Review of Application of Neural Networks in Epileptic Seizure Prediction

doi:10.3778/j.issn.1673-9418.2302001

Abstract

Abstract: Epilepsy, a central nervous system disease caused by abnormal discharge of brain neurons, has a significant impact on patients’ normal life. Early prediction of epileptic seizures and timely preventive measures can effectively improve the quality of life of patients. With the development of data science and big data technology, neural networks are increasingly being applied in the field of epilepsy prediction and have shown great potential for application. This paper provides a review of the application and deficiencies of neural networks in the field of epilepsy prediction, discussing the construction process of epilepsy prediction models in the following order: data- sets, data preprocessing, feature extraction, and neural networks. After introducing the characteristics of EEG signals, common types of datasets, common data preprocessing methods, and common feature extraction methods, especially manual feature extraction methods, this paper focuses on analyzing and summarizing the principles and applications of multi-layer artificial neural networks and spiking neural networks in the field of epilepsy prediction. The disadvantages of neural networks are systematically analyzed, and further application of neural networks in the field of epilepsy prediction is prospected.

Key words: epilepsy, EEG signal, neural networks, epilepsy prediction

摘要： 癫痫作为一种大脑神经元异常放电导致的中枢神经系统疾病，给患者的正常生活带来了极大影响，提前预测癫痫发作并及时采取防范措施可以有效提高患者的生活质量。随着数据科学和大数据技术的发展，神经网络算法越来越多地应用于癫痫预测领域，并展现出了巨大的应用潜力。对神经网络算法在癫痫预测领域的应用情况和不足之处进行了综述，按照癫痫预测模型的搭建流程依次从数据集、数据预处理、特征提取、神经网络算法模型几个模块进行论述。在介绍了脑电信号特点和常用数据集类别、常见数据预处理手段、常见的特征提取方法特别是手工设计特征的提取方法后，重点对多层人工神经网络和脉冲神经网络算法原理及其在癫痫预测领域的应用进行分析梳理和归纳总结，系统性地对神经网络算法的缺点进行剖析，并对神经网络算法在癫痫预测领域的进一步应用发展进行了讨论和展望。

关键词: 癫痫, 脑电信号, 神经网络算法, 癫痫预测

HUANG Honghong, ZHANG Feng, LYU Liangfu, SI Xiaopeng. Review of Application of Neural Networks in Epileptic Seizure Prediction[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(11): 2543-2556.

黄红红, 张丰, 吕良福, 司霄鹏. 神经网络算法在癫痫预测模型中的应用研究综述[J]. 计算机科学与探索, 2023, 17(11): 2543-2556.

