Study of epileptic seizure prediction based on a small-scale neural network

doi:10.3969/j.issn.1006-7795.2025.01.015

Abstract

Abstract: Objective To explore an epileptic seizure prediction method for patients with refractory epilepsy to improve the classification and prediction efficiency of epileptic electroencephalogram (EEG) signals. Methods The study used the long-term EEG database of patients with intractable epilepsy from Children's Hospital Boston (CHB-MIT). The EEG features of epileptic seizures and preictal periods were extracted from multiple dimensions such as EEG synchronization, complexity, and energy distribution, and then these features were input into the artificial neural network model for classification and identification, thereby achieving accurate prediction of epilepsy. The performance were optimized by adjusting the model parameters, and a comparative evaluation was conducted with existing deep learning models. Results The model proposed in this study showed an accuracy rate of 99.29%, a precision of 91.44%, a sensitivity of 96.46%, and a specificity of 99.46%. Compared with current epilepsy seizure prediction studies based on machine learning or deep learning frameworks, the model in this study improved its classification prediction capabilities and demonstrated higher prediction accuracy. Conclusion An effective prediction of epileptic seizures was achieved by manually extracting epileptic EEG features and constructing an artificial neural network model. The model demonstrated high accuracy and stability, providing reliable technique to support clinical treatment and prevention of epilepsy.

Key words: epileptic seizure prediction, electroencephalography, feature extraction, machine learning

CLC Number:

TP391

Ouyang Hui, Li Yutang, Lou Xiaoyue, Liu Renshuo, Sun Jingxiao, Li Chunlin, Zhang Xu. Study of epileptic seizure prediction based on a small-scale neural network[J]. Journal of Capital Medical University, 2025, 46(1): 91-98.

