A machine learning-based wearable device with integrated efficacy assessment and self-corrective mechanism for seizure prediction and proactive epilepsy management
Dhriti Gummaraj
Abstract
This study aims to propose an advanced epilepsy detection and intervention system that predicts seizures 30 minutes to 4 hours in advance, which can help reduce their frequency, and provides personalized, real-time recommendations with a self-corrective mechanism to enhance patient safety and quality of life. The system integrates wearable sensors capturing electroencephalography (EEG), electrocardiography (ECG), electromyography (EMG), electrodermal activity (EDA), heart rate (HR), heart rate variability (HRV), sleep, activity, medication adherence, and lifestyle factors (food intake, periodicity), sourced from local healthcare centers and patient surveys/interviews. Features are extracted using MNE and the system is built using ensembled and deep learning techniques (XGBoost and LSTM), which are trained on multimodal data for seizure detection and prediction, with personalization achieved through patient-specific data retraining and feature importance quantified using SHAP. Findings indicate that even though EEG/ECG highly influence detection, they contribute a mere 20% to prediction accuracy, with HR/HRV impacting 10%, and contextual factors (sleep, medication non-adherence, food intake, over-exertion, and anxiety) dominating with 70%, achieving 83% prediction and 98.5% detection accuracy, with patient-specific patterns (nocturnal vs. awake seizures) boosting outcomes. Limited diversity in local datasets may hinder generalizability; false positives (15%) are reduced via a feedback loop. Future work should diversify data sources and automate efficacy tracking for clinical adoption.
Keywords
epilepsy, seizure prediction, wearable technology, machine learning, self-assessment
Author information & Contribution
High school student from Candor International School, Bangalore, India. Email: krishna.gummaraj@candorschool.net
Disclosure statement
*This paper is a finalist at the 5th International Research Competition (IRC) 2025
Funding
This work was not supported by any funding.
Declaration
The author declares the use of Artificial Intelligence (AI) in writing this paper. In particular, the author used Perplexity to conduct preliminary research, ChatGPT for development & debugging and Grok to structure the paper efficiently. The author takes full responsibility in ensuring proper review and editing of content generated using AI.
Notes
This paper is presented in
Acknowledgement
References
Abbaszadeh, B., Teixeira, C. A. D., & Yagoub, M. C. E. (2022). Online seizure prediction system: A novel probabilistic approach for efficient prediction of epileptic seizure with iEEG signal. The Open Biomedical Engineering Journal, 16, 1–11. https://doi.org/10.2174/18741207-v16-e2208300
Alkhanbouli, R., Matar Abdulla Almadhaani, H., Alhosani, F., & Simsekler, M. C. E. (2025). The role of explainable artificial intelligence in disease prediction: A systematic literature review and future research directions. BMC Medical Informatics and Decision Making, 25(1), 110. https://doi.org/10.1186/s12911-025-02944-6
Baud, M. O., Kleen, J. K., Mirro, E. A., Andrechak, J. C., King-Stephens, D., Chang, E. F., & Rao, V. R. (2018). Multi-day rhythms modulate seizure risk in epilepsy. Nature communications, 9(1), 88. https://doi.org/10.1038/s41467-017-02577-y
Baumgartner, C., Baumgartner, J., Lang, C., Lisy, T., & Koren, J. P. (2025). Seizure detection devices. Journal of Clinical Medicine, 14(3), 863. https://doi.org/10.3390/jcm14030863