References

[1] RASHEED K, QAYYUM A, QADIR J, et al. Machine learning for predicting epileptic seizures using EEG signals: a review[J]. IEEE Reviews in Biomedical Engineering, 2020, 14: 139-155.
[2] EPMOGHADDAM D, SHETH S A, HANEEF Z, et al. Epileptic seizure prediction using spectral width of the covariance matrix[J]. Journal of Neural Engineering, 2022, 19(2): 026029.
[3] LEKSHMY H O, PANICKAR D, HARIKUMAR S. Com-parative analysis of multiple machine learning algorithms for epileptic seizure prediction[J]. Journal of Physics: Con-ference Series, 2022, 2161(1): 012055.
[4] NATU M, BACHUTE M, GITE S, et al. Review on epileptic seizure prediction: machine learning and deep learning approaches[J]. Computational and Mathematical Methods in Medicine, 2022: 239-244.
[5] YANG J, SAWAN M. From seizure detection to smart and fully embedded seizure prediction engine: a review[J]. IEEE Transactions on Biomedical Circuits and Systems, 2020, 14(5): 1008-1023.
[6] 张晓玲. 基于深度学习和头皮脑电的癫痫发作预测研究[D]. 天津: 天津职业技术师范大学, 2022.
ZHANG X L. Research on seizure prediction based on deep learning and scalp EEG[D]. Tianjin: Tianjin University of Technology and Education, 2022.
[7] MESSAOUD R B, CHAVEZ M. Random forest classifier for EEG-based seizure prediction[J]. arXiv:2106.04510, 2021.
[8] PINTO M F, LEAL A, LOPES F, et al. On the clinical acceptance of black-box systems for EEG seizure prediction[J]. Epilepsia Open, 2022, 7(2): 247-259.
[9] TAVANAEI A, GHODRATI M, KHERADPISHEH S R, et al. Deep learning in spiking neural networks[J]. Neural Networks, 2019, 111: 47-63.
[10] USMAN S M, LATIF S, BEG A. Principle components analysis for seizures prediction using wavelet transform[J]. arXiv:2004.07937, 2020.
[11] DAOUD H, BAYOUMI M A. Efficient epileptic seizure prediction based on deep learning[J]. IEEE Transactions on Biomedical Circuits and Systems, 2019, 13(5): 804-813.
[12] XU Y, YANG J, SAWAN M. Multichannel synthetic preictal EEG signals to enhance the prediction of epileptic seizures[J]. IEEE Transactions on Biomedical Engineering, 2022, 69(11): 3516-3525.
[13] USMAN S M, KHALID S, AKHTAR R, et al. Using scalp EEG and intracranial EEG signals for predicting epileptic seizures: review of available methodologies[J]. Seizure, 2019, 71: 258-269.
[14] SINGH K, MALHOTRA J. Two-layer LSTM network-based prediction of epileptic seizures using EEG spectral features[J]. Complex & Intelligent Systems, 2022, 8(3): 2405-2418.
[15] TRUONG N D, NGUYEN A D, KUHLMANN L, et al. Con- volutional neural networks for seizure prediction using intracranial and scalp electroencephalogram[J]. Neural Networks, 2018, 105: 104-111.
[16] YUAN S, ZHOU W, CHEN L. Epileptic seizure prediction using diffusion distance and Bayesian linear discriminate analysis on intracranial EEG[J]. International Journal of Neural Systems, 2018, 28(1): 1750043.
[17] DISSANAYAKE T, FERNANDO T, DENMAN S, et al. Patient-independent epileptic seizure prediction using deep learning models[J]. arXiv:2011.09581, 2020.
[18] LING H, OKADA K. Diffusion distance for histogram comparison[C]//Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recogni- tion, New York, Jun 17-22, 2006. Washington: IEEE Computer Society, 2006: 246-253.
[19] SALAFIAN B, BEN-KNAAN E F, SHLEZINGER N, et al. CNN-aided factor graphs with estimated mutual information features for seizure detection[C]//Proceedings of the 2022 IEEE International Conference on Acoustics, Speech and Signal Processing, Singapore, May 23-27, 2022. Piscataway: IEEE, 2022: 8677-8681.
[20] GUEVARA E, FLORES-CASTRO J A, PENG K, et al. Prediction of epileptic seizures using fNIRS and machine learning[J]. Journal of Intelligent & Fuzzy Systems, 2020, 38(2): 2055-2068.
[21] YANG H, EBERLEIN M, MüLLER J, et al. Seizure prediction with long-term iEEG recordings: what can we learn from data nonstationarity?[C]//Proceedings of the 2021 IEEE International Conference on Bioinformatics and Biomedicine, Houston, Dec 9-12, 2021. Washington: IEEE Computer Society, 2021: 1-6.
