Epilepsy seizure prediction using graph theory

Seizures due to Hippocampal origins are very common amongst epileptic patients. This article presents a novel seizure prediction approach based on graph theory. The early identification of seizure signature allows for various preventive measures to be undertaken. The proposed approach consists of observing a high correlation level between any pair of electrodes along with voltage peaks in the Delta frequencies. Statistical analysis tools were used to determine threshold levels for this frequency sub-band. A graph topology involving IEEG electrodes characterizes seizure signatures for each patient. In order to validate the proposed approach, six patients from both sexes and various age groups with temporal epilepsies originating from the hippocampal area were studied. An average seizure prediction of 30 minutes, a detection accuracy of 72%, and a false positive rate of 0% were accomplished throughout 200 hours of recording time.