Abstract
Epilepsy affects more than 50 million people worldwide, making it one of the world’s most prevalent neurological diseases. The main symptom of epilepsy is seizures, which occur abruptly and can cause serious injury or death. The ability to predict the occurrence of an epileptic seizure could alleviate many risks and stresses people with epilepsy face. We formulate the problem of detecting preictal (or pre-seizure) with reference to normal EEG as a precursor to incoming seizure. To this end, we developed several supervised deep learning approaches model to identify preictal EEG from normal EEG. We further develop novel unsupervised deep learning approaches to train the models on only normal EEG, and detecting pre-seizure EEG as an anomalous event. These deep learning models were trained and evaluated on two large EEG seizure datasets in a person-specific manner. We found that both supervised and unsupervised approaches are feasible; however, their performance varies depending on the patient, approach and architecture. This new line of research has the potential to develop therapeutic interventions and save human lives.
Similar content being viewed by others
Availability of Data and Materials
The datasets used in the paper are publicly available.
References
Shahbazi M, Aghajan H (2018) A generalizable model for seizure prediction based on deep learning using cnn-lstm architecture. In: 2018 IEEE Global conference on signal and information processing (GlobalSIP), Anaheim, USA
Beghi E, Giussani G (2018) Aging and the epidemiology of epilepsy. Neuroepidemiology 51:216–223
Litt B, Echauz J (2002) Prediction of epileptic seizures. Neurology 1:22–30
Nguyen R, T’ellez Zenteno JF (2009) Injuries in epilepsy: a review of its prevalence, risk factors, type of injuries and prevention. Neurol Int 1
Ridsdale L, Charlton J, Ashworth M, Richardson MP, Gulliford MC (2011) Epilepsy mortality and risk factors for death in epilepsy: a population-based study. Br J Gen Pract 61:271–278
Fisher RS (2000) Epilepsy from the patient’s perspective: Review of results of a community-based survey. Epilepsy Behav 1:9–14
Kuhlmann L, Lehnertz K, Richardson MP, Schelter B, Zaveri HP (2018) Seizure prediction — ready for a new era. Nat Rev Neurol 14:618–630
Stacey W, Le Van Quyen M, Mormann F, Schulze-Bonhage A (2011) What is the present-day eeg evidence for a preictal state? Epilepsy Res 97:243–251
Brinkamann BH, Wagenaar J, Abbot D, Adkins P, Bosshard SC, Chen M, Tieng QM, He J, Muñoz-Almaraz FJ, Botella-Rocamora P, Pardo J, Zamora-Martinez F, Hills M, Wu W, Korshunova I, Cukierski W, Vite C, Patterson EE, Litt B, Worrel GA (2016) Crowdsourcing reproducible seizure forecasting in human and canine epilepsy. Brain 139:1713–1722
Bandarabadi M, Rasekhi J, Teixeira CA, Karami MR, Dourado A (2015) On the proper selection of preictal period for seizure prediction. Epilepsy Behav 158–166:46
Giannakakis G, Sakkalis V, Pediaditis M, Tsiknakis M (2014) Methods for seizure detection and prediction: An overview. Mod Electroencephalographic Assem Tech 91:131–157
Georgis-Yap Z, Popovic MR, Khan SS (2022) Preictal-interictal classification for seizure prediction. In: The 35th Canadian conference on artificial intelligence
Burrello A, Cavigelli L, Schindler K, Benini L, Rahimi A (2019) Laelaps: An energy-efficient seizure detection algorithm from long-term human ieeg recordings without false alarms. In: 2019 Design, automation & test in Europe conference & exhibition (DATE). Florence, Italy
Shoeb AH (2009) Application of machine learning to epileptic seizure onset detection and treatment. PhD thesis, Massachusetts Institute of Technology
Acharya UR, Hagiwara Y, Adeli H (2018) Automated seizure prediction. Epilepsy Behav 88:251–261
Natu M, Bachute M, Gite S, Kotecha K, Vidyarthi A (2022) Review on epileptic seizure prediction: machine learning and deep learning approaches. Comput Math Methods Med 2022
LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444
