Patient-specific seizure prediction using a multi-feature and multi-modal EEG-ECG classification

Epilepsy, a neurological disorder in which patients suffer from recurring seizures, affects approximately 1% of the world population. In spite of available drug and surgical treatment options, more than 25% of individuals with epilepsy have seizures that are uncontrollable. For these patients with intractable epilepsy, the unpredictability of seizure occurrence underlies an enhanced risk of sudden unexpected death or morbidity. Therefore, a device that could predict a seizure and notify the patient of the impending event or trigger an antiepileptic device would dramatically increase the quality of life for those patients. Here, a patient-specific classification algorithm is proposed to distinguish between preictal and interictal features extracted from ECG-EEG recordings. It demonstrates that the classifier based on a Support Vector Machine (SVM) can distinguish preictal from interictal with a high degree of sensitivity and specificity. The proposed algorithm was applied to long-term recordings of 4 patients with partial epilepsy, totaling 29 seizures and more than 1333-hour-long interictal, and it produced average sensitivity and specificity values of 90.6% and 85.6% respectively using 10-minute-long window of preictal recording.