Brinkmann, B. H., Karoly, P. J., Nurse, E. S., Dumanis, S. B., Nasseri, M., Viana, P. F., Schulze-Bonhage, A., Freestone, D. R., Worrell, G., Richardson, M. P., & Cook, M. J. (2021). Seizure diaries and forecasting with wearables: Epilepsy monitoring outside the clinic. Frontiers in Neurology, 12, 690404. https://doi.org/10.3389/fneur.2021.690404
Chen, Z., Brodie, M. J., Ding, D., & Kwan, P. (2023). Editorial: Epidemiology of epilepsy and seizures. Frontiers in Epidemiology, 3, 1273163. https://doi.org/10.3389/fepid.2023.1273163
Devinsky, O., Hesdorffer, D. C., Thurman, D. J., Lhatoo, S., & Richerson, G. (2016). Sudden unexpected death in epilepsy: Epidemiology, mechanisms, and prevention. The Lancet Neurology, 15(10), 1075–1088. https://doi.org/10.1016/S1474-4422(16)30158-2
Fernandez Rojas, R., Brown, N., Waddington, G., et al. (2023). A systematic review of neurophysiological sensing for the assessment of acute pain. NPJ Digital Medicine, 6, 76. https://doi.org/10.1038/s41746-023-00810-1
Fisher, R. S., Acevedo, C., Arzimanoglou, A., Bogacz, A., Cross, J. H., Elger, C. E., Engel, J., Jr, Forsgren, L., French, J. A., Glynn, M., Hesdorffer, D. C., Lee, B. I., Mathern, G. W., Moshé, S. L., Perucca, E., Scheffer, I. E., Tomson, T., Watanabe, M., & Wiebe, S. (2014). ILAE official report: a practical clinical definition of epilepsy. Epilepsia, 55(4), 475–482. https://doi.org/10.1111/epi.12550
Frankel, M. A., Lehmkuhle, M. J., Spitz, M. C., Newman, B. J., Richards, S. V., & Arain, A. M. (2021). Wearable reduced-channel EEG system for remote seizure monitoring. Frontiers in Neurology, 12, 728484. https://doi.org/10.3389/fneur.2021.728484
Frassineti, L., Catrambone, V., Lanatà, A., & Valenza, G. (2024). Impaired brain-heart axis in focal epilepsy: Alterations in information flow and implications for seizure dynamics. Network Neuroscience, 8(2), 541–556. https://doi.org/10.1162/netn_a_00367
Furbass, F., Herta, J., Kleiser, R., Kempfner, J., & Kluge, T. (2017). Automatic multimodal long-term EEG monitoring and analysis for epilepsy diagnostics. Clinical Neurophysiology, 128(8), 1508–1518. https://doi.org/10.1016/j.clinph.2017.05.013
Gorman, M. (2024). A novel non-EEG wearable device for the detection of epileptic seizures. Swinburne. https://doi.org/10.25916/sut.27099229.v1
Haridas, B., Chuang, D. T., Nei, M., & Kang, J. Y. (2022). Sudden unexpected death in epilepsy: Pathogenesis, risk factors, and prevention. Seminars in Neurology, 42(5), 658–664. https://doi.org/10.1055/a-1960-1355
Hasan, M., Wu, W., & Zhao, X. (2025). SHAP-Driven Feature Analysis Approach for Epileptic Seizure Prediction. Journal of medical systems, 49(1), 77. https://doi.org/10.1007/s10916-025-02211-1
Haut, S. R., Hall, C. B., Masur, J., & Lipton, R. B. (2007). Seizure occurrence: precipitants and prediction. Neurology, 69(20), 1905–1910. https://doi.org/10.1212/01.wnl.0000278112.48285.84
Hettikankanamage, N., Shafiabady, N., Chatteur, F., Wu, R. M. X., Ud Din, F., & Zhou, J. (2025). eXplainable artificial intelligence (XAI): A systematic review for unveiling the black box models and their relevance to biomedical imaging and sensing. Sensors, 25(21), 6649. https://doi.org/10.3390/s25216649
Kalousios, S., Müller, J., Yang, H., Eberlein, M., Uckermann, O., Schackert, G., Polanski, W. H., & Leonhardt, G. (2025). ECG-based epileptic seizure prediction: Challenges of current data-driven models. Epilepsia Open, 10(1), 143–154. https://doi.org/10.1002/epi4.13073
Karoly, P. J., Eden, D., Nurse, E. S., Cook, M. J., Taylor, J., Dumanis, S., Richardson, M. P., Brinkmann, B. H., & Freestone, D. R. (2021). Cycles of self-reported seizure likelihood correspond to yield of diagnostic epilepsy monitoring. Epilepsia, 62(2), 416–425. https://doi.org/10.1111/epi.16809
