in HC than in BD, and for mild happy faces were higher in HC than UD (all p < 0.001). Interestingly, the predictive probability for intense happy faces was significantly higher in UD than BD (p = 0.03). Conclusions: These results indicate that patterns of whole-brain neural activity to intense happy faces were significantly less distinct from those for neutral faces in BD than in either HC or UD. These findings indicate that pattern recognition approaches can be used to identify abnormal brain activity patterns in patient populations and have promising clinical utility as techniques that can help to discriminate between patients with different psychiatric illnesses.

AB - Objectives: Recently, pattern recognition approaches have been used to classify patterns of brain activity elicited by sensory or cognitive processes. In the clinical context, these approaches have been mainly applied to classify groups of individuals based on structural magnetic resonance imaging (MRI) data. Only a few studies have applied similar methods to functional MRI (fMRI) data. Methods: We used a novel analytic framework to examine the extent to which unipolar and bipolar depressed individuals differed on discrimination between patterns of neural activity for happy and neutral faces. We used data from 18 currently depressed individuals with bipolar I disorder (BD) and 18 currently depressed individuals with recurrent unipolar depression (UD), matched on depression severity, age, and illness duration, and 18 age- and gender ratio-matched healthy comparison subjects (HC). fMRI data were analyzed using a general linear model and Gaussian process classifiers. Results: The accuracy for discriminating between patterns of neural activity for happy versus neutral faces overall was lower in both patient groups relative to HC. The predictive probabilities for intense and mild happy faces were higher in HC than in BD, and for mild happy faces were higher in HC than UD (all p < 0.001). Interestingly, the predictive probability for intense happy faces was significantly higher in UD than BD (p = 0.03). Conclusions: These results indicate that patterns of whole-brain neural activity to intense happy faces were significantly less distinct from those for neutral faces in BD than in either HC or UD. These findings indicate that pattern recognition approaches can be used to identify abnormal brain activity patterns in patient populations and have promising clinical utility as techniques that can help to discriminate between patients with different psychiatric illnesses.

KW - magnetic resonance imaging

KW - functional neuroimaging

KW - bipolar disorder

KW - humans

KW - linear models

KW - brain

KW - predictive value of tests

KW - depressive disorder

KW - facial expression

KW - adult

KW - case-control studies

KW - middle aged

KW - automated pattern recognition

KW - adolescent

KW - female

KW - male

KW - depression

KW - fMRI

KW - Gaussian process

KW - patient classification

KW - pattern recognition

UR - http://onlinelibrary.wiley.com/doi/10.1111/j.1399-5618.2012.01019.x/abstract

U2 - 10.1111/j.1399-5618.2012.01019.x

DO - 10.1111/j.1399-5618.2012.01019.x

M3 - Article

C2 - 22631624

VL - 14

SP - 451

EP - 460

JO - Bipolar Disorders

JF - Bipolar Disorders

SN - 1398-5647

IS - 4

ER -