Identifying Refractory Epilepsy Without Structural Abnormalities by Fusing the Common Spatial Patterns of Functional and Effective EEG Networks

Drug refractory epilepsy (RE) is believed to be associated with structural lesions, but some RE patients show no significant abnormalities (RE-no-SA) on conventional magnetic resonance imaging scans. Since most of the medically controlled (MCE) also do not exhibit abnormalities, a reliable assessment needs developed differentiate RE-no-SA and MCE avoid misdiagnosis inappropriate treatment. Using resting-state scalp electroencephalogram (EEG) datasets, we extracted spatial pattern network (SPN) features from functional effective EEG networks both patients. Compared performance traditional properties, SPN exhibited remarkable superiority in classifying these two groups patients, accuracy values 90.00% 80.00% were obtained for networks, respectively. By further fusing demonstrated that highest value 96.67% could reached, sensitivity 100% specificity 92.86%. Overall, findings only indicate fused are promising as measurements distinguishing may provide new perspective explore complex neurophysiology epilepsy.