OBJECTIVE: Seizure unpredictability can be debilitating and dangerous for people with epilepsy. Accurate seizure forecasters could improve quality of life for those with epilepsy but must be practical for long-term use. This study presents the first validation of a seizure-forecasting system using ultra-long-term, non-invasive wearable data. METHODS: Eleven participants with epilepsy were recruited for continuous monitoring, capturing heart rate and step count via wrist-worn devices and seizures via electroencephalography (average recording duration of 337 days). Two hybrid models-combining machine learning and cycle-based methods-were proposed to forecast seizures at both short (minutes) and long (up to 44 days) horizons. RESULTS: The Seizure Warning System (SWS), designed for forecasting near-term seizures, and the Seizure Risk System (SRS), designed for forecasting long-term risk, both outperformed traditional models. In addition, the SRS reduced high-risk time by 29% while increasing sensitivity by 11%. SIGNIFICANCE: These improvements mark a significant advancement in making seizure forecasting more practical and effective.

Czech Institute of Informatics Robotics and Cybernetics Czech Technical University Prague Prague Czech Republic

Department of Biomedical Engineering University of Melbourne Melbourne Victoria Australia

Department of Medicine St Vincent's Hospital Melbourne University of Melbourne Melbourne Victoria Australia

Department of Microsystems Engineering University of Freiburg Freiburg Germany

Department of Neurosurgery Epilepsy Center Medical Center University of Freiburg Freiburg Germany

Departments of Neurology and Physiology and Biomedical Engineering Mayo Foundation Rochester Minnesota USA

Graeme Clark Institute University of Melbourne Melbourne Victoria Australia

Institute of Psychiatry Psychology and Neuroscience King's College London London UK

S Labs AI Pty Ltd Melbourne Australia

School of Engineering University of North Florida Jacksonville Florida USA

Seer Medical Melbourne Victoria Australia

Zobrazit více v PubMed

Abramovici S, Bagić A. Epidemiology of epilepsy. Handb Clin Neurol. 2016;138:159–171. PubMed

Kwan P, Brodie MJ. Early identification of refractory epilepsy. N Engl J Med. 2000;342(5):314–319. PubMed

Tian N, Boring M, Kobau R, Zack MM, Croft JB. Active Epilepsy and Seizure Control in Adults — United States, 2013 and 2015. MMWR Morb Mortal Wkly Rep. 2018;67(15):437–442. doi: 10.15585/mmwr.mm6715a1 PubMed DOI PMC

Deloitte Access Economics. The Economic Burden of Epilepsy in Australia, 2019–2020. Epilepsy; Australia; 2019.

Arthurs S, Zaveri HP, Frei MG, Osorio I. Patient and caregiver perspectives on seizure prediction. Epilepsy Behav. 2010;19(3):474–477. PubMed

Epilepsy Foundation. Ei2 Community Survey. Epilepsy Foundation; 2016:6. Accessed March 6, 2020. rajn

Schulze-Bonhage A, Sales F, Wagner K, et al. Views of patients with epilepsy on seizure prediction devices. Epilepsy Behav. 2010;18(4):388–396. PubMed

Dumanis SB, French JA, Bernard C, Worrell GA, Fureman BE. Seizure forecasting from idea to reality. Outcomes of the my seizure gauge epilepsy innovation institute workshop. eNeuro. 2017;4(6). PubMed PMC

Grzeskowiak CL, Dumanis SB. Seizure forecasting: patient and caregiver perspectives. Front Neurol. 2021;12:717428. PubMed PMC

Stirling RE, Cook MJ, Grayden DB, Karoly PJ. Seizure forecasting and cyclic control of seizures. Epilepsia. Published online 2020. PubMed

Karoly PJ, Eden D, Nurse ES, et al. Cycles of self-reported seizure likelihood correspond to yield of diagnostic epilepsy monitoring. Epilepsia. 2021;62(2):416–425. PubMed

