Epileptic Seizures Detection with Low Processing Load Using the R-R interval of ECG Signals and Deep Neural Network

Ghaempour, Mostafa; Hassanli, Kourosh; Abiri, Ebrahim

doi:10.22055/jaree.2026.50180.1249

Epileptic Seizures Detection with Low Processing Load Using the R-R interval of ECG Signals and Deep Neural Network

Document Type : Research article

Authors

Mostafa Ghaempour

Kourosh Hassanli

Ebrahim Abiri

Department of Electrical Engineering, Shiraz University of Technology

10.22055/jaree.2026.50180.1249

Abstract

Early detection of seizure occurrence is important in improving the lives of patients with epilepsy. Although various methods have been presented so far, there are still challenges regarding the ease of using these methods. This paper aims to present an approach based on neural networks to detect epileptic seizures using ECG signals instead of EEG signals. In the proposed method, only single-lead ECG signals are used for detecting seizures, making them highly suitable for wearable instruments. In the proposed approach, light pre-processing is first performed to prepare raw ECG signals as labeled data. Then, R-R intervals are extracted and considered as features for classification. Without using other manual feature extraction methods, a combined structure of a convolutional neural network and a bidirectional long short-term memory network is employed for automatic feature extraction and classification. The proposed method was evaluated using a strict Leave-One-Subject-Out cross-validation on five patients, achieving a mean accuracy of 82.4%, sensitivity of 74.4%, specificity of 91.3%, and an aggregated AUC of 0.844. The model requires approximately 4500 trainable parameters, confirming its low computational load. This research demonstrates that a single-lead ECG signal, combined with a lightweight deep learning algorithm, can be effectively used in monitoring systems for epilepsy patients.

Highlights

Detection of epileptic seizures using only a single-lead ECG signal, suitable for wearable devices
Combined CNN-BiLSTM network for automatic feature extraction from R-R intervals, no manual features needed
Low-complexity model with only ~4500 trainable parameters, confirmed by Leave-One-Subject-Out cross-validation
Mean accuracy of 82.4% and specificity of 91.3%, offering a practical alternative to multi-channel EEG systems

Keywords

Epileptic seizure

detection

deep neural network

ECG signals

R-R interval

Subjects

Neural Networks

[1] J.-J. Fan, W. Shan, J.-P. Wu, and Q. Wang, "Research progress of vagus nerve stimulation in the treatment of epilepsy," CNS Neuroscience & Therapeutics, vol. 25, no. 11, pp. 1222–1228, 2019. DOI: https://doi.org/10.1111/cns.13209.

[2] J. M. Rho and D. Boison, "The metabolic basis of epilepsy," Nature Reviews Neurology, vol. 18, no. 6, pp. 333–347, 2022. DOI: https://doi.org/10.1038/s41582-022-00651-8.

[3] T. Kim, P. Nguyen, N. Pham, N. Bui, H. Truong, S. Ha, and T. Vu, "Epileptic seizure detection and experimental treatment: A review," Frontiers in Neurology, vol. 11, Art. no. 701, 2020. DOI: https://doi.org/10.3389/fneur.2020.00701.

[4] A. Shoeibi et al., "Epileptic seizures detection using deep learning techniques: A review," International Journal of Environmental Research and Public Health, vol. 18, no. 11, Art. no. 5780, 2021. DOI: https://doi.org/10.3390/ijerph18115780.

[5] J. J. Falco-Walter, I. E. Scheffer, and R. S. Fisher, "The new definition and classification of seizures and epilepsy," Epilepsy Research, vol. 139, pp. 73–79, 2018. DOI: https://doi.org/10.1016/j.eplepsyres.2017.11.015.

[6] X. Qiu, F. Yan, and H. Liu, "A difference attention ResNet-LSTM network for epileptic seizure detection using EEG signal," Biomedical Signal Processing and Control, vol. 83, Art. no. 104652, 2023. DOI: https://doi.org/10.1016/j.bspc.2023.104652.

[7] A. C. Modi, A. D. Patel, C. A. Mara, M. Schmidt, J. R. Tenney, and J. Stevens, "Pilot randomized controlled clinical trial of an adherence social norms intervention for adolescents with epilepsy," Epilepsy & Behavior, vol. 140, Art. no. 109082, 2023. DOI: https://doi.org/10.1016/j.yebeh.2022.109082.

[8] L. Kuhlmann, K. Lehnertz, M. P. Richardson, B. Schelter, and H. P. Zaveri, "Seizure prediction—ready for a new era," Nature Reviews Neurology, vol. 14, no. 10, pp. 618–630, 2018. DOI: https://doi.org/10.1038/s41582-018-0055-2.

[9] B. Olmi, L. Frassineti, A. Lanatà, and C. Manfredi, "Automatic detection of epileptic seizures in neonatal intensive care units through EEG, ECG and video recordings: A survey," IEEE Access, vol. 9, pp. 138174–138191, 2021. DOI: https://doi.org/10.1109/ACCESS.2021.3118227.

[10] T. Nguyen and C. J. Wusthoff, "Clinical manifestations of neonatal seizures," Pediatrics International, vol. 63, no. 6, pp. 631–635, 2021. DOI: https://doi.org/10.1111/ped.14654.

[11] M. Sahani, S. K. Rout, and P. K. Dash, "FPGA implementation of epileptic seizure detection using semisupervised reduced deep convolutional neural network," Applied Soft Computing, vol. 110, Art. no. 107639, 2021. DOI: https://doi.org/10.1016/j.asoc.2021.107639.

[12] S. Y. Shah, H. Larijani, R. M. Gibson, and D. Liarokapis, "Random neural network based epileptic seizure episode detection exploiting electroencephalogram signals," Sensors, vol. 22, no. 7, Art. no. 2466, 2022. DOI: https://doi.org/10.3390/s22072466.

[13] K. Komal, F. Cleary, J. S. G. Wells, and L. Bennett, "A systematic review of the literature reporting on remote monitoring epileptic seizure detection devices," Epilepsy Research, vol. 201, Art. no. 107334, 2024. DOI: https://doi.org/10.1016/j.eplepsyres.2024.107334.

[14] A. A. E. Shoka, M. M. Dessouky, A. El-Sayed, and E. E.-D. Hemdan, "An efficient CNN based epileptic seizures detection framework using encrypted EEG signals for secure telemedicine applications," Alexandria Engineering Journal, vol. 65, pp. 399–412, 2023. DOI: https://doi.org/10.1016/j.aej.2022.10.014.

[15] W.-L. Mao, H. I. K. Fathurrahman, Y. Lee, and T. W. Chang, "EEG dataset classification using CNN method," in Journal of Physics: Conference Series, vol. 1456, no. 1, 2020, Art. no. 012017. DOI: https://doi.org/10.1088/1742-6596/1456/1/012017.

[16] S. Mao and E. Sejdić, "A review of recurrent neural network-based methods in computational physiology," IEEE Transactions on Neural Networks and Learning Systems, vol. 34, no. 10, pp. 6983–7003, 2023. DOI: https://doi.org/10.1109/TNNLS.2022.3145365.

[17] L. Billeci, D. Marino, L. Insana, G. Vatti, and M. Varanini, "Patient-specific seizure prediction based on heart rate variability and recurrence quantification analysis," PLoS ONE, vol. 13, no. 9, Art. no. e0204339, 2018. DOI: https://doi.org/10.1371/journal.pone.0204339.

[18] J. Jeppesen, A. Fuglsang-Frederiksen, P. Johansen, J. Christensen, S. Wüstenhagen, H. Tankisi, E. Qerama, A. Hess, and S. Beniczky, "Seizure detection based on heart rate variability using a wearable electrocardiography device," Epilepsia, vol. 60, no. 10, pp. 2105–2113, 2019. DOI: https://doi.org/10.1111/epi.16343.

[19] J. Jeppesen, K. Lin, H. M. Melo, J. Pavei, J. L. B. Marques, S. Beniczky, and R. Walz, "Detection of seizures with ictal tachycardia, using heart rate variability and patient adaptive logistic regression machine learning methods: A hospital-based validation study," Epileptic Disorders, vol. 26, no. 2, pp. 199–208, 2024. DOI: https://doi.org/10.1002/epd2.20196.

[20] K. M. Hassan, M. R. Islam, T. T. Nguyen, and M. K. I. Molla, "Epileptic seizure detection in EEG using mutual information-based best individual feature selection," Expert Systems with Applications, vol. 193, Art. no. 116414, 2022. DOI: https://doi.org/10.1016/j.eswa.2021.116414.

[21] S. E. Sánchez-Hernández, R. A. Salido-Ruiz, S. Torres-Ramos, and I. Román-Godínez, "Evaluation of feature selection methods for classification of epileptic seizure EEG signals," Sensors, vol. 22, no. 8, Art. no. 3066, 2022. DOI: https://doi.org/10.3390/s22083066.

[22] L. Yang, Q. Liu, Z. Zhang, L. Gan, Y. Zhang, and J. Wu, "Materials for dry electrodes for the electroencephalography: Advances, challenges, perspectives," Advanced Materials Technologies, vol. 7, no. 3, Art. no. 2100612, 2022. DOI: https://doi.org/10.1002/admt.202100612.

[23] H. Gelbard-Sagiv, S. Pardo, N. Getter, M. Guendelman, F. Benninger, D. Kraus, O. Shriki, and S. Ben-Sasson, "Optimizing electrode configurations for wearable EEG seizure detection using machine learning," Sensors, vol. 23, no. 13, Art. no. 5805, 2023. DOI: https://doi.org/10.3390/s23135805.

[24] A. Delorme, "EEG is better left alone," Scientific Reports, vol. 13, no. 1, Art. no. 2372, 2023. DOI: https://doi.org/10.1038/s41598-023-27528-0.

[25] X. Wei, L. Zhou, Z. Chen, L. Zhang, and Y. Zhou, "Automatic seizure detection using three-dimensional CNN based on multi-channel EEG," BMC Medical Informatics and Decision Making, vol. 18, Suppl. 5, Art. no. 111, 2018. DOI: https://doi.org/10.1186/s12911-018-0693-8.

[26] Y.-H. Chen et al., "Soft, comfortable polymer dry electrodes for high quality ECG and EEG recording," Sensors, vol. 14, no. 12, pp. 23758–23780, 2014. DOI: https://doi.org/10.3390/s141223758.

[27] J.-J. Wang, S.-H. Liu, C.-H. Tsai, I. Manousakas, X. Zhu, and T.-L. Lee, "Signal quality analysis of single-arm electrocardiography," Sensors, vol. 23, no. 13, Art. no. 5818, 2023. DOI: https://doi.org/10.3390/s23135818.

[28] T. De Cooman, C. Varon, B. Hunyadi, W. Van Paesschen, L. Lagae, and S. Van Huffel, "Online automated seizure detection in temporal lobe epilepsy patients using single-lead ECG," International Journal of Neural Systems, vol. 27, no. 7, Art. no. 1750022, 2017. DOI: https://doi.org/10.1142/S012906571750022X.

[29] S. Baghersalimi, T. Teijeiro, D. Atienza, and A. Aminifar, "Personalized real-time federated learning for epileptic seizure detection," IEEE Journal of Biomedical and Health Informatics, vol. 26, no. 2, pp. 898–909, 2022. DOI: https://doi.org/10.1109/JBHI.2021.3097768.

[30] M. Ghaempour, K. Hassanli, and E. Abiri, "An approach to detect and predict epileptic seizures with high accuracy using convolutional neural networks and single-lead-ECG signal," Biomedical Physics & Engineering Express, vol. 10, no. 2, Art. no. 025041, 2024. DOI: https://doi.org/10.1088/2057-1976/ad29a3.

[31] R. E. Stirling et al., "Forecasting seizure likelihood with wearable technology," Frontiers in Neurology, vol. 12, Art. no. 704060, 2021. DOI: https://doi.org/10.3389/fneur.2021.704060.

[32] M. Kołodziej, A. Majkowski, P. Tarnowski, R. J. Rak, and A. Rysz, "A new method of cardiac sympathetic index estimation using a 1D-convolutional neural network," Bulletin of the Polish Academy of Sciences: Technical Sciences, vol. 69, no. 3, Art. no. e137054, 2021. DOI: https://doi.org/10.24425/bpasts.2021.137054.

[33] Z. Lou, L. Wang, K. Jiang, Z. Wei, and G. Shen, "Reviews of wearable healthcare systems: Materials, devices and system integration," Materials Science and Engineering: R: Reports, vol. 140, Art. no. 100523, 2020. DOI: https://doi.org/10.1016/j.mser.2019.100523.

[34] M. M. Taye, "Theoretical understanding of convolutional neural network: Concepts, architectures, applications, future directions," Computation, vol. 11, no. 3, Art. no. 52, 2023. DOI: https://doi.org/10.3390/computation11030052.

[35] I. Al-Aweel, K. Krishnamurthy, J. Hausdorff, J. Mietus, J. Ives, A. Blum, D. Schomer, and A. Goldberger, "Postictal heart rate oscillations in partial epilepsy," Neurology, vol. 53, no. 7, pp. 1590–1590, 1999. DOI: https://doi.org/10.1212/WNL.53.7.1590.

[36] PhysioNet. "Post-Ictal Heart Rate Oscillations in Partial Epilepsy" [Online]. Available: https://physionet.org/content/pihr/1.0.0/.

[37] MathWorks. "MATLAB (Deep Learning Toolbox)" [Online]. Available: https://www.mathworks.com/products/deep-learning.html.

[38] D. P. Kingma and J. Ba, "Adam: A method for stochastic optimization," arXiv preprint arXiv:1412.6980, 2014.

[39] O. Doyle, A. Temko, W. Marnane, G. Lightbody, and G. Boylan, "Heart rate based automatic seizure detection in the newborn," Medical Engineering & Physics, vol. 32, no. 8, pp. 829–839, 2010. DOI: https://doi.org/10.1016/j.medengphy.2010.05.010.

[40] F. Massé, M. V. Bussel, A. Serteyn, J. Arends, and J. Penders, "Miniaturized wireless ECG monitor for real-time detection of epileptic seizures," ACM Transactions on Embedded Computing Systems, vol. 12, no. 4, Art. no. 47, 2013. DOI: https://doi.org/10.1145/2485984.2485990.