Teixeira CA, Direito B, Bandarabadi M, Le Van Quyen M, Valerrama M, Schelter B, Schulze-Bonhage A, Navarro V, Sales F, Dourado A (2014) Epileptic seizure predictors based on computational intelligence techniques: A comparative study with 278 patients. Comput Methods Prog Biomed 114:324–336
Fei K, Wang W, Yang Q, Tang S (2017) Chaos feature study in fractional fourier domain for preictal prediction of epileptic seizure. Neurocomputing 249:290–298
Mirowski P, Madhavan D, LeCun Y, Kuzniecky R (2009) Classification of patterns of eeg synchronization for seizure prediction. Clin Neurophysiol 120:1927–1940
Khan H, Marcuse L, Fields M, Swann K, Yener B (2018) Focal onset seizure prediction using convolutional networks. IEEE Trans Biomed Eng 65:2109–2118
Truong ND, Nguyen AD, Kuhlmann L, Bonyadi MR, Yang J, Ippolito S, Kavehei O (2018) Convolutional neural networks for seizure prediction using intracranial and scalp electroencephalogram. Neural Netw 105:104–111
Eberlein M, Hildebrand R, Tetzlaff R, Hoffmann N, Kuhlmann L, Brinkmann B, M”uller J (2018) Convolutional neural networks for epileptic seizure prediction. In: 2018 IEEE International conference on bioinformatics and biomedicine (BIBM), Madrid
Zhang Y, Guo Y, Yang P, Chen W, Lo B (2020) Epilepsy seizure prediction on eeg using common spatial pattern and convolutional neural network. IEEE J Biomed Health Informat 24:465–474
Liu Y, Sivathamboo S, Goodin P, Bonnington P, Kwan P, Kuhlmann L, O’Brien T, Perucca P, Ge Z (2020) Epileptic seizure detection using convolutional neural network: A multi-biosignal study. In: ACSW ’20: Proceedings of the Australasian computer science week multiconference, Melbourne, Australia
Dissanayake T, Fernando T, Denman S, Sridharan S, Fookes C (2021) Deep learning for patient-independent epileptic seizure prediction using scalp eeg signals. IEEE Sensors J 21:9377–9388
Jana R, Mukherjee I (2021) Deep learning based efficient epileptic seizure prediction with eeg channel optimization. Biomed Signal Process Control 68
Xu Y, Yang J, Zhao S, Wu H, Sawan M (2020) An end-to-end deep learning approach for epileptic seizure prediction. In: 2020 2nd IEEE International conference on artificial intelligence circuits and systems (AICAS), Italy
Tsiouris KM, Pezoulas VC, Zervakis M, Konitsiotis S, Koutsouris DD, Fotiadis DI (2018) A long short-term memory deep learning network for the prediction of epileptic seizures using eeg signals. Comput Biol Med 99:24–37
Abdelhameed AM, Bayoumi M (2018) Semi-supervised deep learning system for epileptic seizures onset prediction. In: 2018 17th IEEE International conference on machine learning and applications (ICMLA), Orlando
Daoud H, Bayoumi MA (2019) Efficient epileptic seizure prediction based on deep learning. IEEE Trans Biomed Circ Syst 13:804–813
Wei X, Zhou L, Zhang Z, Chen Z, Zhou Y (2019) Early prediction of epileptic seizures using a long-term recurrent convolutional network. J Neurosci Methods 327
Usman SM, Khalid S, Aslam MH (2020) Epileptic seizures prediction using deep learning techniques. IEEE Access 8:39998–40007
Hussein A, Djandji M, Mahmoud R, Dhaybi M, Hajj HM (2020) Augmenting dl with adversarial training for robust prediction of epilepsy seizures. J ACM 1
Prathaban BP, Balasubramanian R (2021) Dynamic learning framework for epileptic seizure prediction using sparsity based eeg reconstruction with optimized cnn classifier. Expert Syst Appl 170
Ozcan AR, Erturk S (2019) Seizure prediction in scalp eeg using 3d convolutional neural networks with an image-based approach. IEEE Trans Neural Syst Rehab Eng 27:2284–2293
Truong ND, Zhou L, Kavehei O (2019) Semi-supervised seizure prediction with generative adversarial networks. In: 2019 41st Annual international conference of the ieee engineering in medicine and biology society (EMBC), Berlin
Sherstinsky A (2020) Fundamentals of recurrent neural network (rnn) and long short-term memory (lstm) network. Physic D Nonlinear Phenom 404:132306
Thill M, Konen W, Wang H, B”ack T, (2021) Temporal convolutional autoencoder for unsupervised anomaly detection in time series. Appl Soft Comput 112:107751
