A brain functional network framework based on EEG connectivity for major depressive disorder recognition

When the brain is regarded as a complex dynamic system, its abnormalities often show the overall network reorganization. Traditional analysis for major depressive disorder (MDD) based on single-channel features of electroencephalogram (EEG) mainly focuses on signal changes, while ignoring inter-regional functional connectivity and network topology. As a consequence, it is challenging to reveal the systemic abnormal mechanisms.

To address this problem, this study built a framework of multi-frequency brain functional network (BFN) construction and recognition based on resting-state EEG. Phase-locking value (PLV) and Pearson correlation coefficient (PCC) were separately utilized to characterize phase synchronization and amplitude correlation. Abnormal BFNs in MDD were systematically evaluated from both connectivity patterns and node topology.

Results suggest that MDD patients exhibit increased connectivity in the left frontal, central, and parietal regions in the low-frequency bands. In the mid-frequency bands, increased fronto-central connectivity and reduced posterior connectivity are observed. In the high-frequency band, the connectivity pattern is characterized by increased fronto-temporal and centro-temporal connectivity, together with reduced connectivity in the posterior regions. At the node level, the most prominent alterations are concentrated in the parietal region, particularly in the α band, where altered betweenness centrality (BC) is consistently identified across both PLV and PCC networks. On this basis, the support vector machine (SVM) classifier was employed to evaluate the discriminative capability of PLV-Edge, PCC-Edge, PLV-Node, and PCC-Node features for MDD identification. Among the four feature types, PLV-Node features achieve the highest mean classification balanced accuracy of 81.44%, and PCC-Node features achieve a mean balanced accuracy of 79.14%.

All four feature types demonstrate discriminative potential for distinguishing patients with MDD from healthy controls (HCs). These findings suggest that functional connectivity-based brain network features may provide meaningful information for the auxiliary identification of MDD.