Hostname: page-component-745bb68f8f-l4dxg Total loading time: 0 Render date: 2025-01-29T13:33:50.577Z Has data issue: false hasContentIssue false
  • English
  • Français

EARLY WARNING PREDICTION WITH AUTOMATIC LABELLING IN EPILEPSY PATIENTS

Part of: Biology and other natural sciences Mathematical biology in general

Published online by Cambridge University Press:  27 January 2025

PENG ZHANG Open the ORCID record for PENG ZHANG [Opens in a new window] ,
TING GAO Open the ORCID record for TING GAO [Opens in a new window] ,
JIN GUO Open the ORCID record for JIN GUO [Opens in a new window] ,
JINQIAO DUAN Open the ORCID record for JINQIAO DUAN [Opens in a new window]  and
SERGEY NIKOLENKO Open the ORCID record for SERGEY NIKOLENKO [Opens in a new window]
PENG ZHANG
Affiliation:
School of Mathematics and Statistics, Huazhong University of Science and Technology, Wuhan, PR China; e-mail: kazusa_zp@hust.edu.cn Center for Mathematical Science, Huazhong University of Science and Technology, Wuhan, PR China; Steklov-Wuhan Institute for Mathematical Exploration, Huazhong University of Science and Technology, Wuhan, PR China; e-mail: jinguo0805@hust.edu.cn
TING GAO*
Affiliation:
School of Mathematics and Statistics, Huazhong University of Science and Technology, Wuhan, PR China; e-mail: kazusa_zp@hust.edu.cn Center for Mathematical Science, Huazhong University of Science and Technology, Wuhan, PR China; Steklov-Wuhan Institute for Mathematical Exploration, Huazhong University of Science and Technology, Wuhan, PR China; e-mail: jinguo0805@hust.edu.cn
JIN GUO
Affiliation:
School of Mathematics and Statistics, Huazhong University of Science and Technology, Wuhan, PR China; e-mail: kazusa_zp@hust.edu.cn Center for Mathematical Science, Huazhong University of Science and Technology, Wuhan, PR China; Steklov-Wuhan Institute for Mathematical Exploration, Huazhong University of Science and Technology, Wuhan, PR China; e-mail: jinguo0805@hust.edu.cn
JINQIAO DUAN
Affiliation:
Steklov-Wuhan Institute for Mathematical Exploration, Huazhong University of Science and Technology, Wuhan, PR China; e-mail: jinguo0805@hust.edu.cn Department of Mathematics and Department of Physics, Great Bay University, Dongguan, PR China; e-mail: duan@gbu.edu.cn Guangdong Provincial Key Laboratory of Mathematical and Neural Dynamical Systems, Dongguan, China
SERGEY NIKOLENKO
Affiliation:
St. Petersburg Department of the Steklov Mathematical Institute, St. Petersburg, Russia; e-mail: sergey@logic.pdmi.ras.ru
*
e-mail: tgao0716@hust.edu.cn
Get access Rights & Permissions [Opens in a new window]

Abstract

Early warning for epilepsy patients is crucial for their safety and well being, in particular, to prevent or minimize the severity of seizures. Through the patients’ electroencephalography (EEG) data, we propose a meta learning framework to improve the prediction of early ictal signals. The proposed bilevel optimization framework can help automatically label noisy data at the early ictal stage, as well as optimize the training accuracy of the backbone model. To validate our approach, we conduct a series of experiments to predict seizure onset in various long-term windows, with long short-term memory (LSTM) and ResNet implemented as the baseline models. Our study demonstrates that not only is the ictal prediction accuracy obtained by meta learning significantly improved, but also the resulting model captures some intrinsic patterns of the noisy data that a single backbone model could not learn. As a result, the predicted probability generated by the meta network serves as a highly effective early warning indicator.

Keywords

meta learningearly warning indicatorautomatic labellingtippingepilepsy

MSC classification

Secondary: 92-06: Proceedings, conferences, collections, etc. 92B20: Neural networks, artificial life and related topics
Type
Research Article
Information
The ANZIAM Journal , First View , pp. 1 - 16
Check for updates
Copyright
© The Author(s), 2025. Published by Cambridge University Press on behalf of Australian Mathematical Publishing Association Inc.

