Anti-seizure Medication Classification using EEG signals via Attention-based CNN

Anti-Seizure medications (also known as anticonvulsants or anti-epileptic medications) are a broad class of medicines mostly used to treat epileptic seizures. Objectively relating anticonvulsant identification with electroencephalogram (EEG) signals of the subject having a history of taking medication(s), can result in evaluating the effectiveness of the course of treatments for seizure-related illness, which is helpful in patient care. In this work, we propose a deep learning based method to discriminate the EEG recordings of the subjects who have used anti-epileptic medicines in the past from those who have not. Specifically, EEG recordings taken from the subjects are used to distinguish between the presence of the two common anticonvulsants, namely- keppra & dilantin; and the presence of no anticonvulsants at all. We extracted frequency domain features from the EEG recordings using the Fourier transform, and we then used the information as input to the proposed model. Frequency domain features are extracted since the frequency domain representation of EEG signals has some notable differences across the medication paradigms. We then suggest a model based on a convolutional neural network framework with attention to solve the three class (keppra, dilantin, and no medication) classification problem. The attention network aids in giving the features differential weights. The model's classification performance is shown to increase as a result of differential weighting, which makes it possible to focus more on the pertinent aspects needed for classification. We demonstrate that our approach yields improvements over the state-of-the-art results using the standard publicly available Temple University Hospital EEG Corpus (TUEG).