Epileptic seizure monitoring by One-Class Support Vector Machine

Although refractory epileptic patients suffer from uncontrolled seizures, their quality of life (QoL) may be improved if the seizure can be predicted in advance. On the hypothesis that the excessive neuronal activity of epilepsy affects the autonomie nervous system and the fluctuation of the R-R interval (RRI) of an electrocardiogram (ECG), called heart rate variability (HRV), reflects the autonomie nervous function, there is possibility that an epileptic seizure can be predicted through monitoring RRI data. The present work proposes an HRV-based epileptic seizure monitoring method by utilizing One Class Support Vector Machine (OCSVM). Various HRV features are derived from the RRI data in both the interictal period and the preictal period, and an OCSVM-based seizure prediction model is built from the interictal HRV features. The application results of the proposed monitoring method to a clinical data are reported.