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Adeli, H., Zhou, Z. and Dadmehr, N., “Analysis of EEG records in an epileptic patient using wavelet transform”, J. Neurosci. Methods 123 (2003) 69–87; doi:10.1016/S0165-0270(02)00340-0.CrossRefGoogle Scholar
Asgari, E. and Mofrad, M. R. K., “Continuous distributed representation of biological sequences for deep proteomics and genomics”, PLoS One 10 (2015) Article ID: e0141287; doi:10.1371/journal.pone.0141287.CrossRefGoogle ScholarPubMed
Ashwin, P. and Zaikin, A., “Pattern selection: the importance of how you get there”, Biophys. J. 108 (2015) 1307–1308; doi:10.1016/j.bpj.2015.01.036.CrossRefGoogle Scholar
Avola, D., Cascio, M., Cinque, L., Fagioli, A., Marini, M. R. and Pannone, D., “Analyzing EEG data with machine and deep learning: a benchmark”, in: International conference on image analysis and processing (eds. Sclaroff, S., Distante, C., Leo, M., Farinella, G. M. and Tombari, F.) (Springer International Publishing, Cham, 2022); doi:10.1007/978-3-031-06427-2_28.Google Scholar
Berglund, N. and Gentz, B., “Metastability in simple climate models: pathwise analysis of slowly driven Langevin equations,” Stoch. Dyn. 2 (2002) 327–356; doi:10.1142/S0219493702000455.CrossRefGoogle Scholar
Berglund, N. and Gentz, B., Noise-induced phenomena in slow-fast dynamical systems: a sample-paths approach (Springer-Verlag, London, 2006); doi:10.1007/1-84628-186-5.Google Scholar
Biggs, R., Carpenter, S. R. and Brock, W. A., “Turning back from the brink: detecting an impending regime shift in time to avert it”, Proc. Natl. Acad. Sci. USA 106 (2009) 826–831; doi:10.1073/pnas.0811729106.CrossRefGoogle Scholar
Birjandtalab, J., Heydarzadeh, M. and Nourani, M., “Automated EEG-based epileptic seizure detection using deep neural networks”, in: 2017 IEEE international conference on healthcare informatics (ICHI), Park City, UT, USA (eds. C. Giraud-Carrier, J. Facelli, H. Nakajima, M. Cummins and G. Meixner) (CPS, IEEE, Los Alamitos, CA, 2017) 552–555 doi:10.1109/ICHI.2017.55.Google Scholar
Camfield, P. and Camfield, C., “Idiopathic generalized epilepsy with generalized tonic-clonic seizures (IGE-GTC): a population-based cohort with $>$ 20 year follow up for medical and social outcome”, Epilepsy & Behavior 18 (2010) 61–63; doi:10.1016/j.yebeh.2010.02.014.CrossRefGoogle ScholarPubMed
Cao, Y., Guo, Y., Yu, H. and Yu, X., “Epileptic seizure auto-detection using deep learning method”, in: 2017 4th international conference on systems and informatics (ICSAI), Hangzhou, China, 2017 (eds. X. Fei, L. Wang, C. Ji, N. Chen, Q. Sun, X. Song and X. Wang) (IEEE, Danvers, MA, 2017) 1076–1081; doi:10.1109/ICSAI.2017.8248445.Google Scholar
Carpenter, S. R. and Brock, W. A., “Rising variance: a leading indicator of ecological transition”, Ecol. Lett. 9 (2006) 311–318; doi:10.1111/j.1461-0248.2005.00877.x.CrossRefGoogle ScholarPubMed
Charikar, M., Steinhardt, J. and Valiant, G., “Learning from untrusted data”, in: Proceedings of the 49th annual ACM SIGACT symposium on theory of computing (eds. H. Hatami, P. McKenzie and V. King) (ACM, Inc., New York, 2017) 47–60; doi:10.1145/3055399.3055491.CrossRefGoogle Scholar
Cogan, D., Birjandtalab, J., Nourani, M., Harvey, J. and Nagaraddi, V., “Multi-biosignal analysis for epileptic seizure monitoring”, Int. J. Neural Syst. 27 (2017) Article ID: 1650031; doi:10.1142/S0129065716500313.CrossRefGoogle ScholarPubMed
