Machine Learning-Based Prediction of Drug-Resistant Epilepsy

Abstract

data from used a a convolutional neural network, a temporal convolutional network to learn the EEG patterns of patients with drug-resistant epilepsy. Data from 978 EEG examinations were available for training and testing. best performance an accuracy of of Our models predicted drug-resistant epilepsy better than drug-sensitive epilepsy. that EEG contain information predictive of epilepsy; the performance of the current model insufficient for clinical use to predict drug-resis-tant epilepsy. Our findings warrant further investigation to identify EEG markers of drug-resistance and to increase model performance to a level sufficient to aid in clinical decision-making.