Detection of Obsessive Compulsive Disorder Using Resting-State Functional Connectivity Data

Obsessive Compulsive Disorder (OCD) is a serious psychological disease that might be affiliated with abnormal resting-state functional connectivity (rs-FC) in default mode network (DMN) of brain. In this study it is aimed to discriminate patients with OCD from healthy individuals by employing pattern recognition methods on resting-state functional connectivity (rs-FC) data. For this purpose, two different feature extraction approaches were implemented. In the first approach the rs-FC fMRI data were subsampled and then the dimensionality of the subsampled data was reduced using subspace transforms. In the second approach, feature vectors having already low dimensions were obtained by measuring similarities of the rs-FC data of subjects to the separate means in OCD and healthy groups. Afterwards the healthy and OCD groups were classified using Support Vector Machine (SVM). In order to obtain more reliable performance results, the Double LOO-CV method that we proposed as a version of Leave-One-Out Cross Validation (LOO-CV) was used. Quite encouraging results are obtained when the features extracted using similarity measures are classified by SVM.