Classification of Bipolar Disorder and Schizophrenia Using Steady-State Visual Evoked Potential Based Features

The accurate discrimination between bipolar disorder (BD) and schizophrenic patients is crucial because of the considerable overlap between their clinical signs and symptoms (e.g., hallucination and delusion). Recently, electroencephalograms (EEGs) measured in the resting state have been vastly analyzed as a means for classifying the BD and schizophrenic patients, but EEGs evoked by external audio/visual stimuli have been rarely investigated, despite their high signal-to-noise ratio (SNR). In this study, in order to investigate whether EEGs evoked by external stimuli can be used for classifying the BD and schizophrenic patients, we used a visual stimulus modulated at a specific frequency to induce steady-state visual evoked potential (SSVEP). In the experiment, a photic stimulation modulated at 16 Hz was presented to two groups of the schizophrenic and BD patients for 95 s, during which the EEG data were recorded. Statistical measures of SSVEPs (mean, skewness, and kurtosis) described in SNR units were extracted as features to characterize and classify the variations of brain activity patterns in the two groups. Two brain areas, O1 and Fz, showed a statistically significant difference between the two groups for SNR mean and kurtosis, respectively. Among five applied classifiers, k-nearest neighbor provided the highest classification accuracy of 91.30% with the best feature set selected by Fisher score. An acceptable accuracy for binary classification (>70%) was retained until analysis time was reduced up to 10 s using a support vector machine classifier, and 20 s for other classifiers. Our results demonstrate the potential applicability of the proposed SSVEP-based classification approach with relatively short single-trial EEG signals.