Naim-Feil J, Stirling RE, Karoly PJ, et al. Pro-ictal EEG scheduling improves the yield of epilepsy monitoring: Validating the use of multiday seizure cycles to optimize video-EEG timing. Ann Neurol. Published online 2024. doi: 10.1002/ana.27078 PubMed DOI

Stirling RE, Nurse ES, Payne D, et al. User experience of a seizure risk forecasting app: a mixed methods investigation. Epilepsy Behav. Published online 2024. PubMed

Brinkmann BH, Wagenaar J, Abbot D, et al. Crowdsourcing reproducible seizure forecasting in human and canine epilepsy. Brain. 2016;139(6):1713–1722. PubMed PMC

Cook MJ, O’Brien TJ, Berkovic SF, 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. Lancet Neurol. 2013;12(6):563–571. doi: 10.1016/S1474-4422(13)70075-9 PubMed DOI

Karoly PJ, Goldenholz DM, Freestone DR, et al. Circadian and circaseptan rhythms in human epilepsy: a retrospective cohort study. Lancet Neurol. 2018;17(11):977–985. PubMed

Kuhlmann L, Karoly P, Freestone DR, et al. Epilepsyecosystem.org: crowd-sourcing reproducible seizure prediction with long-term human intracranial EEG. Brain. Published online August 8, 2018. doi: 10.1093/brain/awy210 PubMed DOI PMC

Maturana MI, Meisel C, Dell K, et al. Critical slowing as a biomarker for seizure susceptibility. Nat Commun. Published online 2020. PubMed PMC

Nejedly P, Kremen V, Sladky V, et al. Deep-learning for seizure forecasting in canines with epilepsy. J Neural Eng. 2019;16(3):036031. doi: 10.1088/1741-2552/ab172d PubMed DOI

Kremen V, Brinkmann BH, Kim I, et al. Integrating Brain Implants With Local and Distributed Computing Devices: A Next Generation Epilepsy Management System. IEEE J Transl Eng Health Med. 2018;6:1–12. doi: 10.1109/JTEHM.2018.2869398 PubMed DOI PMC

Pal Attia T, Crepeau D, Kremen V, et al. Epilepsy Personal Assistant Device-A Mobile Platform for Brain State, Dense Behavioral and Physiology Tracking and Controlling Adaptive Stimulation. Front Neurol. 2021;12:704170–704170. doi: 10.3389/fneur.2021.704170 PubMed DOI PMC

Leguia MG, Rao VR, Tcheng TK, et al. Learning to generalize seizure forecasts. Epilepsia. Published online 2022. PubMed

Proix T, Truccolo W, Leguia MG, et al. Forecasting seizure risk in adults with focal epilepsy: a development and validation study. Lancet Neurol. 2021;20(2):127–135. doi: 10.1016/S1474-4422(20)30396-3 PubMed DOI PMC

Pal Attia T, Viana PF, Nasseri M, et al. Seizure forecasting using minimally invasive, ultra-long-term subcutaneous EEG: Generalizable cross-patient models. Epilepsia. Published online May 4, 2022:epi.17265. doi: 10.1111/epi.17265 PubMed DOI PMC

Stirling RE, Maturana MI, Karoly PJ, et al. Seizure Forecasting Using a Novel Sub-Scalp Ultra-Long Term EEG Monitoring System. Front Neurol. 2021;12:713794. doi: 10.3389/fneur.2021.713794 PubMed DOI PMC

Viana PF, Pal Attia T, Nasseri M, et al. Seizure forecasting using minimally invasive, ultra-long-term subcutaneous electroencephalography: Individualized intrapatient models. Epilepsia. Published online April 16, 2022:epi.17252. doi: 10.1111/epi.17252 PubMed DOI PMC

Prathaban BP, Balasubramanian R, Kalpana R. A wearable ForeSeiz headband for forecasting real-time epileptic seizures. IEEE Sens J. 2021;21(23):26892–26901.

