Seizure Prediction Based on Hybrid Deep Learning Model Using Scalp Electroencephalogram

Epilepsy is a neurological disorder that affects the brain and causes recurring seizures. Scalp electroencephalography (EEG)-based seizure prediction is essential to improve the daily life of patients. To achieve more accurate and reliable predictions of seizures, this study introduces a hybrid model that merges the Dense Convolutional Network (DenseNet) and Bidirectional LSTM (BiLSTM). The densely connected structure of DenseNet can learn richer feature information in the initial layers, while BiLSTM can consider the correlation of the time series and better capture the dynamic changing features of the signal. The raw EEG data is first converted into a time-frequency matrix by short-time Fourier transform (STFT) and then the STFT converted images are fed into the DenseNet-BiLSTM hybrid model to carry out end-to-end feature extraction and classification. Using Leave-One-Out Cross-Validation (LOOCV), our model achieved an average accuracy of 92.45%, an average sensitivity of 92.66%, an F1-Score of 0.923, an average false prediction rate (FPR) of 0.066 per hour, and an Area Under Curve (AUC) score was 0.936 on the CHB-MIT EEG dataset. Our model exhibits superior performance when compared to state-of-the-art methods, especially lower false prediction rate, which has great potential for clinical application.