Pattern classification of valence in depression

I. Habes, S. Krall, S.J. Johnston, K.S.L. Yuen, D. Healy, R. Goebel, B. Sorger, D.E.J. Linden

Research output: Contribution to journalArticleAcademicpeer-review

8 Citations (Scopus)

Abstract

Neuroimaging biomarkers of depression have potential to aid diagnosis, identify individuals at risk and predict treatment response or course of illness. Nevertheless none have been identified so far, potentially because no single brain parameter captures the complexity of the pathophysiology of depression. Multi-voxel pattern analysis (MVPA) may overcome this issue as it can identify patterns of voxels that are spatially distributed across the brain. Here we present the results of an MVPA to investigate the neuronal patterns underlying passive viewing of positive, negative and neutral pictures in depressed patients. A linear support vector machine (SVM) was trained to discriminate different valence conditions based on the functional magnetic resonance imaging (fMRI) data of nine unipolar depressed patients. A similar dataset obtained in nine healthy individuals was included to conduct a group classification analysis via linear discriminant analysis (LDA). Accuracy scores of 86% or higher were obtained for each valence contrast via patterns that included limbic areas such as the amygdala and frontal areas such as the ventrolateral prefrontal cortex. The LDA identified two areas (the dorsomedial prefrontal cortex and caudate nucleus) that allowed group classification with 72.2% accuracy. Our preliminary findings suggest that MVPA can identify stable valence patterns, with more sensitivity than univariate analysis, in depressed participants and that it may be possible to discriminate between healthy and depressed individuals based on differences in the brain's response to emotional cues. (C) 2013 The Authors. Published by Elsevier Inc.

Original languageEnglish
Pages (from-to)675-683
Number of pages9
JournalNeuroimage
Volume2
DOIs
Publication statusPublished - 1 Jan 2013

Keywords

  • Affect
  • BRAIN STATES
  • Depression
  • EMOTIONAL PICTURES
  • Emotion
  • FUNCTIONAL NEUROANATOMY
  • LDA
  • MAJOR DEPRESSION
  • MOOD DISORDERS
  • MVPA
  • NEUROBIOLOGICAL MARKERS
  • REAL-TIME
  • RESTING-STATE
  • SPATIAL-PATTERNS
  • SUPPORT VECTOR MACHINES
  • Valence

Cite this

Habes, I., Krall, S., Johnston, S. J., Yuen, K. S. L., Healy, D., Goebel, R., ... Linden, D. E. J. (2013). Pattern classification of valence in depression. Neuroimage, 2, 675-683. https://doi.org/10.1016/j.nicl.2013.05.001
Habes, I. ; Krall, S. ; Johnston, S.J. ; Yuen, K.S.L. ; Healy, D. ; Goebel, R. ; Sorger, B. ; Linden, D.E.J. / Pattern classification of valence in depression. In: Neuroimage. 2013 ; Vol. 2. pp. 675-683.
@article{04b096302ac14ee59d3c76234a921929,
title = "Pattern classification of valence in depression",
abstract = "Neuroimaging biomarkers of depression have potential to aid diagnosis, identify individuals at risk and predict treatment response or course of illness. Nevertheless none have been identified so far, potentially because no single brain parameter captures the complexity of the pathophysiology of depression. Multi-voxel pattern analysis (MVPA) may overcome this issue as it can identify patterns of voxels that are spatially distributed across the brain. Here we present the results of an MVPA to investigate the neuronal patterns underlying passive viewing of positive, negative and neutral pictures in depressed patients. A linear support vector machine (SVM) was trained to discriminate different valence conditions based on the functional magnetic resonance imaging (fMRI) data of nine unipolar depressed patients. A similar dataset obtained in nine healthy individuals was included to conduct a group classification analysis via linear discriminant analysis (LDA). Accuracy scores of 86{\%} or higher were obtained for each valence contrast via patterns that included limbic areas such as the amygdala and frontal areas such as the ventrolateral prefrontal cortex. The LDA identified two areas (the dorsomedial prefrontal cortex and caudate nucleus) that allowed group classification with 72.2{\%} accuracy. Our preliminary findings suggest that MVPA can identify stable valence patterns, with more sensitivity than univariate analysis, in depressed participants and that it may be possible to discriminate between healthy and depressed individuals based on differences in the brain's response to emotional cues. (C) 2013 The Authors. Published by Elsevier Inc.",
keywords = "Affect, BRAIN STATES, Depression, EMOTIONAL PICTURES, Emotion, FUNCTIONAL NEUROANATOMY, LDA, MAJOR DEPRESSION, MOOD DISORDERS, MVPA, NEUROBIOLOGICAL MARKERS, REAL-TIME, RESTING-STATE, SPATIAL-PATTERNS, SUPPORT VECTOR MACHINES, Valence",
author = "I. Habes and S. Krall and S.J. Johnston and K.S.L. Yuen and D. Healy and R. Goebel and B. Sorger and D.E.J. Linden",
year = "2013",
month = "1",
day = "1",
doi = "10.1016/j.nicl.2013.05.001",
language = "English",
volume = "2",
pages = "675--683",
journal = "Neuroimage",
issn = "1053-8119",
publisher = "Elsevier Science",

}

Pattern classification of valence in depression. / Habes, I.; Krall, S.; Johnston, S.J.; Yuen, K.S.L.; Healy, D.; Goebel, R.; Sorger, B.; Linden, D.E.J.