[22] LI C, SHAO C, SONG R, et al. Spatio-temporal MLP network for seizure prediction using EEG signals[J]. Measurement, 2023, 206: 112278.
[23] KHAN H, MARCUSE L, FIELDS M, et al. Focal onset seizure prediction using convolutional networks[J]. IEEE Transactions on Biomedical Engineering, 2017, 65(9): 2109- 2118.
[24] XU Y, YANG J, ZHAO S, et al. An end-to-end deep learning approach for epileptic seizure prediction[C]//Proceedings of the 2020 2nd IEEE International Conference on Artificial Intelligence Circuits and Systems, Genova, Aug 31-Sep 2, 2020. Piscataway: IEEE, 2020: 266-270.
[25] KHAN A, SOHAIL A, ZAHOORA U, et al. A survey of the recent architectures of deep convolutional neural networks[J]. Artificial Intelligence Review, 2020, 53: 5455-5516.
[26] WANG X, WANG X, LIU W, et al. One dimensional convolutional neural networks for seizure onset detection using long-term scalp and intracranial EEG[J]. Neurocom-puting, 2021, 459: 212-222.
[27] GUPTA S, RANGA V, AGRAWAL P. EpilNet: a novel approach to IoT based epileptic seizure prediction and diagnosis system using artificial intelligence[J]. arXiv:2111. 03265, 2021.
[28] WANG Z, YANG J, SAWAN M. A novel multi-scale dilated 3D CNN for epileptic seizure prediction[C]//Proceedings of the 2021 IEEE 3rd International Conference on Artificial Intelligence Circuits and Systems, Washington, Jun 6-9, 2021. Piscataway: IEEE, 2021: 1-4.
[29] HUSSEIN R, LEE S, WARD R, et al. Epileptic seizure prediction: a semi-dilated convolutional neural network architecture[C]//Proceedings of the 25th International Con-ference on Pattern Recognition, Milan, Jan 10-15, 2021. Washington: IEEE Computer Society, 2021: 5436-5443.
[30] GAO Y, CHEN X, LIU A, et al. Pediatric seizure prediction in scalp EEG using a multi-scale neural network with dilated convolutions[J]. IEEE Journal of Translational Engineering in Health and Medicine, 2022, 10: 1-9.
[31] LIU C L, XIAO B, HSAIO W H, et al. Epileptic seizure prediction with multi-view convolutional neural networks[J]. IEEE Access, 2019, 7: 170352-170361.
[32] TARIQ Z B, IYENGAR A, MARCUSE L, et al. Patient-specific seizure prediction using single seizure electroencephalography recording[M]//AI for Disease Surveillance and Pandemic Intelligence: Intelligent Disease Detection in Action. Cham: Springer International Publishing, 2022: 295-308.
[33] LIANG D, LIU A, LI C, et al. A novel consistency-based training strategy for seizure prediction[J]. Journal of Neuro-science Methods, 2022, 372: 109557.
[34] YARLAGADDA A, MALLA R M, JANAPANA H. Seizure prediction based on convolution neural network with subnet loss function[J]. International Journal of Intelligent Engineer- ing & Systems, 2022, 15(2): 126-134.
[35] DAS S, PANDEY P, MIYAPURAM K P. Improving self-supervised pretraining models for epileptic seizure detection from EEG data[J]. arXiv:2207.06911, 2022.
[36] RASHEED K, QADIR J, O’BRIEN T J, et al. A generative model to synthesize EEG data for epileptic seizure prediction[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2021, 29: 2322-2332.
[37] LIANG D, LIU A, WU L, et al. Semisupervised seizure prediction in scalp EEG using consistency regularization[J]. Journal of Healthcare Engineering, 2022: 1573076.
[38] WU D, SHI Y, WANG Z, et al. C2SP-Net: joint compression and classification network for epilepsy seizure prediction[J]. arXiv:2110.13674, 2021.
[39] LI C, LAMMIE C, DONG X, et al. Seizure detection and prediction by parallel memristive convolutional neural networks[J]. IEEE Transactions on Biomedical Circuits and Systems, 2022, 16(4): 609-625.
[40] ZHAO S, YANG J, XU Y, et al. Binary single-dimensional convolutional neural network for seizure prediction[C]// Proceedings of the 2020 IEEE International Symposium on Circuits and Systems, Sevilla, Oct 10-21, 2020. Piscataway: IEEE, 2020: 1-5.
[41] AGARWAL P, WANG H C, SRINIVASAN K. Epileptic seizure prediction over EEG data using hybrid CNN-SVM model with edge computing services[C]//Proceedings of the 22nd International Conference on Circuits, Systems, Communications and Computers, Majorca, Jul 14-17, 2018. Paris: EDP Sciences, 2018: 03016.