References

［1］ Johnson E L. Seizures and epilepsy［J］. Med Clin North Am, 2019, 103(2): 309－324.
［2］ Thijs R D, Surges R, O'Brien T J, et al. Epilepsy in adults［J］. Lancet, 2019, 393(10172): 689－701.
［3］ Kalilani L, Sun X Z, Pelgrims B, et al. The epidemiology of drug-resistant epilepsy: a systematic review and meta-analysis［J］. Epilepsia, 2018, 59(12): 2179－2193.
［4］ Niestroj L M, Perez-Palma E, Howrigan D P, et al. Epilepsy subtype-specific copy number burden observed in a genome-wide study of 17 458 subjects［J］. Brain, 2020, 143(7): 2106－2118.
［5］ Allers K, Essue B M, Hackett M L, et al. The economic impact of epilepsy: a systematic review［J］. BMC Neurol, 2015, 15: 245.
［6］吴逊. 癫痫治疗策略［J］. 现代神经疾病杂志, 2002, 2(4): 200－202.
［7］ Cook M J, O'Brien T J, Berkovic S F, et al. Prediction of seizure likelihood with a long-term, implanted seizure advisory system in patients with drug-resistant epilepsy: a first-in-man study［J］. Lancet Neurol, 2013, 12(6): 563－571.
［8］ Acharya U R, Hagiwara Y, Adeli H. Automated seizure prediction［J］. Epilepsy Behav, 2018, 88: 251－261.
［9］ Nabbout R, Kuchenbuch M. Impact of predictive, preventive and precision medicine strategies in epilepsy［J］. Nat Rev Neurol, 2020, 16(12): 674－688.
［10］ Benbadis S R, Beniczky S, Bertram E, et al. The role of EEG in patients with suspected epilepsy［J］. Epileptic Disord, 2020, 22(2): 143－155.
［11］ Alexandre T C, Direito B, Bandarabadi M, et al. Epileptic seizure predictors based on computational intelligence techniques:a comparative study with 278 patients［J］. Comput Methods Programs Biomed, 2014, 114(3): 324－336.
［12］ Karoly P J, Freestone D R, Boston R, et al. Interictal spikes and epileptic seizures: their relationship and underlying rhythmicity［J］. Brain, 2016, 139(Pt 4): 1066－1078.
［13］ Rebello B C, Ramirez A R G, Heredia-Negron F, et al. A machine learning-based approach to epileptic seizure prediction using electro-encephalographic signals［J］. J Eng Res(Ponta Grossa), 2022, 2(8): 10.22533/at.ed.317282219056.
［14］ Parvez M Z, Paul M. Epileptic seizure prediction by exploiting spatiotemporal relationship of EEG signals using phase correlation［J］. IEEE Trans Neural Syst Rehabil Eng, 2016, 24(1): 158－168.
［15］ Li H, Zhang Q, Lin Z, et al. Prediction of epilepsy based on tensor decomposition and functional brain network［J］. Brain Sci, 2021, 11(8): 1066.
［16］ Wang X S, Gong G H, Li N, et al. Detection analysis of epileptic EEG using a novel random forest model combined with grid search optimization［J］. Front Hum Neurosci, 2019, 13: 52.
［17］ Wang X, Zhang C, Karkkainen T, et al. Channel increment strategy-based 1D convolutional neural networks for seizure prediction using intracranial EEG［J］. IEEE Trans Neural Syst Rehabil Eng, 2023, 31: 316－325.
［18］ Wang X S, Zhang G H, Wang Y, et al. One-dimensional convolutional neural networks combined with channel selection strategy for seizure prediction using long-term intracranial EEG［J］. Int J Neural Syst, 2022, 32(2): 2150048.
［19］ Qi N, Piao Y, Yu P, et al. Predicting epileptic seizures based on EEG signals using spatial depth features of a 3D-2D hybrid CNN［J］. Med Biol Eng Comput, 2023, 61(7): 1845－1856.
［20］ Ding X, Nie W W, Liu X Y, et al. Compact convolutional neural network with multi-headed attention mechanism for seizure prediction［J］. Int J Neural Syst, 2023, 33(3): 2350014.
［21］ Choi W H, Kim M J, Yum M S, et al. Deep convolutional gated recurrent unit combined with attention mechanism to classify preictal from interictal EEG with minimized number of channels［J］. J Pers Med, 2022, 12(5): 763.
［22］ Liu D S, Dong X C, Bian D, et al. Epileptic seizure prediction using attention augmented convolutional network［J］. Int J Neural Syst, 2023, 33(11): 2350054.
［23］ Lu X, Wen A H, Sun L, et al. An epileptic seizure prediction method based on CBAM-3D CNN-LSTM model［J］. IEEE J Transl Eng Health Med, 2023, 11: 417－423.
［24］ Shoeb A H. Application of machine learning to epileptic seizure onset detection and treatment［D］. Harvard: Harvard University, 2009.
［25］ Mao L, Zheng G, Cai Y, et al. Frontotemporal phase lag index correlates with seizure severity in patients with temporal lobe epilepsy［J］. Front Neurol, 2022, 13: 855842.
［26］王雅静, 王群, 李博闻, 等. 基于脑电信号预发作数据段选取的癫痫发作预测［J］. 浙江大学学报:工学版, 2020, 54(11): 2258－2265.
［27］ Ilyas A, Alamoudi O A, Riley K O, et al. Proictal state in human temporal lobe epilepsy［J］. NEJM Evid, 2023, 2(3): EVIDoa2200187.
［28］ Ziv J, Lempel A. Compression of individual sequences via variable-rate coding［J］. IEEE Trans Inf Theory, 1978, 24(5): 530－536.
［29］ Ra J S, Li T N, Zhou Yanli. A novel epileptic seizure prediction method based on synchroextracting transform and 1-dimensional convolutional neural network［J］. Comput Methods Programs Biomed, 2023, 240: 107678.
［30］ Jiang X, Liu X, Liu Y, et al. Epileptic seizures detection and the analysis of optimal seizure prediction horizon based on frequency and phase analysis［J］. Front Neurosci, 2023, 17: 1191683.