Drijfhout, S., Bathiany, S., Beaulieu, C., Brovkin, V., Claussen, M., Huntingford, C., Scheffer, M., Sgubin, G. and Swingedouw, D., “Catalogue of abrupt shifts in Intergovernmental Panel on Climate Change climate models”, Proc. Natl. Acad. Sci. USA 112 (2015) E5777–E5786; doi:10.1073/pnas.1511451112.CrossRefGoogle ScholarPubMed
Ein Shoka, A. A., Dessouky, M. M., El-Sayed, A. and El-Din Hemdan, E., “EEG seizure detection: concepts, techniques, challenges, and future trends”, Multimed. Tools Appl. 82 (2023) 42021–42051; doi:10.1007/s11042-023-15052-2.CrossRefGoogle Scholar
Folke, C., Carpenter, S., Walker, B., Scheffer, M., Elmqvist, T., Gunderson, L. and Holling, C.S., “Regime shifts, resilience, and biodiversity in ecosystem management”, Annu. Rev. Ecol. Evol. Syst. 35 (2004): 557–581; doi:10.1146/annurev.ecolsys.35.021103.105711.CrossRefGoogle Scholar
Gao, T., Duan, J., Kan, X. and Cheng, Z., “Dynamical inference for transitions in stochastic systems with $\alpha$ -stable Lévy noise”, J. Phys. A 49 (2016) Article ID: 294002; doi:10.1088/1751-8113/49/29/294002.CrossRefGoogle Scholar
Gao, Y., Gao, B., Chen, Q., Liu, J. and Zhang, Y., “Deep convolutional neural network-based epileptic electroencephalogram (EEG) signal classification”, Front. Neurol. 11 (2020) Article ID: 525678; doi:10.3389/fneur.2020.00375.CrossRefGoogle ScholarPubMed
Gentiletti, D., Suffczynski, P., Gnatkovsky, V. and de Curtis, M., “Changes of ionic concentrations during seizure transitions—a modeling study”, Intl. J. Neur. Sys. 27 (2017) Article ID: 1750004; doi:10.1142/S0129065717500046.Google ScholarPubMed
Gramacki, A. and Gramacki, J., “A deep learning framework for epileptic seizure detection based on neonatal EEG signals”, Sci. Rep. 12 (2022) Article ID: 13010; doi:10.1038/s41598-022-15830-2.CrossRefGoogle ScholarPubMed
Guo, J., Gao, T., Zhang, P., Han, J. and Duan, J., “Deep reinforcement learning in finite-horizon to explore the most probable transition pathway”, Phys. D 458 (2024) Article ID: 133955; doi:10.1016/j.physd.2023.133955.CrossRefGoogle Scholar
Habashi, A. G., Azab, A. M., Eldawlatly, S. and Aly, G. M., “Generative adversarial networks in EEG analysis: an overview”, J. NeuroEng. Rehabilitation 20 (2023) Article ID: 40; doi:10.1186/s12984-023-01169-w.Google ScholarPubMed
Hartmann, K. G., Schirrmeister, R. T. and Ball, T., “EEG-GAN: generative adversarial networks for electroencephalograhic (EEG) brain signals”, Preprint, 2018, arXiv:1806.01875.Google Scholar
Hirota, M., Holmgren, M, Van Nes, E. H. and Scheffer, M., “Global resilience of tropical forest and savanna to critical transitions”, Science 334 (2011) 232–235; doi:10.1126/science.1210657.CrossRefGoogle ScholarPubMed
Hussein, R., Palangi, H., Ward, R. K. and Wang, Z. J., “Optimized deep neural network architecture for robust detection of epileptic seizures using EEG signals”, Clin. Neurophysiol. 130 (2019) 25–37; doi:10.1016/j.clinph.2018.10.010.CrossRefGoogle ScholarPubMed
Khan, H., Marcuse, L., Fields, M., Swann, K. and Yener, B., “Focal onset seizure prediction using convolutional networks”, IEEE Trans. Biomed. Eng. 65 (2018) 2109–2118; doi:10.1109/TBME.2017.2785401.CrossRefGoogle ScholarPubMed
Kim, M.-J., Youn, Y. C. and Paik, J., “Deep learning-based EEG analysis to classify normal, mild cognitive impairment, and dementia: algorithms and dataset”, NeuroImage 272 (2023) Article ID: 120054; doi:10.1016/j.neuroimage.2023.120054.CrossRefGoogle ScholarPubMed
Lade, S. J. and Gross, T., “Early warning signals for critical transitions: a generalized modeling approach”, PLoS Comput. Biol. 8 (2012) Article ID: e1002360; doi:10.1371/journal.pcbi.1002360.CrossRefGoogle ScholarPubMed
