Characterizing Brain Signals for Epileptic Pre-ictal Signal Classification

Epilepsy is a kind of neurological disorder characterized by recurrent epileptic seizures. While it is crucial to characterize pre-ictal brain electrical activities, the problem to this day still remains computationally challenging. Using brain signal acquisition and advances in deep learning technology, we aim to classify pre-ictal signals and characterize the brain waveforms of patients with epilepsy during the pre-ictal period. We develop a novel machine learning model called Pre-ictal Signal Classification (PiSC) for pre-ictal signal classification and for identifying brain waveform patterns critical for seizure onset early detection. In PiSC, a unique preprocessing procedure is developed to convert the stereo-electroencephalography (sEEG) signals to data blocks ready for pre-ictal signal classification. Also, a novel deep learning framework is developed to integrate deep neural networks and meta-learning to effectively mitigate patient-to-patient variances as well as fine-tuning a trained classification model for new patients. The unique network architecture ensures model stability and generalization in sEEG data modeling. The experimental results on a real-world patient dataset show that PiSC improved the accuracy and F1 score by 10% compared with the existing models. Two types of sEEG patterns were discovered to be associated with seizure development in nocturnal epileptic patients.