MDD Detection Based on Time-Spatial Features from EEG Symmetrical Microstate–Brain Networks

Major depressive disorder (MDD), identified by the World Health Organization as the leading cause of disability worldwide, remains underdiagnosed due to the lack of objective diagnostic tools. Electroencephalogram (EEG) signals offer potential biomarkers, yet conventional analyses often overlook the brain’s nonlinear dynamics. In this study, we analyzed resting-stage EEG data to identify four microstate types in MDD patients. Symmetrical microstate–brain networks were then constructed for each microstate by using time series of four types of microstates as dynamic windows. Then, we compared microstate features (duration, occurrence, coverage, transition probability) and brain network parameters (clustering coefficient, characteristic path length, local and global efficiency) between MDD patients and healthy controls to analyze the characteristics of the changes in the brain activities of the patients with MDD and the topological patterns of the functional connectivity. The comparative analysis showed that MDD patients showed more frequent microstate transitions and reduced network efficiency, suggesting elevated energy consumption and impaired neural integration, which may imply a cognitive shift in MDD patients toward internal focus and psychological withdrawal from external stimuli. By integrating microstate and brain network features, we captured the temporal and spatial characteristics of MDD-related brain activity and validated their diagnostic utility using our previously proposed multiscale spatiotemporal convolutional attention network (MSCAN). Our MSCAN achieved an accuracy of 98.64% for MDD detection, outperforming existing approaches. Our study can offer promising implications for the intelligent diagnosis of MDD and a deeper understanding of its neurophysiological underpinnings.