Abstract

Epilepsy is one of the most prevalent neurological disorders, affecting more than 50 million people worldwide. Seizures are a common symptom of epilepsy, which manifest abruptly and cause disruption in a patient’s life. Epileptic seizures can lead to serious injury, and people with untreatable epilepsy must live with the uncertainty of the next seizure occurrence. The ability to predict the occurrence of a seizure could alleviate many of the risks people with epilepsy face. Patients would have time to take precautions to reduce the risk of injury or prevent the seizure altogether. Most of the current approaches are focused on detecting seizures when they occur. While these approaches are useful, they do not provide any lead time to take preventive measures. It is widely known that the brain activity before an actual seizure is a strong indicator of an upcoming seizure. Therefore, we approach this problem from a prediction lens, by developing a classifier that can separate the pre-seizure state from regular brain activity. Development of such a classifier with high performance will provide a lead time to take preventive measures to handle an incoming seizure. The classification model used customized convolutional neural networks trained on short-time Fourier transform images to learn features from multi-channel intracranial electroencephalography (iEEG). The model was trained on a large publicly available dataset (SWEC-ETHZ iEEG database) containing over 2500 hours of EEG data from 18 patients. We have performed these experiments on the data of 9 patients in the database with varying results, highest being an AUC of 0.86.

Article ID: 2022L26

Month: May

Year: 2022

Address: Online

Venue: Canadian Conference on Artificial Intelligence

Publisher: Canadian Artificial Intelligence Association

URL: https://caiac.pubpub.org/pub/9aiajuq2