EEG Classification in Epilepsy

Epilepsy is the second most common serious brain disorder after stroke. Worldwide, at least 40 million people or 1% of population currently suffer from epilepsy. Approximately 25-30% of epileptic patients remain unresponsive to antiepileptic drug treatment, which is the standard therapy for epilepsy. There is a growing interest in predicting epileptic seizures using intracranial electroencephalogram (EEG), which is a tool for evaluating the physiological state of the brain. Although recent research in seizure prediction has demonstrated the seizure predictability, the question of whether the brain’s normal and pre-seizure epileptic activities are distinctive or differentiable remains unanswered. In this study, we apply data mining techniques to EEG data in order to verify the classifiability of the brain’s normal and pre-seizure epileptic activities through the measure of the brain dynamics, which were previously shown capable of contemplating dynamical mechanisms of the brain network. A statistical cross validation is implemented to estimate the accuracy of the brain state classification. In addition, support vector machines were also implemented to classify the brain’s activities. The results of this study indicate that it may be possible to design and develop efficient seizure warning algorithms for diagnostic and therapeutic purposes. This framework is also an initial proof of concept investigations, which is a necessary first step in differentiating the brain’s normal and pre-seizure epileptic activities.