EpiCNN-LSTMDetect: A Combined Deep Learning Method for Identifying Epileptic Seizures

Epilepsy, characterized by recurrent seizures, necessitates timely and accurate detection for effective management. This study presents EpiCNN-LSTMDetect, a hybrid deep learning framework combining Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks to analyze EEG data for seizure identification. Leveraging the CHBMIT EEG dataset, the model extracts features such as mean, skewness, kurtosis, and STFT. These features effectively capture spatial and temporal brain dynamics. EpiCNN-LSTMDetect achieved exceptional performance. It recorded an average accuracy of 99.61%, sensitivity of 99.83%, specificity of 99.23%, and an F1 score of 99.64%. The results surpass existing methods. These findings highlight the potential of advanced deep learning techniques in improving epilepsy care.