Discriminative Analysis of Major Depressive Disorder and Anxious Depression Using Support Vector Machine

Comorbidity with anxiety disorders is a relatively common occurrence in major depressive disorder. However, there are no objective, neurological markers which can be used to identify depressive disorder with and without anxiety disorders. The aim of this study was to examine the diagnostic value of structural MRI to distinguish depressive patients with and without anxiety disorders using support vector machine. We applied voxel-based morphometry of gray matter volume (GMV) in normal controls (NC group, n = 28), depressive patients without anxiety disorder (DP group, n = 18), and depressive patients with anxiety disorder (DPA group, n = 20). The most discriminative features were choosed to classify different group using linear support vector machine (SVM) classifier. The accuracy is 81.6% between DPA group and DP group with both high sensitivity (83.3%) and high specificity (80.0%) (p < 0.001). The most discriminative features between DPA and DP groups are located in right inferior frontal gyrys, right occipital and temporal lobes. The experimental results showed that specific structural brain regions may be a potential biomarkers for disease diagnosis.