Brain Functional Networks Based on Resting-State EEG Data for Major Depressive Disorder Analysis and Classification

If the brain is regarded as a system, it will be one of most complex systems in universe. Traditional analysis and classification methods major depressive disorder (MDD) based on electroencephalography (EEG) feature-levels often regard electrode isolated node ignore correlation between them, so it's difficult to find alters abnormal topological architecture brain. To solve this problem, we propose functional network framework for MDD resting state EEG. The phase lag index (PLI) was calculated 64-channel EEG construct function connection matrix reduce avoid volume conductor effect. Then binarization small world realized. Statistical analyses were performed different frequency band regions. results showed that significant alterations synchronization occurred frontal, temporal, parietal-occipital regions left temporal region right And average shortest path length clustering coefficient central theta betweenness centrality significantly correlated with PHQ-9 score MDD, which indicates these three metrics may served potential biomarkers effectively distinguish from controls highest accuracy can reach 93.31%. Our findings also point out patients shows random trend, characteristics appears weaken.