Brinkmann BH, Karoly PJ, Nurse ES, et al. Seizure Diaries and Forecasting With Wearables: Epilepsy Monitoring Outside the Clinic. Front Neurol. 2021;12:690404. doi: 10.3389/fneur.2021.690404 PubMed DOI PMC

Janse SA, Dumanis SB, Huwig T, Hyman S, Fureman BE, Bridges JFP. Patient and caregiver preferences for the potential benefits and risks of a seizure forecasting device: A best–worst scaling. Epilepsy Behav. 2019;96:183–191. doi: 10.1016/j.yebeh.2019.04.018 PubMed DOI

Bruno E, Simblett S, Lang A, et al. Wearable technology in epilepsy: The views of patients, caregivers, and healthcare professionals. Epilepsy Behav. 2018;85:141–149. PubMed

Hoppe C, Feldmann M, Blachut B, Surges R, Elger CE, Helmstaedter C. Novel techniques for automated seizure registration: patients’ wants and needs. Epilepsy Behav. 2015;52:1–7. PubMed

Nasseri M, Nurse E, Glasstetter M, et al. Signal quality and patient experience with wearable devices for epilepsy management. Epilepsia. 2020;61 Suppl 1:S25–S35. doi: 10.1111/epi.16527 PubMed DOI

Meisel C, El Atrache R, Jackson M, Schubach S, Ufongene C, Loddenkemper T. Machine learning from wristband sensor data for wearable, noninvasive seizure forecasting. Epilepsia. 2020;61(12):2653–2666. PubMed

Nasseri M, Pal Attia T, Joseph B, et al. Ambulatory seizure forecasting with a wrist-worn device using long-short term memory deep learning. Sci Rep. 2021;11(1):1–9. PubMed PMC

Stirling RE, Grayden DB, D’Souza W, et al. Forecasting seizure likelihood with wearable technology. Front Neurol. 2021;12:704060. PubMed PMC

Xiong W, Stirling RE, Payne DE, et al. Forecasting seizure likelihood from cycles of self-reported events and heart rate: a prospective pilot study. EBioMedicine. 2023;93. PubMed PMC

Gregg NM, Pal Attia T, Nasseri M, et al. Seizure occurrence is linked to multiday cycles in diverse physiological signals. Epilepsia. 2023;64(6):1627–1639. PubMed PMC

Bruno E, Simblett S, Lang A, et al. Wearable technology in epilepsy: The views of patients, caregivers, and healthcare professionals. Epilepsy Behav. 2018;85:141–149. PubMed

Karoly PJ, Stirling RE, Freestone DR, et al. Multiday cycles of heart rate are associated with seizure likelihood: An observational cohort study. EBioMedicine. 2021;72:103619. PubMed PMC

Sladky V, Nejedly P, Mivalt F, et al. Distributed brain co-processor for tracking spikes, seizures and behaviour during electrical brain stimulation. Brain Commun. 2022;4(3):fcac115. doi: 10.1093/braincomms/fcac115 PubMed DOI PMC

Nelson BW, Allen NB. Accuracy of Consumer Wearable Heart Rate Measurement During an Ecologically Valid 24-Hour Period: Intraindividual Validation Study. JMIR MHealth UHealth. 2019;7(3):e10828. doi: 10.2196/10828 PubMed DOI PMC

Haghayegh S, Khoshnevis S, Smolensky MH, Diller KR. Accuracy of PurePulse photoplethysmography technology of Fitbit Charge 2 for assessment of heart rate during sleep. Chronobiol Int. 2019;36(7):927–933. doi: 10.1080/07420528.2019.1596947 PubMed DOI

Germini F, Noronha N, Debono VB, et al. Accuracy and Acceptability of Wrist-Wearable Activity-Tracking Devices: Systematic Review of the Literature. J Med Internet Res. 2022;24(1):e30791. doi: 10.2196/30791 PubMed DOI PMC

Gu F, Khoshelham K, Shang J, Yu F, Wei Z. Robust and accurate smartphone-based step counting for indoor localization. IEEE Sens J. 2017;17(11):3453–3460.

