In-Depth Analysis Of Epileptic Episodes For Stress Detection Using Hyperparameter Optimization
DOI:
https://doi.org/10.29284/j3h3ke76Keywords:
Epilepsy, Machine learning.Abstract
This study explores the application of Generative Artificial Intelligence (GenAI) techniques for enhancing epilepsy prediction using physiological data collected from wearable devices such as Fitbit. Epilepsy prediction remains a critical healthcare challenge due to the unpredictable nature of seizures and the limitations of traditional methods. To address this, a data-driven prediction framework is proposed that leverages advanced AI models to analyze temporal patterns in multimodal physiological signals. The research systematically examines key components of the prediction pipeline, including data preprocessing, feature engineering, model selection, and performance evaluation. Special emphasis is placed on optimizing model accuracy, reliability, and computational efficiency through the integration of modern AI approaches. The study also considers the broader implications of wearable-based prediction systems, highlighting their potential for cost-effective and real-time healthcare monitoring. By improving the robustness and practical applicability of epilepsy prediction models, this work aims to support early detection and enable proactive clinical interventions. Ultimately, the proposed framework contributes to advancing intelligent healthcare systems and improving patient outcomes through timely and reliable seizure prediction.
References
1. Iqbal, T., et al.: Stress monitoring using wearable sensors: a pilot study and stress-predict dataset. Sensors. 22(21), 8135 (2022). https://doi.org/10.3390/s22218135
2.Muaremi, A., Arnrich, B., Tröster, G.: Towards measuring stress with smartphones and wear-able devices during workday and sleep. BioNanoSci. 3, 172–183 (2013). https://doi.org/10. 1007/s12668-013-0089-2
3.Vos, G., Trinh, K., Sarnyai, Z., Rahimi Azghadi, M.: Generalizable machine learning for stress monitoring from wearable devices: a systematic literature review. Int. J. Med. Inform. 173, 105026 (2023). https://doi.org/10.1016/j.ijmedinf.2023.105026. Epub 2023 Feb 28
4. Kerr, R., McHugh, M., McCrory, M.: HSE management standards and stress-related work outcomes. Occup. Med. 59(8), 574–579 (2009). https://doi.org/10.1093/occmed/kqp146
5. Guk, K., et al.: Evolution of wearable devices with real-time disease monitoring for person-alized healthcare. Nanomaterials (Basel). 9(6), 813 (2019). https://doi.org/10.3390/nano90 60813. PMID: 31146479; PMCID: PMC6631918
6. Kaczor, E.E., Carreiro, S., Stapp, J., Chapman, B., Indic, P.: Objective measurement of physi-cian stress in the emergency department using a wearable sensor. In: Proceedings of the Annual Hawaii International Conference on System Sciences. Annual Hawaii International Conference on System Sciences, Big Island, Hawaii, 3–6 January 2000, vol. 2020, p. 3729 (2020)
7. Suni Lopez, F., Condori-Fernandez, N., Catala, A.: Towards real-time automatic stress detec-tion for office workplaces. In: Proceedings of the Information Management and Big Data: 5th International Conference, SIMBig 2018, Lima, Peru, 3–5 September 2018, pp. 273–288. Springer, Berlin/Heidelberg (2019)
8. Abd Al-Alim, M., Mubarak, R., Salem, N.M., Sadek, I.: A machine learning approach for stress detection using wearable sensors in free-living environments. Comput. Biol. Med. 171, 107926 (2024). https://doi.org/10.1016/j.compbiomed.2024.107926
9. World Health Organization. (2023). "Epilepsy: A public health imperative." Retrieved from WHO website.
10. Saminu, Sani & Xu, Guizhi & Shuai, Zhang & Abd El Kader, Isselmou & Halilu Jabire, Adamu & Ahmed, Yusuf & Karaye, Ibrahim & Ahmad, Isah. (2021). A Recent Investigation on Detection and Classification of Epileptic Seizure Techniques Using EEG Signal. Brain
11. Afrakhteh, Sajjad & Mosavi, M.. (2020). An Efficient Method for Selecting the Optimal Features using Evolutionary Algorithms for Epilepsy Diagnosis. Journal of Circuits, Systems and Computers. 29. 2050195. 10.1142/S0218126620501959
12. Paul, Yash. (2018). Various epileptic seizure detection techniques using biomedical signals: a review. Brain Informatics.
13. Shoeb, A., & Guttag, J. (2010). "Application of machine learning to epileptic seizure detection." Proceedings of the 27th International Conference on Machine Learning, 975-982.
14. Zeng, Wei & Shan, Liangmin & Su, Bo & Du, Shaoyi. (2023). Epileptic seizure detection with deep EEG features by convolutional neural network and shallow classifiers. Frontiers in Neuroscience. 17. 10.3389/fnins.2023.1145526.
15. Mirowski, P., et al. (2009). "Classification of patterns of EEG synchronization for seizure prediction." Clinical Neurophysiology, 120(11), 1927-1940.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