Lee, J.-G., Jun, S., Cho, Y.-W., Lee, H., Kim, G. B., Seo, J. B. and Kim, N., “Deep learning in medical imaging: general overview”, Korean J. Radiol. 18 (2017) Article ID: 570; doi:10.3348/kjr.2017.18.4.570.CrossRefGoogle ScholarPubMed
Lenton, T. M., Livina, V. N., Dakos, V., van Nes, E. H. and Scheffer, M., “Early warning of climate tipping points from critical slowing down: comparing methods to improve robustness”, Philos. Trans. Royal Soc. A 370.1962 (2012) 1185–1204; doi:10.1098/rsta.2011.0304.CrossRefGoogle ScholarPubMed
Meisel, C. and Kuehn, C., “Scaling effects and spatio-temporal multilevel dynamics in epileptic seizures”, PLoS One 7 (2012) Article ID: e30371; doi:10.1371/journal.pone.0030371.CrossRefGoogle ScholarPubMed
Mir, W. A., Anjum, M. and Shahab, S., “Deep-EEG: an optimized and robust framework and method for EEG-based diagnosis of epileptic seizure”, Diagnostics 13 (2023) Article ID: 773; doi:10.3390/diagnostics13040773.CrossRefGoogle ScholarPubMed
Neubert, M. G. and Caswell, H., “Alternatives to resilience for measuring the responses of ecological systems to perturbations”, Ecology 78 (1997) 653–665; doi:10.2307/2266047.CrossRefGoogle Scholar
Nikolenko, S. I., Synthetic data for deep learning, Volume 174 of Springer Optim. Appl. Series (Springer Nature, Cham, Switzerland, 2021); doi:10.1007/978-3-030-75178-4.CrossRefGoogle Scholar
Ott, D., Siddarth, P., Gurbani, S., Koh, S., Tournay, A., Donald Shields, W. and Caplan, R., “Behavioral disorders in pediatric epilepsy: unmet psychiatric need”, Epilepsia 44 (2003) 591–597; doi:10.1046/j.1528-1157.2003.25002.x.CrossRefGoogle ScholarPubMed
Proverbio, D., Skupin, A. and Gonçalves, J., “Systematic analysis and optimization of early warning signals for critical transitions using distribution data”, iScience 26 (2023) Article ID: 107156; doi:10.1016/j.isci.2023.107156.CrossRefGoogle ScholarPubMed
Quail, T., Shrier, A. and Glass, L., “Predicting the onset of period-doubling bifurcations in noisy cardiac systems”, Proc. Natl. Acad. Sci. USA 112 (2015) 9358–9363; doi:10.1073/pnas.1424320112.CrossRefGoogle ScholarPubMed
Ramgopal, S., et al. “Seizure detection, seizure prediction, and closed-loop warning systems in epilepsy”, Epilepsy Behavior 37 (2014) 291–307; doi:10.1016/j.yebeh.2014.06.023.CrossRefGoogle ScholarPubMed
Roy, Y., Banville, H., Albuquerque, I., Gramfort, A., Falk, T. H. and Faubert, J., “Deep learning-based electroencephalography analysis: a systematic review”, J. Neural Eng. 16 (2019) Article ID: 051001; doi:10.1088/1741-2552/ab260c.CrossRefGoogle ScholarPubMed
San-Segundo, R., Gil-Martín, M., D’Haro-Enríquez, L. F., Pardo, J. M., “Classification of epileptic EEG recordings using signal transforms and convolutional neural networks”, Comput. Biol. Med. 109 (2019) 148–158; doi:10.1016/j.compbiomed.2019.04.031.CrossRefGoogle ScholarPubMed
Schabert, V. F., Stern, S., Ferrari, L., Wade, C.T., Willke, R. J. and Hasser, W. A. “Incidence of mental health conditions by seizure control among adults with epilepsy in the United States”, Epilepsy Behavior 134 (2022) Article ID: 108865; doi:10.1016/j.yebeh.2022.108865.CrossRefGoogle ScholarPubMed
Scheffer, M., Carpenter, S., Foley, J. A., Folke, C. and Walker, B., “Catastrophic shifts in ecosystems”, Nature 413 (2001) 591–596; doi:10.1038/35098000.CrossRefGoogle ScholarPubMed
Scheffer, M., et al., “Early-warning signals for critical transitions”, Nature 461 (2009) 53–59; doi:10.1038/nature08227.CrossRefGoogle ScholarPubMed