Karoly, P. J., Freestone, D. R., Boston, R., Grayden, D. B., Himes, D., Leyde, K., Seneviratne, U., Berkovic, S., O’Brien, T., & Cook, M. J. (2016). Interictal spikes and epileptic seizures: their relationship and underlying rhythmicity. Brain : a journal of neurology, 139(Pt 4), 1066–1078. https://doi.org/10.1093/brain/aww019
Kerr, W. T., McFarlane, K. N., & Figueiredo Pucci, G. (2024). The present and future of seizure detection, prediction, and forecasting with machine learning, including the future impact on clinical trials. Frontiers in Neurology, 15, Article 1425490. https://doi.org/10.3389/fneur.2024.1425490
Khan, S., Nobili, L., Khatami, R., Loddenkemper, T., Cajochen, C., Dijk, D.-J., & Eriksson, S. H. (2018). Circadian rhythm and epilepsy. The Lancet Neurology, 17(12), 1098–1108. https://doi.org/10.1016/S1474-4422(18)30335-1
Kim, T., Nguyen, P., Pham, N., Bui, N., Truong, H., Ha, S., & Vu, T. (2020). Epileptic Seizure Detection and Experimental Treatment: A Review. Frontiers in Neurology, 11. https://doi.org/10.3389/fneur.2020.00701
Koutsouvelis, P., Chybowski, B., Gonzalez-Sulser, A., Abdullateef, S., & Escudero, J. (2024). Preictal period optimization for deep learning-based epileptic seizure prediction. Journal of Neural Engineering, 21(6), 066040. https://doi.org/10.1088/1741-2552/ad9ad0
Kuhlmann, L., Karoly, P. J., Freestone. (2018). Epilepsyecosystem.org: Crowd-sourcing reproducible seizure prediction with long-term human intracranial EEG. Brain, 141(9), 2619–2630. https://doi.org/10.1093/brain/awy210
Kwan, P., & Brodie, M. J. (2000). Early Identification of Refractory Epilepsy. New England Journal of Medicine, 342(5), 314–319. https://doi.org/10.1056/nejm200002033420503
Lehnertz, K., Ansmann, G., Bialonski, S., Dickten, H., Geier, C., & Porz, S. (2016). Evolving networks in the human epileptic brain. Physica D: Nonlinear Phenomena, 323–324, 1–9. https://doi.org/10.1016/j.physd.2013.06.009
Li, J., Karoly, P. J., Grayden, D. B., Cook, M. J., & Nurse, E. S. (2025). Multimodal seizure detection with long-term ambulatory ECG and accelerometry data. medRxiv. https://doi.org/10.64898/2025.12.16.25342428
Malarvili, M. B., & Mesbah, M. (2008). Combining newborn EEG and HRV information for automatic seizure detection. In Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 4756–4759). IEEE. https://doi.org/10.1109/IEMBS.2008.4650276
Markov, K., Elgendi, M., & Menon, C. (2024). EEG-based headset sleep wearable devices. NPJ Biosensing, 1, 12. https://doi.org/10.1038/s44328-024-00013-y
Mesbah, M., Balakrishnan, M., Colditz, P. B., & Boashash, B. (2012). Automatic seizure detection based on the combination of newborn multi-channel EEG and HRV information. EURASIP Journal on Advances in Signal Processing, 2012(1), Article 215. https://doi.org/10.1186/1687-6180-2012-215
Mienye, I. D., Obaido, G., Jere, N., Mienye, E., Aruleba, K., Emmanuel, I. D., & Ogbuokiri, B. (2024). A survey of explainable artificial intelligence in healthcare: Concepts, applications, and challenges. Informatics in Medicine Unlocked, 51, 101587. https://doi.org/10.1016/j.imu.2024.101587
Millán, A. P., van Straaten, E. C. W., Stam, C. J., Nissen, I. A., Idema, S., Baayen, J. C., Van Mieghem, P., & Hillebrand, A. (2022). Epidemic models characterize seizure propagation and the effects of epilepsy surgery in individualized brain networks based on MEG and invasive EEG recordings. Scientific Reports, 12(1), 4086. https://doi.org/10.1038/s41598-022-07730-2
Miron, G., Halimeh, M., Jeppesen, J., Loddenkemper, T., & Meisel, C. (2025). Autonomic biosignals, seizure detection, and forecasting. Epilepsia, 66(Suppl. 3), 25–38. https://doi.org/10.1111/epi.18034
