Deep Learning Approaches for Seizure Detection and Prediction Using EEG Signals: A Comprehensive Review and Proposed CNN Framework

C V Keerthi Latha ^1*, M Kezia Joseph ^1*

Early seizure prediction via EEG signals might enable timely intervention, potentially improving patient outcomes and reducing clinical risks.

Abstract

Background: Epilepsy, a neurological disorder characterized by recurring seizures, affects millions globally and presents significant medical challenges. The unpredictable nature of seizures necessitates advancements in their detection and prediction. This study introduces a novel approach for classifying and identifying epileptic seizures through the analysis of EEG (Electroencephalogram) data using Convolutional Neural Networks (CNNs). Methods: We employed CNNs to analyze EEG signals, identifying recognizable patterns in temporal and spatial information, thereby enhancing the accuracy of seizure detection. Our proposed CNN framework incorporates Batch Normalization (BN), dropout layers, and dense layers specifically designed for EEG signal analysis. This novel approach improves the model’s capacity for extracting and detecting complex spatial-temporal patterns in EEG data, supporting effective seizure prediction and detection. The implementation of this Deep Learning (DL) methodology allows for continuous epilepsy monitoring, significantly advancing seizure prediction accuracy. Results: Extensive validation of the framework on a publicly accessible dataset demonstrated its superiority over traditional Machine Learning (ML) techniques, achieving an accuracy rate of 98.52%. This CNN-based approach successfully distinguished between abnormal brain activity due to seizures and normal brain function. Conclusion: The developed DL framework represents a significant advancement in epileptic seizure detection and prediction. By leveraging CNNs for EEG signal analysis, this study provides a robust and accurate tool for continuous epilepsy monitoring, offering improved patient outcomes and contributing to the broader field of neurological disorder management.

Keywords: Epilepsy Seizure Detection (ESD), Convolutional Neural Networks (CNNs), EEG Signal Analysis, (DL) Deep Learning, (SD)Seizure Detection, Epilepsy Detection, SP (Seizure Prediction).

References

Abdelhameed, A., & Bayoumi, M. (2021). A deep learning approach for automatic seizure detection in children with epilepsy. Frontiers in Computational Neuroscience, 15, 650050.
Aslam, M. H., Usman, S. M., Khalid, S., Anwar, A., Alroobaea, R., Hussain, S., Almotiri, J., Ullah, S. S., & Yasin, A. (2022). Classification of EEG signals for prediction of epileptic seizures. Applied Sciences, 12(14), 7251.

Benbadis, S. R., Beniczky, S., Bertram, E., MacIver, S., & Moshé, S. L. (2020). The role of EEG in patients with suspected epilepsy. Epileptic Disorders, 22(2), 143-155.

Chaddad, A., Wu, Y., Kateb, R., & Bouridane, A. (2023). Electroencephalography signal processing: A comprehensive review and analysis of methods and techniques. Sensors, 23(14), 6434.

Gao, Y., Gao, B., Chen, Q., Liu, J., & Zhang, Y. (2020). Deep convolutional neural network-based epileptic electroencephalogram (EEG) signal classification. Frontiers in Neurology, 11, 375.

Gao, Z., Dang, W., Wang, X., Hong, X., Hou, L., Ma, K., & Perc, M. (2021). Complex networks and deep learning for EEG signal analysis. Cognitive Neurodynamics, 15, 369-388.

Ibrahim, F. E., Emara, H. M., El-Shafai, W., Elwekeil, M., Rihan, M., Eldokany, I. M., Taha, T. E., et al. (2022). Deep-learning-based seizure detection and prediction from electroencephalography signals. International Journal for Numerical Methods in Biomedical Engineering, 38(6), e3573.

Jana, R., & Mukherjee, I. (2021). Deep learning based efficient epileptic seizure prediction with EEG channel optimization. Biomedical Signal Processing and Control, 68, 102767.

Kudlacek, J., Chvojka, J., Kumpost, V., Hermanovska, B., Posusta, A., Jefferys, J. G. R., Maturana, M. I., et al. (2021). Long-term seizure dynamics are determined by the nature of seizures and the mutual interactions between them. Neurobiology of Disease, 154, 105347.

Milligan, T. A. (2021). Epilepsy: A clinical overview. The American Journal of Medicine, 134(7), 840-847.

Ouichka, O., Echtioui, A., & Hamam, H. (2022). Deep learning models for predicting epileptic seizures using iEEG signals. Electronics, 11(4), 605.

Sen, A., Jette, N., Husain, M., & Sander, J. W. (2020). Epilepsy in older people. The Lancet, 395(10225), 735-748.

Shankar, A., Khaing, H. K., Dandapat, S., & Barma, S. (2021). Analysis of epileptic seizures based on EEG using recurrence plot images and deep learning. Biomedical Signal Processing and Control, 69, 102854.

Singh, K., & Malhotra, J. (2021). Deep learning based smart health monitoring for automated prediction of epileptic seizures using spectral analysis of scalp EEG. Physical and Engineering Sciences in Medicine, 44(4), 1161-1173.

Singh, K., & Malhotra, J. (2022). Smart neurocare approach for detection of epileptic seizures using deep learning based temporal analysis of EEG patterns. Multimedia Tools and Applications, 81(20), 29555-29586.

Usman, S. M., Khalid, S., & Bashir, S. (2021). A deep learning based ensemble learning method for epileptic seizure prediction. Computers in Biology and Medicine, 136, 104710.

Varli, M., & Yilmaz, H. (2023). Multiple classification of EEG signals and epileptic seizure diagnosis with combined deep learning. Journal of Computational Science, 67, 101943.

Wanleenuwat, P., Suntharampillai, N., & Iwanowski, P. (2020). Antibiotic-induced epileptic seizures: Mechanisms of action and clinical considerations. Seizure, 81, 167-174.