Sharan, R. V. and Berkovsky, S., “Epileptic seizure detection using multi-channel EEG wavelet power spectra and 1-D convolutional neural networks”, in: 2020 42nd annual international conference of the IEEE engineering in medicine and biology society (EMBC) (ed. R. Barbieri) (IEEE, Danvers, MA, 2020); doi:10.1109/EMBC44109.2020.9176243.Google Scholar
Thurman, D. J., et al., “The burden of premature mortality of epilepsy in high-income countries: a systematic review from the Mortality Task Force of the International League Against Epilepsy.” Epilepsia 58 (2017) 17–26; doi:10.1111/epi.13604.CrossRefGoogle ScholarPubMed
Truong, N. D., Kuhlmann, L., Bonyadi, M. R., Querlioz, D., Zhou, L. and Kavehei, Omid, “Epileptic seizure forecasting with generative adversarial networks.” IEEE Access 7 (2019) 143999–144009; doi:10.1109/ACCESS.2019.2944691.CrossRefGoogle Scholar
Truong, N. D., Nguyen, A. D., Kuhlmann, L., Bonyadi, M. R., Yang, J. and Kavehei, O., “A generalised seizure prediction with convolutional neural networks for intracranial and scalp electroencephalogram data analysis”, Preprint, 2017, arXiv:1707.01976.CrossRefGoogle Scholar
Tsiouris, K. M., et al., “A long short-term memory deep learning network for the prediction of epileptic seizures using EEG signals”, Comput. Biol. Med. 99 (2018) 24–37; doi:10.1016/j.compbiomed.2018.05.019.CrossRefGoogle Scholar
Veit, A., Alldrin, N., Chechik, G., Krasin, I., Gupta, A. and Belongie, S., “Learning from noisy large-scale datasets with minimal supervision”, in: 30th IEEE conference on computer vision and pattern recognition, CVPR 2017, Honolulu, Hawaii, 21--26 July 2016 (CPS, IEEE, Los Alamitos, CA, 2017); doi:10.1109/CVPR.2017.696.Google Scholar
Wang, R., Dearing, J. A., Langdon, P. G., Zhang, E., Yang, X., Dakos, V. and Scheffer, M., “Flickering gives early warning signals of a critical transition to a eutrophic lake state”, Nature 492 (2012) 419–422; doi:10.1038/nature11655.CrossRefGoogle ScholarPubMed
Wei, W., Gao, T., Chen, X. and Duan, J., “An optimal control method to compute the most likely transition path for stochastic dynamical systems with jumps”, Chaos 32 (2022) Article ID: 051102; doi:10.1063/5.0093924.CrossRefGoogle ScholarPubMed
World Health Organization, “Epilepsy” (accessed 9 February 2023); https://www.who.int/news-room/fact-sheets/detail/epilepsy.Google Scholar
Yang, L., Ding, S., Zhou, H.-M. and Yang, X., “A strategy combining intrinsic time-scale decomposition and a feedforward neural network for automatic seizure detection”, Physiol. Meas. 40 (2019) Article ID: 095004; doi:10.1088/1361-6579/ab3e2e.CrossRefGoogle Scholar
Yang, L., Gao, T., Wei, W., Dai, M., Fang, C. and Duan, J., “Multi-task meta label correction for time series prediction”, Pattern Recognit. 150 (2024) Article ID: 110319; doi:10.1016/j.patcog.2024.110319.CrossRefGoogle Scholar
Zaveri, H. P., Duckrow, R. B. and Spencer, S. S., “On the use of bipolar montages for time-series analysis of intracranial electroencephalograms”, Clin. Neurophysiol. 117 (2006) 2102–2108; doi:10.1016/j.clinph.2006.05.032.CrossRefGoogle ScholarPubMed
Zhang, C., Bengio, S., Hardt, M. and Recht, B., “Understanding deep learning (still) requires rethinking generalization”, Commun. ACM 64 (2021) 107–115; doi:10.1145/3446776.CrossRefGoogle Scholar
Zheng, G., Awadallah, A. H. and Dumais, S., “Meta label correction for noisy label learning”, in: Proceedings of the AAAI conference on artificial intelligence, Vol. 35 (AAAI Press, Palo Alto, CA, 2021) 11053–11061; doi:10.1609/aaai.v35i12.17319.CrossRefGoogle Scholar