Original ArticlePattern Classification of Sad Facial Processing: Toward the Development of Neurobiological Markers in Depression
Section snippets
Subjects
Nineteen participants (13 women; age range: 29–58 years) meeting DSM-IV criteria for major depressive disorder (1) according to the Structured Clinical Interview for DSM-IV Axis I Disorders (22) and clinical interview with a psychiatrist were recruited through local newspaper advertisements. Inclusion criteria were an acute episode of major depressive disorder of the unipolar subtype and a score of at least 18 on the 17-item Hamilton Rating Scale for Depression (HRSD) (23). Exclusion criteria
Group Classification of Diagnosis
From the whole brain analysis, training with the individual scans for each affective intensity, at the highest intensity, 74% of the patients were correctly classified as belonging to the patient group and 63% of healthy comparison subjects were correctly assigned to the control group. The accuracy was 68% with a sensitivity of 74% and a specificity of 63% (Figure 1, Table 2). The probability of reaching such a level of accuracy by allocating subjects at random to either group is p = .017.
Discussion
The whole brain pattern of neural activity to implicit processing of sad facial expressions significantly distinguished individuals in an acute episode of depression from healthy individuals. Moreover, the prediction of those patients who achieved a full clinical remission following antidepressant therapy from those who had persistent symptoms reached a trend toward significance. The development of neurobiological diagnostic markers for depression and predictors of treatment response requires
References (45)
Neuroimaging studies of mood disorders
Biol Psychiatry
(2000)- et al.
Frontal and parietal metabolic disturbances in unipolar depression
Biol Psychiatry
(1994) - et al.
Brain metabolic changes associated with symptom factor improvement in major depressive disorder
Biol Psychiatry
(2001) - et al.
Glucose metabolism in the amygdala in depression: Relationship to diagnostic subtype and plasma cortisol levels
Pharmacol Biochem Behav
(2002) - et al.
Increased amygdala response to masked emotional faces in depressed subjects resolves with antidepressant treatment: an fMRI study
Biol Psychiatry
(2001) - et al.
Beyond mind-reading: Multi-voxel pattern analysis of fMRI data
Trends Cogn Sci
(2006) - et al.
Classifying brain states and determining the discriminating activation patterns: Support vector machine on functional MRI data
Neuroimage
(2005) - et al.
Brain activation during facial emotion processing
Neuroimage
(2002) - et al.
An fMRI study investigating cognitive modulation of brain regions associated with emotional processing of visual stimuli
Neuropsychologia
(2003) - et al.
Characterizing dynamic brain responses with fMRI: A multivariate approach
Neuroimage
(1995)
Generalizable patterns in neuroimaging: How many principal components?
Neuroimage
Automated anatomical labelling of activations in SPM using a macroscopic anatomical parcellation of the MNI MRI single subject brain
Neuroimage
The distributed human neural system for face perception
Trends Cogn Sci
A differential pattern of neural response toward sad versus happy facial expressions in major depressive disorder
Biol Psychiatry
Negative thinking in depression: Cause, effect, or reciprocal relationship?
Adv Behav Res Ther
Brain metabolic changes in major depressive disorder from pre- to post-treatment with paroxetine
Psychiatry Res
Diagnostic and Statistical Manual of Mental Disorders
Neuroimaging studies of mood disorders
Modulating dysfunctional limbic-cortical circuits in depression: Towards development of brain-based algorithms for diagnosis and optimised treatment
Br Med Bull
Reduction of prefrontal cortex glucose metabolism common to three types of depression
Arch Gen Psychiatry
The anatomy of melancholia—focal abnormalities of cerebral blood flow in major depression
Psychol Med
Changes in regional brain glucose metabolism measured with positron emission tomography after paroxetine treatment of major depression
Am J Psychiatry
Cited by (287)
Predicting the outcome of psilocybin treatment for depression from baseline fMRI functional connectivity
2024, Journal of Affective DisordersNeurocognitive Measures of Self-blame and Risk Prediction Models of Recurrence in Major Depressive Disorder
2022, Biological Psychiatry: Cognitive Neuroscience and NeuroimagingAberrant resting-state co-activation network dynamics in major depressive disorder
2024, Translational PsychiatryMachine learning based detection of depression from task-based fMRI using weighted-3D-DWT denoising method
2024, Multimedia Tools and Applications