Patient classification as an outlier detection problem: An application of the One-Class Support Vector Machine

TY - JOUR

T1 - Patient classification as an outlier detection problem

T2 - An application of the One-Class Support Vector Machine

AU - Mourao-Miranda, Janaina

AU - Hardoon, David R

AU - Hahn, Tim

AU - Marquand, Andre

AU - Williams, Steven

AU - Shawe-Taylor, John

AU - Brammer, Michael

N1 - Copyright © 2011 Elsevier Inc. All rights reserved.

PY - 2011/10/1

Y1 - 2011/10/1

N2 - Pattern recognition approaches, such as the Support Vector Machine (SVM), have been successfully used to classify groups of individuals based on their patterns of brain activity or structure. However these approaches focus on finding group differences and are not applicable to situations where one is interested in accessing deviations from a specific class or population. In the present work we propose an application of the one-class SVM (OC-SVM) to investigate if patterns of fMRI response to sad facial expressions in depressed patients would be classified as outliers in relation to patterns of healthy control subjects. We defined features based on whole brain voxels and anatomical regions. In both cases we found a significant correlation between the OC-SVM predictions and the patients' Hamilton Rating Scale for Depression (HRSD), i.e. the more depressed the patients were the more of an outlier they were. In addition the OC-SVM split the patient groups into two subgroups whose membership was associated with future response to treatment. When applied to region-based features the OC-SVM classified 52% of patients as outliers. However among the patients classified as outliers 70% did not respond to treatment and among those classified as non-outliers 89% responded to treatment. In addition 89% of the healthy controls were classified as non-outliers.

AB - Pattern recognition approaches, such as the Support Vector Machine (SVM), have been successfully used to classify groups of individuals based on their patterns of brain activity or structure. However these approaches focus on finding group differences and are not applicable to situations where one is interested in accessing deviations from a specific class or population. In the present work we propose an application of the one-class SVM (OC-SVM) to investigate if patterns of fMRI response to sad facial expressions in depressed patients would be classified as outliers in relation to patterns of healthy control subjects. We defined features based on whole brain voxels and anatomical regions. In both cases we found a significant correlation between the OC-SVM predictions and the patients' Hamilton Rating Scale for Depression (HRSD), i.e. the more depressed the patients were the more of an outlier they were. In addition the OC-SVM split the patient groups into two subgroups whose membership was associated with future response to treatment. When applied to region-based features the OC-SVM classified 52% of patients as outliers. However among the patients classified as outliers 70% did not respond to treatment and among those classified as non-outliers 89% responded to treatment. In addition 89% of the healthy controls were classified as non-outliers.

KW - PATTERN-CLASSIFICATION

KW - Depression

KW - Outlier detection

KW - MAGNETIC-RESONANCE SPECTROSCOPY

KW - CORTEX

KW - DISORDER

KW - MAJOR DEPRESSION

KW - fMRI

KW - Pattern classification

KW - Support Vector Machine

KW - BRAIN

KW - GAMMA-AMINOBUTYRIC-ACID

KW - DISEASE

KW - Machine learning

KW - NEUROBIOLOGICAL MARKERS

KW - MENTAL STATES

U2 - 10.1016/j.neuroimage.2011.06.042

DO - 10.1016/j.neuroimage.2011.06.042

M3 - Article

C2 - 21723950

SN - 1095-9572

VL - 58

SP - 793

EP - 804

JO - NeuroImage

JF - NeuroImage

IS - 3

ER -