In: Neuroimage, Vol. 2, 01.01.2013, p. 675-683.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Pattern classification of valence in depression

AU - Habes, I.

AU - Krall, S.

AU - Johnston, S.J.

AU - Yuen, K.S.L.

AU - Healy, D.

AU - Goebel, R.

AU - Sorger, B.

AU - Linden, D.E.J.

PY - 2013/1/1

Y1 - 2013/1/1

N2 - Neuroimaging biomarkers of depression have potential to aid diagnosis, identify individuals at risk and predict treatment response or course of illness. Nevertheless none have been identified so far, potentially because no single brain parameter captures the complexity of the pathophysiology of depression. Multi-voxel pattern analysis (MVPA) may overcome this issue as it can identify patterns of voxels that are spatially distributed across the brain. Here we present the results of an MVPA to investigate the neuronal patterns underlying passive viewing of positive, negative and neutral pictures in depressed patients. A linear support vector machine (SVM) was trained to discriminate different valence conditions based on the functional magnetic resonance imaging (fMRI) data of nine unipolar depressed patients. A similar dataset obtained in nine healthy individuals was included to conduct a group classification analysis via linear discriminant analysis (LDA). Accuracy scores of 86% or higher were obtained for each valence contrast via patterns that included limbic areas such as the amygdala and frontal areas such as the ventrolateral prefrontal cortex. The LDA identified two areas (the dorsomedial prefrontal cortex and caudate nucleus) that allowed group classification with 72.2% accuracy. Our preliminary findings suggest that MVPA can identify stable valence patterns, with more sensitivity than univariate analysis, in depressed participants and that it may be possible to discriminate between healthy and depressed individuals based on differences in the brain's response to emotional cues. (C) 2013 The Authors. Published by Elsevier Inc.

AB - Neuroimaging biomarkers of depression have potential to aid diagnosis, identify individuals at risk and predict treatment response or course of illness. Nevertheless none have been identified so far, potentially because no single brain parameter captures the complexity of the pathophysiology of depression. Multi-voxel pattern analysis (MVPA) may overcome this issue as it can identify patterns of voxels that are spatially distributed across the brain. Here we present the results of an MVPA to investigate the neuronal patterns underlying passive viewing of positive, negative and neutral pictures in depressed patients. A linear support vector machine (SVM) was trained to discriminate different valence conditions based on the functional magnetic resonance imaging (fMRI) data of nine unipolar depressed patients. A similar dataset obtained in nine healthy individuals was included to conduct a group classification analysis via linear discriminant analysis (LDA). Accuracy scores of 86% or higher were obtained for each valence contrast via patterns that included limbic areas such as the amygdala and frontal areas such as the ventrolateral prefrontal cortex. The LDA identified two areas (the dorsomedial prefrontal cortex and caudate nucleus) that allowed group classification with 72.2% accuracy. Our preliminary findings suggest that MVPA can identify stable valence patterns, with more sensitivity than univariate analysis, in depressed participants and that it may be possible to discriminate between healthy and depressed individuals based on differences in the brain's response to emotional cues. (C) 2013 The Authors. Published by Elsevier Inc.

KW - Affect

KW - BRAIN STATES

KW - Depression

KW - EMOTIONAL PICTURES

KW - Emotion

KW - FUNCTIONAL NEUROANATOMY

KW - LDA

KW - MAJOR DEPRESSION

KW - MOOD DISORDERS

KW - MVPA

KW - NEUROBIOLOGICAL MARKERS

KW - REAL-TIME

KW - RESTING-STATE

KW - SPATIAL-PATTERNS

KW - SUPPORT VECTOR MACHINES

KW - Valence

U2 - 10.1016/j.nicl.2013.05.001

DO - 10.1016/j.nicl.2013.05.001

M3 - Article

VL - 2

SP - 675

EP - 683

JO - Neuroimage

JF - Neuroimage

SN - 1053-8119

ER -

Habes I, Krall S, Johnston SJ, Yuen KSL, Healy D, Goebel R et al. Pattern classification of valence in depression. Neuroimage. 2013 Jan 1;2:675-683. https://doi.org/10.1016/j.nicl.2013.05.001