A Classification Model of EEG Signals Based on RNN-LSTM for Diagnosing Focal and Generalized Epilepsy

Abstract

Epilepsy is a chronic neurological disorder caused by abnormal neuronal activity that is diagnosed visually by analyzing electroencephalography (EEG) signals. Background: Surgical operations are the only option for epilepsy treatment when patients are refractory to treatment, which highlights the role of classifying focal and generalized epilepsy syndrome. Therefore, developing a model to be used for diagnosing focal and generalized epilepsy automatically is important. Methods: A classification model based on longitudinal bipolar montage (LB), discrete wavelet transform (DWT), feature extraction techniques, and statistical analysis in feature selection for RNN combined with long short-term memory (LSTM) is proposed in this work for identifying epilepsy. Initially, normal and epileptic LB channels were decomposed into three levels, and 15 various features were extracted. The selected features were extracted from each segment of the signals and fed into LSTM for the classification approach. Results: The proposed algorithm achieved a 96.1% accuracy, a 96.8% sensitivity, and a 97.4% specificity in distinguishing normal subjects from subjects with epilepsy. This optimal model was used to analyze the channels of subjects with focal and generalized epilepsy for diagnosing purposes, relying on statistical parameters. Conclusions: The proposed approach is promising, as it can be used to detect epilepsy with satisfactory classification performance and diagnose focal and generalized epilepsy.

Power spectral density-based resting-state EEG classification of first-episode psychosis

“…Other RBF kernels should also be considered for comparison. Deep recurrent neural network (RNN) models trained with time–frequency features, much like the recently proposed models for epilepsy classification, age prediction, and concussion classification 39 – 41 , can hypothetically outperform this model. Another aspect that requires further analysis is the method for computing PSD.…”

Transfer learning for epilepsy detection using spectrogram images

“…Common machine learning algorithms that have been used for epilepsy detection include support vector machines (SVM), decision trees, and neural networks. Hassan and Subasi [4] [5]. Another approach the feature engineering, this approach involves carefully selecting and designing features that are relevant for detecting epilepsy, and then using machine learning algorithms to classify the EEG signals based on these features.…”