Graph theory analysis based on cross frequency coupling methods in major depressive disorder: A resting state EEG study

Abstract

Major depressive disorder (MDD) is a common and debilitating mental disorder that affects the personal and social activities of individuals. Conventional diagnostic approaches are based on the validity of the information provided by the patient and the expertise of the psychiatrist, which may limit precision. This study aimed to identify potential EEG-based biomarkers for diagnosing depression severity. Resting-state EEG signals were recorded from 37 subjects (15 healthy, 10 moderately depressed, and 12 severely depressed), and then analyzed using cross-frequency coupling (CFC) measures and graph theory metrics. Using the statistical analysis results, it was observed that depression affects the entire cerebral cortex, especially the frontal and occipital regions. The degree and K-coreness centrality measures showed statistically significant differences in almost all regions. In scaling depression severity, the Support Vector Machine (SVM) classifier achieved an accuracy of 94.25 % using 4 selected features derived from CFC between the low $\alpha$ and the low $\gamma$ band. To the best of our knowledge, this is the first study combining CFC and graph-theoretical analysis for multi-level depression severity classification.Using our proposed method along with psychological scales may be effective for diagnosing and treatment of MDD.