Deep Learning Models In The Early Brediction Of Epileptic Seizures
Main Article Content
Abstract
Abstract
Prediction of early epileptic seizures is still a challenge in clinical neuroscience due to the unpredictability of seizures and their psychological and physical dangers to the patient. EEG can be used as an important modality for seizure warning systems with the goal of improving patient quality of life. Hence, the paper will compare and evaluate the performance of several deep learning models for seizure prediction 15 minutes in advance using EEG data. To this end, a uniform experimental protocol was followed in order to ensure a comparison between models: LSTM, BiLSTM, Graph Neural Network, and Transformer. Models were evaluated based on the CHB-MIT database that consisted of long-term recordings from 24 patients. Each signal was subjected to different pre-processing steps such as filtering, normalization, and time window segmentation. Then, an individual set of features was extracted, while data between pre-ictal and ictal classes were made balanced. Models were studied based on various metrics such as accuracy, specificity, reproducibility, F1 coefficient, and area under the curve.
Therefore, the results from the deep learning models used show converging performance. The LSTM and BiLSTM models showed high accuracy in positive cases, with a retrieval rate of 0.99. The Transformer model showed the highest accuracy of 0.95 and highest specificity of 0.76. The Graph Neural Network (GNN) showed comparable performance to the other models, with competitive performance but not outstanding in any of them. The use of Explainable AI (XAI) enabled the assessment of the importance of the temporal phases and features in both the performance and the decisions of the model. Hence, the findings confirm that the Transformer model has a high capacity for early seizure prediction, and thus, it is useful in the development of reliable early warning systems in patients with epilepsy.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
T. Kaur et al., “Artificial Intelligence in Epilepsy, ” May 01, 2021, Wolters Kluwer Medknow
Publications. doi: 10.4103/0028-3886.317233.
A. Esmaeilpour, S. S. Tabarestani, and A. Niazi, “Deep learning-based seizure prediction using EEG signals: A comparative analysis of classification methods on the CHB-MIT dataset,” Eng. Reports, vol. 6, no. 11, Nov. 2024, doi: 10.1002/eng2.12918.
Y. Huang et al., “Early Prediction of Refractory Epilepsy in Children Under Artificial Intelligence Neural Network,” Front. Neurorobot., vol. 15, Jun. 2021, doi: 10.3389/fnbot.2021.690220.
X. Lu, A. Wen, L. Sun, H. Wang, Y. Guo, and Y. Ren, “An Epileptic Seizure Prediction Method Based on CBAM-3D CNN-LSTM Model,” IEEE J. Transl. Eng. Heal. Med., vol. 11, pp. 417–423, 2023, doi: 10.1109/JTEHM.2023.3290036.
H. K. Ibrahim, N. Rokbani, A. Wali, and A. M. Alimi, “Deep Networks for Medical Images Classification, a Comparative Study,” 2024 IEEE Int. Conf. Artif. Intell. Green Energy, ICAIGE 2024, 2024, doi: 10.1109/ICAIGE62696.2024.10776632.
W. Zhao et al., “Residual and bidirectional LSTM for epileptic seizure detection,” Front. Comput. Neurosci. , vol. 18, 2024, doi: 10.3389/fncom.2024.1415967.
A. Bajaj and V. Sharma, “EEG-Based Epileptic Seizure Prediction Using Variants of the Long Short Term Memory Algorithm,” 2025.
A. Alasiry, G. A. Sampedro, A. Almadhor, R. A. Juanatas, S. Alsubai, and V. Karovic, “Epileptic seizures diagnosis and prognosis from EEG signals using heterogeneous graph neural network,” PeerJ Comput. Sci., vol. 11, 2025, doi: 10.7717/peerj-cs.2765.
R. Hussein, S. Lee, and R. Ward, “Multi-Channel Vision Transformer for Epileptic Seizure Prediction,” Biomedicines, vol. 10, no. 7, Jul. 2022, doi: 10.3390/biomedicines10071551.
P. Kunekar, M. K. Gupta, and P. Gaur, “Detection of epileptic seizure in EEG signals using machine learning and deep learning techniques,” J. Eng. Appl. Sci., vol. 71, no. 1, Dec. 2024, doi: 10.1186/s44147-023-00353-y.
A. Omar and T. Abd El-Hafeez, “Optimizing epileptic seizure recognition performance with feature scaling and dropout layers,” Neural Comput. Appl., vol. 36, no. 6, pp. 2835–2852, Feb. 2024, doi: 10.1007/s00521-023-09204-6.
A. Rahmani, A. Venkitaraman, and P. Frossard, “A Meta-GNN approach to personalized seizure detection and classification,” Mar. 2023, [Online]. Available: http://arxiv.org/abs/2211.02642
M. H. Aslam et al., “Classification of EEG Signals for Prediction of Epileptic Seizures,” Appl. Sci., vol. 12, no. 14, 2022, doi: 10.3390/app12147251.
I. Jemal, N. Mezghani, L. Abou-Abbas, and A. Mitiche, “An Interpretable Deep Learning Classifier for Epileptic Seizure Prediction Using EEG Data,” IEEE Access, vol. 10, pp. 60141–60150, 2022, doi: 10.1109/ACCESS.2022.3176367.
X. Liu et al., “Epileptic seizure prediction based on EEG using pseudo-three-dimensional CNN,” Front. Neuroinform., vol. 18, 2024, doi: 10.3389/fninf.2024.1354436.
Z. Wang, L. Shi, H. Wu, J. Luo, X. Kong, and J. Qi, “DistilCLIP-EEG: Enhancing Epileptic Seizure Detection Through Multi-modal Learning and Knowledge Distillation,” Oct. 2025, doi: 10.1109/JBHI.2025.3603022.
B. Jaishankar, A. M. Ashwini, D. Vidyabharathi, and L. Raja, “A novel epilepsy seizure prediction model using deep learning and classification,” Healthc. Anal., vol. 4, Dec. 2023, doi: 10.1016/j.health.2023.100222.
J. D. Chambers, M. J. Cook, A. N. Burkitt, and D. B. Grayden, “Using Long Short-Term Memory (LSTM) recurrent neural networks to classify unprocessed EEG for seizure prediction,” Front. Neurosci., vol. 18, 2024, doi: 10.3389/fnins.2024.1472747.