[42] 汤云琪, 郭滨, 李可欣. 基于改进的LSTM癫痫预测算法研究[J]. 长春理工大学学报(自然科学版), 2021, 44(4): 37-42.
TANG Y Q, GUO B, LI K X. Research on epilepsy prediction algorithm based on improved LSTM[J]. Journal of Changchun University of Science and Technology (Natural Science Edition), 2021, 44(4): 37-42.
[43] ALI H, KARIM F, QURESHI J J, et al. Seizure prediction using bidirectional LSTM[C]//Proceedings of the Cyberspace Data and Intelligence, and Cyber-Living, Syndrome, and Health: International 2019 Cyberspace Congress, CyberDI and CyberLife, Beijing, Dec 16-18, 2019. Cham: Springer, 2019: 349-356.
[44] GODOY R V, REIS T J S, POLEGATO P H, et al. EEG-based epileptic seizure prediction using temporal multi-channel transformers[J]. arXiv:2209.11172, 2022.
[45] HUSSEIN R, LEE S, WARD R. Multi-channel vision trans-former for epileptic seizure prediction[J]. Biomedicines, 2022, 10(7): 1551.
[46] YAN J, LI J, XU H, et al. Seizure prediction based on transformer using scalp electroencephalogram[J]. Applied Sciences, 2022, 12(9): 4158.
[47] HU S, LIU J, YANG R, et al. Exploring the applicability of transfer learning and feature engineering in epilepsy prediction using hybrid transformer model[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2023, 31: 1321-1332.
[48] TAHERKHANI A, BELATRECHE A, LI Y, et al. A review of learning in biologically plausible spiking neural networks[J]. Neural Networks, 2020, 122: 253-272.
[49] GHOSH-DASTIDAR S, ADELI H. A new supervised learning algorithm for multiple spiking neural networks with application in epilepsy and seizure detection[J]. Neural Networks, 2009, 22(10): 1419-1431.
[50] ZARRIN P S, ZIMMER R, WENGER C, et al. Epileptic seizure detection using a neuromorphic-compatible deep spiking neural network[C]//LNCS 12108: Proceedings of the 8th International Work-Conference on Bioinformatics and Biomedical Engineering, Granada, May 6-8, 2020. Cham: Springer, 2020: 389-394.
[51] TIAN F, YANG J, ZHAO S, et al. A new neuromorphic computing approach for epileptic seizure prediction[C]// Proceedings of the 2021 IEEE International Symposium on Circuits and Systems, Daegu, May 22-28, 2021. Piscataway: IEEE, 2021: 1-5.
[52] BURELO K, RAMANTANI G, INDIVERI G, et al. A neuromorphic spiking neural network detects epileptic high frequency oscillations in the scalp EEG[J]. Scientific Reports, 2022, 12(1): 1798.
[53] TRUONG N D, ZHOU L, KAVEHEI O. Semi-supervised seizure prediction with generative adversarial networks[C]//Proceedings of the 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Berlin, Jul 23-27, 2019. Piscataway: IEEE, 2019: 2369-2372.
[54] HOSSEINI M P, SOLTANIAN-ZADEH H, ELISEVICH K, et al. Cloud-based deep learning of big EEG data for epileptic seizure prediction[C]//Proceedings of the 2016 IEEE Global Conference on Signal and Information Processing, Washington, Dec 7-9, 2016. Piscataway: IEEE, 2016: 1151-1155.
[55] KIRAL-KORNEK I, ROY S, NURSE E, et al. Epileptic seizure prediction using big data and deep learning: toward a mobile system[J]. EBioMedicine, 2018, 27: 103-111.
[56] ZAGHLOUL Z S, BAYOUMI M. Early prediction of epilepsy seizures VLSI BCI system[J]. arXiv:1906.02894, 2019.
[57] SEETHALAKSHMI V, NAVEENKUMAR P, PRABU G K, et al. A review on wearable epileptic seizure prediction system[C]//Proceedings of the 2021 International Conference on Computing, Communication, Electrical and Biomedical Systems, Coimbatore, Mar 25-26, 2021. Bristol: IOP Publishing, 2021: 012075.
[58] BOROVAC A, GUDMUNDSSON S, THORVARDSSON G, et al. Ensemble learning using individual neonatal data for seizure detection[J]. arXiv:2204.07043, 2022.
[59] CICHY R M, OLIVA A. A M/EEG-fMRI fusion primer: resolving human brain responses in space and time[J]. Neuron, 2020, 107(5).
[60] GABEFF V, TEIJEIRO T, ZAPATER M, et al. Interpreting deep learning models for epileptic seizure detection on EEG signals[J]. Artificial Intelligence in Medicine, 2021, 117: 102084.