Mormann, F., Andrzejak, R. G., Elger, C. E., & Lehnertz, K. (2007). Seizure prediction: The long and winding road. Brain, 130(2), 314–333. https://doi.org/10.1093/brain/awl241
Muhammad, D., & Bendechache, M. (2024). Unveiling the black box: A systematic review of explainable artificial intelligence in medical image analysis. Computational and Structural Biotechnology Journal, 24, 542–560. https://doi.org/10.1016/j.csbj.2024.08.005
Napa, K. K., Govindarajan, R., Sathya, S., Senthil Murugan, J., & Vijayammal, B. K. P. (2025). Comparative analysis of explainable machine learning models for cardiovascular risk stratification using clinical data and Shapley additive explanations. Intelligence-Based Medicine, 12, 100286. https://doi.org/10.1016/j.ibmed.2025.100286
Pillalamarri, R., & Shanmugam, U. (2025). A review on EEG-based multimodal learning for emotion recognition. Artificial Intelligence Review, 58, 131. https://doi.org/10.1007/s10462-025-11126-9
Poh, M.-Z., Loddenkemper, T., Reinsberger, C., Swenson, N. C., Goyal, S., Sabtala, M. C., Madsen, J. R., & Picard, R. W. (2012). Autonomic changes with seizures correlate with postictal EEG suppression. Neurology, 78(23), 1868–1876. https://doi.org/10.1212/WNL.0b013e318258f7f1
Qaraqe, M., Ismail, M., Serpedin, E., & Zulfi, H. (2016). Epileptic seizure onset detection based on EEG and ECG data fusion. Epilepsy & Behavior, 58, 48–60. https://doi.org/10.1016/j.yebeh.2016.02.039
Regalia, G., Onorati, F., Lai, M., Caborni, C., & Picard, R. W. (2019). Multimodal wrist-worn devices for seizure detection and advancing research: Focus on the Empatica wristbands. Epilepsy Research, 153, 79–82. https://doi.org/10.1016/j.eplepsyres.2019.02.007
Saadoon, Y. A., Khalil, M., & Battikh, D. (2025). Predicting epileptic seizures using EfficientNet-B0 and SVMs: A deep learning methodology for EEG analysis. Bioengineering, 12(2), 109. https://doi.org/10.3390/bioengineering12020109
Schroeder, G. M., Diehl, B., Chowdhury, F. A., Duncan, J. S., de Tisi, J., Trevelyan, A. J., Forsyth, R., Jackson, A., Taylor, P. N., & Wang, Y. (2020). Seizure pathways change on circadian and slower timescales in individual patients with focal epilepsy. Proceedings of the National Academy of Sciences of the United States of America, 117(20), 11048–11058. https://doi.org/10.1073/pnas.1922084117
Shorvon, S. D. (2011). The etiologic classification of epilepsy. Epilepsia, 52(6), 1052–1057. https://doi.org/10.1111/j.1528-1167.2011.03041.x
Slimen, I. B., Boubchir, L., & Seddik, H. (2020). Epileptic seizure prediction based on EEG spikes detection of ictal-preictal states. Journal of Biomedical Research, 34(3), 162–169. https://doi.org/10.7555/JBR.34.20190097
Stevelink, R., Luykx, J. J., Lin, B. D., Leu, C., Lal, D., Smith, A. W., Schijven, D., Carpay, J. A., Rademaker, K., Baldez, R. A. R., … [additional authors]. (2021). Shared genetic basis between genetic generalized epilepsy and background electroencephalographic oscillations. Epilepsia, 62(7), 1518–1527. https://doi.org/10.1111/epi.16922
Sun, T., Yu, T., & Liu, P. (2025). Global, regional, and national burden of epilepsy, 1990–2021: A systematic analysis for the Global Burden of Disease Study in 2021. Cost Effectiveness and Resource Allocation, 23(1), 28. https://doi.org/10.1186/s12962-025-00635-7
Tan, S., Tang, Z., He, Q., Li, Y., Cai, Y., Zhang, J., Fan, D., & Guo, Z. (2025). Automatic detection and prediction of epileptic EEG signals based on nonlinear dynamics and deep learning: A review. Frontiers in Neuroscience, 19, 1630664. https://doi.org/10.3389/fnins.2025.1630664