Nasseri M, Attia TP, Joseph B, et al. Non-invasive wearable seizure detection using long–short-term memory networks with transfer learning. J Neural Eng. 2021;18(5):056017. doi: 10.1088/1741-2552/abef8a PubMed DOI

Satopää VA, Baron J, Foster DP, Mellers BA, Tetlock PE, Ungar LH. Combining multiple probability predictions using a simple logit model. Int J Forecast. 2014;30(2):344–356.

Stirling RE, Maturana MI, Karoly PJ, et al. Seizure forecasting using a novel sub-scalp ultra-long term EEG monitoring system. Front Neurol. 2021;12:713794. PubMed PMC

Satopää VA, Baron J, Foster DP, Mellers BA, Tetlock PE, Ungar LH. Combining multiple probability predictions using a simple logit model. Int J Forecast. 2014;30(2):344–356.

Andrzejak RG, Mormann F, Kreuz T, et al. Testing the null hypothesis of the nonexistence of a preseizure state. Phys Rev E. 2003;67(1):010901. PubMed

Snyder DE, Echauz J, Grimes DB, Litt B. The statistics of a practical seizure warning system. J Neural Eng. 2008;5(4):392. PubMed PMC

Leguia MG, Andrzejak RG, Rummel C, et al. Seizure cycles in focal epilepsy. JAMA Neurol. 2021;78(4):454–463. PubMed PMC

Stirling RE, Hidajat CM, Grayden DB, et al. Sleep and seizure risk in epilepsy: bed and wake times are more important than sleep duration. Brain. 2023;146(7):2803–2813. PubMed PMC

Privitera M, Walters M, Lee I, et al. Characteristics of people with self-reported stress-precipitated seizures. Epilepsy Behav EB. 2014;41:74–77. doi: 10.1016/j.yebeh.2014.09.028 PubMed DOI

Billeci L, Marino D, Insana L, Vatti G, Varanini M. Patient-specific seizure prediction based on heart rate variability and recurrence quantification analysis. Biagini G, ed. PLOS ONE. 2018;13(9):e0204339. doi: 10.1371/journal.pone.0204339 PubMed DOI PMC

Patel AD, Moss R, Rust SW, et al. Patient-centered design criteria for wearable seizure detection devices. Epilepsy Behav. 2016;64:116–121. doi: 10.1016/j.yebeh.2016.09.012 PubMed DOI

Cui J, Viana PP, Pal Attia T, et al. Enhancing seizure forecasting by inegrating multiday seizure patterns with deep-learning model utilizing ultra long-term subcutaneous EEG. 2nd Int Conf Artif Intell Epilepsy Neurol Disroders. In Press.

Vossler DG. Forecasting seizure storms using epilepsy wristband sensors. Epilepsy Curr. 2021;21(2):99–101. PubMed PMC

Baud MO, Proix T, Gregg NM, et al. Seizure forecasting: bifurcations in the long and winding road. Epilepsia. Published online 2022. PubMed PMC

Chiang S, Moss R, Black AP, et al. Evaluation and recommendations for effective data visualization for seizure forecasting algorithms. JAMIA Open. 2021;4(1):ooab009. doi: 10.1093/jamiaopen/ooab009 PubMed DOI PMC

Kuhlmann L, Lehnertz K, Richardson MP, Schelter B, Zaveri HP. Seizure prediction—ready for a new era. Nat Rev Neurol. Published online 2018:1. PubMed

Duun-Henriksen J, Baud M, Richardson MP, et al. A new era in electroencephalographic monitoring? Subscalp devices for ultra–long-term recordings. Epilepsia. PubMed