Stefan Denkovski SSK, Mihailidis A (2023) Temporal shift - multi-objective loss function for improved anomaly fall detection. In: \(15^{th}\) Asian conference on machine learning
Khan SS, Khoshbakhtian F, Ashraf AB (2021) Anomaly detection approach to identify early cases in a pandemic using chest x-rays. In: Canadian conference on AI
Jacob Nogas SSK, Mihailidis A (2018) Fall detection from thermal camera using convolutional lstm autoencoder. In: Proceedings of the 2nd workshop on aging, rehabilitation and independent assisted living, IJCAI workshop
Abedi A, Khan SS (2023) Detecting disengagement in virtual learning as an anomaly using temporal convolutional network autoencoder. SIViP
Al-Fahoum AS, Al-Fraihat AA (2014) Methods of eeg signal features extraction using linear analysis in frequency and time-frequency domains. Int Scholar Res Not 2014
Herrmann CS, Rach S, Vosskuhl J, Str’’uber D (2014) Time–frequency analysis of event-related potentials: A brief tutorial. Brain Topogr 27:438–450
Herrmann CS, Rach S, Vosskuhl J, Str’’uber D (2014) Time–frequency analysis of event-related potentials: A brief tutorial. Brain Topogr 27:438–450
Fadzal CWNFCW, Mansor W, Khuan LY, Zabidi A (2012) Short-time fourier transform analysis of eeg signal from writing. In: 2012 IEEE 8th International colloquium on signal processing and its applications. Malacca, Malaysia
Edakawa K, Yanagisawa T, Kishima H, Fukuma R, Oshino S, Khoo HM, Kobayashi M, Tanaka M, Yoshimine T (2016) Detection of epileptic seizures using phase–amplitude coupling in intracranial electroencephalography. Sci Rep 6(1):1–8
Huang J, Ling CX (2005) Using auc and accuracy in evaluating learning algorithms. IEEE Trans Knowl Data Eng 17:299–310
Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, Killeen T, Lin Z, Gimelshein N, Antiga L, Desmaison A, Kopf A, Yang E, DeVito Z, Raison M, Tajani A, Chilamkurthy S, Steiner B, Fang L, Bai J, Chintala S (2019) Pytorch: An imperative style, high-performance deep learning library. In: Advances in neural information processing systems 32, Vancouver
Branco P, Torgo L, Ribeiro RR (2016) A survey of predictive modeling on imbalanced domains. ACM Comput Surv (CSUR) 49:1–50
Khan SS, Karg ME, Kulić D, Hoey J (2017) Detecting falls with x-factor hidden markov models. Appl Soft Comput 55:168–177
Khan SS, Mishra PK, Ye B, Newman K, Iaboni A, Mihailidis A (2023) Empirical thresholding on spatio-temporal autoencoders trained on surveillance videos in a dementia care unit. In: 2023 20th Conference on robots and vision (CRV), pp 265–272. IEEE
Habashi AG, Azab AM, Eldawlatly S, Aly GM (2023) Generative adversarial networks in eeg analysis: an overview. J NeuroEng Rehab 20(1):40
Khan SS, Nogas J, Mihailidis A (2021) Spatio-temporal adversarial learning for detecting unseen falls. Pattern Anal Applic 24:381–391
Funding
This work is supported by the Natural Sciences and Engineering Research Council of Canada and Data Science Institute, University of Toronto.
Author information
Authors and Affiliations
Contributions
Zakary Georgis-Yap and Shehroz S. Khan contributed equally in terms of developing algorithms, evaluation of results and manuscript preparation. Shehroz S. Khan prepared subsequent revisions of the paper. Milos R. Popovic provided academic support and consultation throughout the study.
Corresponding author
Ethics declarations
Ethics Approval
Two publicly available datasets were used in this work; therefore, ethics approvals were not required to use them.
Informed Consent
All the co-authors give their consent to publish this paper.
Conflict of Interest
The authors declare no competing interests.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Georgis-Yap, Z., Popovic, M.R. & Khan, S.S. Supervised and Unsupervised Deep Learning Approaches for EEG Seizure Prediction. J Healthc Inform Res 8, 286–312 (2024). https://doi.org/10.1007/s41666-024-00160-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s41666-024-00160-x