Tang, J., El Atrache, R., Yu, S., Asif, U., Jackson, M., Roy, S., Mirmomeni, M., Cantley, S., Sheehan, T., Schubach, S., Ufongene, C., Vieluf, S., Meisel, C., Harrer, S., & Loddenkemper, T. (2021). Seizure detection using wearable sensors and machine learning: Setting a benchmark. Epilepsia, 62(8), 1807–1819. https://doi.org/10.1111/epi.16967
Tang, T., Zhou, Y., & Zhai, X. (2024). Circadian rhythm and epilepsy: A nationally representative cross-sectional study based on actigraphy data. Frontiers in Neurology, 15, 1496507. https://doi.org/10.3389/fneur.2024.1496507
Ulate-Campos, A., Coughlin, F., Gaínza-Lein, M., Sánchez Fernández, I., Pearl, P. L., & Loddenkemper, T. (2016). Automated seizure detection systems and their effectiveness for each type of seizure. Seizure, 40, 88–101. https://doi.org/10.1016/j.seizure.2016.06.008
Vieluf, S., Tomioka, S., Zhang, B., Krishnan, V., Bosl, W. J., Grinnell, T., & Loddenkemper, T. (2025). Seizure monitoring by combined diary and wearable data: A multicenter, longitudinal, observational study. Epilepsia, 66(11), 4259–4271. https://doi.org/10.1111/epi.18550
Wang, Y., Wang, Y., Qiu, X., Yu, Z., & Wang, L. (2025). Global, regional, and national epilepsy of unknown cause incidence and mortality, 1990–2036: Cross-national health inequalities and predictive analytics. Frontiers in Neurology, 16, 1526984. https://doi.org/10.3389/fneur.2025.1526984
Whitney, R., & Donner, E. J. (2019). Risk factors for sudden unexpected death in epilepsy (SUDEP) and their mitigation. Current Treatment Options in Neurology, 21(2), 7. https://doi.org/10.1007/s11940-019-0547-4
World Health Organization. (2024, July 2). Epilepsy [Fact sheet]. Retrieved from https://www.who.int/news-room/fact-sheets/detail/epilepsy
You, S. M., Cho, B. H., Bae, H. E., Kim, Y. K., Kim, J. R., Park, S. R., Shon, Y. M., Seo, D. W., & Kim, I. Y. (2023). Exploring autonomic alterations during seizures in temporal lobe epilepsy: Insights from a heart-rate variability analysis. Journal of Clinical Medicine, 12(13), 4284. https://doi.org/10.3390/jcm12134284
Zambrana-Vinaroz, D., Vicente-Samper, J. M., Manrique-Cordoba, J., & Sabater-Navarro, J. M. (2022). Wearable epileptic seizure prediction system based on machine learning techniques using ECG, PPG, and EEG signals. Sensors, 22(23), 9372. https://doi.org/10.3390/s22239372
Cite this article:
Gummaraj, D. (2025). A machine learning-based wearable device with integrated efficacy assessment and self-corrective mechanism for seizure prediction and proactive epilepsy management. The Research Probe, 5(2), 173-189. https://doi.org/10.53378/trp.200
License:
This work is licensed under a Creative Commons Attribution (CC BY 4.0) International License.
Most read articles
- Senior High School Strand Alignment and Its Implication to The Tertiary Programs: A Basis for Bridging Program
- Reading Comprehension Difficulties Among Junior High School Learners
- Difficulties in the writing skills of Grade 11 HUMSS students
- Identifying gender stereotypes of high school LGBTQ students
- Lived experiences of senior high school focal persons in the implementation of work immersion program
- Factors Influencing Reading Comprehension and Difficulties Among Intermediate Learners: Basis For Developing Remedial Reading Intervention
- Disaster risk reduction and management on earthquake preparedness: An assessment
- Digital Marketing Strategies Used by Competing Coffee Shops in Candelaria, Quezon: Perspective of Employees
- Analysis of school rules and regulation implementation: Basis for policy enhancement program
- Technical vocational students’ higher learning institution preference and level of academic and skills preparedness