Skip to main content
SpringerLink
Log in

Deep learning-based multi-head self-attention model for human epilepsy identification from EEG signal for biomedical traits

  • 1238: Recent Advances in Biometrics Based on Biomedical Information
  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

The neurological condition epilepsy is demanding and even fatal. Electroencephalogram (EEG)-based epilepsy detection still faces various difficulties. EEG readings fluctuate, and different patients have various seizure activity patterns. EEG signal detection is time-consuming and labour-intensive, which puts a strain on medical staff and raises the possibility of erroneous detections. Usually, electrodes are inserted into the scalp or inside the brain for a brief period of time in order to obtain EEG data. It is essential to research efficient cross-patient automatic epilepsy detection techniques. The multi-head self-attention mechanism recognises long-distance dependencies with the same proficiency as it does temporal dynamic correlations between short-term temporal pattern characteristics and sequential relationships. The contextual representations are inputted into a bidirectional long short-term memory network (BiLSTM) so that information can be extracted in both directions. Classification and training are carried out utilising the log SoftMax algorithm. The experiments utilised scalp EEG data from the CHB-MIT database. Sensitivity, specificity, F1-score, and accuracy were computed to be 96.5 percent, 97.04 percent, 96.6 percent, and 96.2 percent, respectively. The results of the experiment show how well the technique works for detecting seizures in several patients utilising multi-channel EEG recordings. The results also demonstrate the method's improved generalisation capabilities and resilience and consistency in collecting seizure patterns. This is particularly critical for the tertiary diagnosis of epilepsy, and the findings indicate that the proposed method significantly improves the accuracy of detection.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

Data availability

The data associated with this research shall be available on request.

References

  1. Supriya S, Siuly S, Wang H, Zhang Y (2023) Epilepsy detection from EEG using complex network techniques: a review. IEEE Rev Biomed Eng 16:292–306. https://doi.org/10.1109/RBME.2021.3055956

    Article  Google Scholar 

  2. Li J, Haldar JP, Mosher JC, Nair DR, Gonzalez-Martinez JA, Leahy RM (2019) Scalable and robust tensor decomposition of spontaneous stereotactic EEG data. IEEE Trans Biomed Eng 66(6):1549–1558. https://doi.org/10.1109/TBME.2018.2875467

    Article  Google Scholar 

  3. Busonera G et al (2018) EEG spectral coherence analysis in nocturnal epilepsy. IEEE Trans Biomed Eng 65(12):2713–2719. https://doi.org/10.1109/TBME.2018.2814479

    Article  Google Scholar 

  4. Xie L, Deng Z, Xu P, Choi K-S, Wang S (2019) Generalized hidden-mapping transductive transfer learning for recognition of epileptic electroencephalogram signals. IEEE Trans Cybern 49(6):2200–2214. https://doi.org/10.1109/TCYB.2018.2821764

    Article  Google Scholar 

  5. Sheykhivand S, Rezaii TY, Mousavi Z, Delpak A, Farzamnia A (2020) Automatic identification of epileptic seizures from EEG signals using sparse representation-based classification. IEEE Access 8:138834–138845. https://doi.org/10.1109/ACCESS.2020.3011877

    Article  Google Scholar 

  6. Fraiwan L, Alkhodari M (2020) Classification of focal and non-focal epileptic patients using single channel EEG and long short-term memory learning system. IEEE Access 8:77255–77262. https://doi.org/10.1109/ACCESS.2020.2989442

    Article  Google Scholar 

  7. Tian X et al (2019) Deep multi-view feature learning for eeg-based epileptic seizure detection. IEEE Trans Neural Syst Rehabil Eng 27(10):1962–1972. https://doi.org/10.1109/TNSRE.2019.2940485

    Article  Google Scholar 

  8. Rashed-Al-Mahfuz M, Moni MA, Uddin S, Alyami SA, Summers MA, Eapen V (2021) A deep convolutional neural network method to detect seizures and characteristic frequencies using Epileptic Electroencephalogram (EEG) data. In IEEE J Transl Eng Health Med 9(1–12):2000112. https://doi.org/10.1109/JTEHM.2021.3050925

    Article  Google Scholar 

  9. Shukla U, Saxena GJ, Kumar M, Bafila AS, Pundir A, Singh S (2021) An improved decision support system for identification of abnormal EEG signals using a 1D convolutional neural network and savitzky-golay filtering. IEEE Access 9:163492–163503. https://doi.org/10.1109/ACCESS.2021.3133326

    Article  Google Scholar 

  10. Yang Y, Truong ND, Eshraghian JK, Maher C, Nikpour A, Kavehei O (2022) A multimodal ai system for out-of-distribution generalization of seizure identification. IEEE J Biomed Health Inform 26(7):3529–3538. https://doi.org/10.1109/JBHI.2022.3157877

    Article  Google Scholar 

  11. Khosla A, Khandnor P, Chand T (2022) Automated diagnosis of depression from EEG signals using traditional and deep learning approaches: a comparative analysis. Biocybernetics Biomed Eng 42(1):108–142. https://doi.org/10.1016/j.bbe.2021.12.005

    Article  Google Scholar 

  12. Asadzadeh S, YousefiRezaii T, Beheshti S, Delpak A, Meshgini S (2020) A systematic review of EEG source localization techniques and their applications on diagnosis of brain abnormalities. J Neurosci Methods 339:108740. https://doi.org/10.1016/j.jneumeth.2020.108740

    Article  Google Scholar 

  13. Kora P, Meenakshi K, Swaraja K, Rajani A, Raju MS (2021) EEG based interpretation of human brain activity during yoga and meditation using machine learning: a systematic review. Complement Ther Clin Pract 43:101329. https://doi.org/10.1016/j.ctcp.2021.101329

    Article  Google Scholar 

  14. Babiloni C, Arakaki X, Bonanni L, Bujan A, Carrillo MC, Del Percio C, Edelmayer RM, Egan G, Elahh FM, Evans A, Ferri R, Frisoni GB, Güntekin B, Hainsworth A, Hampel H, Jelic V, Jeong J, Kim DK, Kramberger M, ... Yener G (2021) EEG measures for clinical research in major vascular cognitive impairment: Recommendations by an expert panel. Neurobiol Aging 103:78–97. https://doi.org/10.1016/j.neurobiolaging.2021.03.003

  15. Babiloni C, Barry RJ, Başar E, Blinowska KJ, Cichocki A, Drinkenburg WH, Klimesch W, Knight RT, Lopes da Silva F, