2690-6791ISSN (Online)
2769-786XISSN (Print)
Volume 15 , Issue 1 , PP: 74-90, 2025 | Cite this article as | XML | Html | PDF | Full Length Article
Mahy E. Elemam 1 * , A. F. Elgamal 2 , I. Elmenshawi 3 , Hanan E. Abdelkader 4
Doi: https://doi.org/10.54216/JISIoT.150107
This paper explores an innovative approach for the automatic detection of epileptic seizures from audio recordings and Heart Rate Variability (HRV) using Convolutional Neural Networks (CNNs). In medical settings, accurately labeling seizure events is critical for patient monitoring. However, manual annotation by experts is not only time-intensive but also highly repetitive. To address this challenge, we developed a structured questionnaire for patients and eyewitnesses, concentrating on observable characteristics during typical seizure events. This questionnaire was used to prospectively study 198 consecutive adult patients with either Psychogenic Non-Epileptic Seizures (PNES) or Epileptic Seizures (ES). For each question, specific signs, symptoms, and risk factors were extracted as variables. The results showed a sensitivity of 95.10% and a specificity of 97.06%, confirming the reliability of the questionnaire. Also, the method proposed in the study categorizes all seizure vocalizations into a singular target event class, modeling the detection task as a binary classification problem target (seizure event) vs. non-target (non-seizure event). The CNN is trained to detect seizure events in short time frames. Experimental results indicate that the method achieves over 92.5% detection accuracy. Furthermore, the research leverages the correlation between pre-ictal epileptic states and HRV features. By addressing the noise interference commonly present during seizures, the proposed model can robustly train the CNN to identify pre-ictal states. The model's performance is promising, yielding an accuracy of over 91.5% for both positive and negative predictions. The proposed system underwent a human evaluation by a group of physicians at Mansoura University Hospital. The results were highly satisfactory, with the doctors expressing strong approval of the system's performance.
Convolutional neural network (CNN) , Epilepsy , Seizure detection , Epilepsy prediction , Sound event detection
[1] Scheffer, I. E., Berkovic, S., Capovilla, G., Connolly, M. B., French, J., et al., "ILAE classification of the epilepsies: Position paper of the ILAE Commission for Classification and Terminology," Epilepsia, 2017.
[2] Akyuz, E., Paudel, Y., Polat, A. K., Dundar, H. E., and Angelopoulou, E., "Enlightening the neuroprotective effect of quercetin in epilepsy: From mechanism to therapeutic opportunities," Epilepsy Behav., vol. 115, pp. 107701, 2021, DOI: 10.1016/j.yebeh.2020.107701.
[3] World Health Organization, "World health organization," [Online]. Available: http://www.who.int/mediacentre/factsheets/fs999/en/, Accessed on: Feb. 7, 2024.
[4] Nijsen, T. M. E., Cluitmans, P. J. M., Arends, J. B. A. M., and Griep, P. A. M., "Detection of subtle nocturnal motor activity from 3-d accelerometry recordings in epilepsy patients," IEEE Trans. Biomed. Eng., vol. 54, no. 11, pp. 2073–2081, 2007.
[5] Stafstrom, C. E., and Carmant, L., "Seizures and Epilepsy: An Overview for Neuroscientists," Cold Spring Harb. Perspect. Med., 2015.
[6] Zhang, L., Wang, X., Jiang, J., Xiao, N., Guo, J., Zhuang, K., et al., "Automatic interictal epileptiform discharge (IED) detection based on convolutional neural network (CNN)," Front. Mol. Biosci., 2023, DOI: 10.3389/fmolb.2023.1146606.
[7] Sharmila, Raj, A., Pandey, S., and Mahalakshmi, P., "Epileptic seizure detection using DWT-based approximate entropy, Shannon entropy and support vector machine: a case study," J. Med. Eng. Technol., vol. 42, pp. 1–8, 2018.
[8] Kurada, A. V., Srinivasan, T., Hammond, S., Ulate-Campos, A., Bidwell, J., "Seizure detection devices for use in antiseizure medication clinical trials: A systematic review," Seizure, vol. 66, pp. 61–69, 2019, DOI: 10.1016/j.seizure.2019.02.007.
[9] Xiaoyan, W., Zhang, Z., and Zhou, Y., "Epileptic seizure detection from multivariate sequential signals using multidimensional convolution network," Res. Square, 2022, DOI: 10.21203.
[10] Moridani, M. K., and Farhadi, H., "Heart rate variability as a biomarker for epilepsy seizure prediction," Bratisl. Med. J., vol. 118, no. 1, pp. 21–25, Jan. 2017, DOI: 10.4149/BLL_2017_001.
[11] Zambrana-Vinaroz, D., Vicente-Samper, J. M., Manrique-Cordoba, J., and Sabater-Navarro, J. M., "Wearable epileptic seizure prediction system based on machine learning techniques using ECG, PPG and EEG signals," Sensors, vol. 22, no. 23, pp. 9372, 2022, DOI: 10.3390/s22239372.
[12] Saminu, S., Xu, G., Zhang, S., Ab El Kader, I., Aliyu, H. A., Jabire, A. H., et al., "Applications of artificial intelligence in automatic detection of epileptic seizures using EEG signals: A review," Artif. Intell. Appl., vol. 1, pp. 11–25, 2022.
[13] Ryu, S., and Joe, I., "A hybrid DenseNet-LSTM model for epileptic seizure prediction," Appl. Sci., vol. 11, no. 7661, 2021.
[14] Lourenço, C. da S., Tjepkema-Cloostermans, M. C., and van Putten, M. J. A. M., "Machine learning for detection of interictal epileptiform discharges," Clin. Neurophysiol., vol. 132, pp. 1433–1443, 2021, DOI: 10.1016/j.clinph.2021.02.403.
[15] Zhengdao, L., Hwang, K., Li, K., and Wu, J., "Graph generative neural network for EEG based epileptic seizure detection via discovery of dynamic brain functional connectivity," Sci. Rep., vol. 12, no. 18998, 2023.
[16] Lee, D., Kim, B., Kim, T., Joe, I., Chong, J., Min, K., and Jung, K., "A ResNet-LSTM hybrid model for predicting epileptic seizures using a pretrained model with supervised contrastive learning," Sci. Rep., vol. 14, no. 1319, 2024, DOI: 10.1038/s41598-023-43328-y.
[17] Srivastava, S., Manjunath, R. K., and Shanthi, P., "Design, simulation and fabrication of a microstrip bandpass filter," Int. J. Sci. Eng. Appl., vol. 3, no. 5, pp. 45–58, 2014, ISSN 2319-7560.
[18] Al Younis, S. M., Hadjileontiadis, L. J., Khandoker, A. H., Stefanini, C., Soulaidopoulos, S., et al., "Prediction of heart failure patients with distinct left ventricular ejection fraction levels using circadian ECG features and machine learning," PLOS ONE, vol. 13, May 2024, DOI: 10.1371/journal.pone.0302639.
[19] Absar, N., et al., "The efficacy of machine-learning-supported smart system for heart disease prediction," Healthcare, vol. 10, no. 6, 2022.
[20] Song, K., et al., "An intelligent epileptic prediction system based on synchrosqueezed wavelet transform and multi-level feature CNN for smart healthcare IoT," Sensors, vol. 22, no. 27, Aug. 2022.
[21] Wu, X., et al., "Epileptic seizure prediction using successive variational mode decomposition and transformers deep learning network," Front. Neurosci, vol. 26, Sept. 2022.
[22] Singh, K., et al., "Two-layer LSTM network-based prediction of epileptic seizures using EEG spectral features," Complex & Intell. Syst., 2022.
[23] Yu, J., et al., "AI-based stroke disease prediction system using real-time electromyography signals," Appl. Sci., vol. 28, Sept. 2020.
[24] Yamakawa, T., et al., "Wearable epileptic seizure prediction system with machine-learning-based anomaly detection of heart rate variability," Sensors, vol. 20, no. 17, July 2020.
[25] Al-Hammadi, F. M., "The impact of audio classification on detecting seizures and psychogenic non-epileptic seizures," 2015.
[26] Arends, J., van Dorp, J., van Hoek, D., Kramer, N., van Mierlo, P., van der Vorst, D., and Tan, F. I. Y., "Diagnostic accuracy of audio-based seizure detection in patients with severe epilepsy and an intellectual disability," Epilepsy Behav., vol. 62, pp. 180–185, 2016.
[27] de Bruijne, G. R., Sommen, P. C. W., and Aarts, R. M., "Detection of epileptic seizures through audio classification," in 4th Eur. Conf. Int. Fed. Med. Biol. Eng., J. Vander Sloten, P. Verdonck, M. Nyssen, and J. Haueisen, Eds. Berlin, Germany: Springer, 2009, pp. 1450–1454.
[28] Srivastava, S., Manjunath, R. K., and Shanthi, P., "Design, simulation and fabrication of a microstrip bandpass filter," Int. J. Sci. Eng. Appl., vol. 3, no. 5, pp. 45–58, 2014.
[29] West, R., "Understanding the accuracy of diagnostic and serology tests: Sensitivity and specificity," Johns Hopkins Center for Health Security, Dec. 2020.
