Identifying Patients with Epilepsy Having Depression/Anxiety Disorder Using Common Spatial Patterns of Functional EEG Networks

The presentation of epilepsy with depression/anxiety disorder (E-AD) is a complex comorbidity, and systematic psychiatric screen poses heavy economic burden on the patients. Typically, distinguishing between E-AD patients without (E-no-AD) needs multiple evaluations, which incredibly difficult owing to high costs. Therefore, there an urgent need for reliable assessment protocol preemptively distinguish two types We collected resting-state electroencephalography (EEG) signals from E-no-AD constructed functional networks groups of. connectivity strength corresponding network properties different frequency bands were statistically compared explore inherent differences. Based differences in networks, we evaluated classification performance using features, including properties, principal component analysis (PCA) spatial patterns (SPN). Using support vector machine, differentiation 4416 EEG segments 6346 was realized three features. results revealed that SPN feature remarkably superior traditional patient groups, appreciable accuracy 89.90% sensitivity 87.37% specificity 91.67%. These findings demonstrate superiority features as way characterize potentially provide insights regarding mechanisms causing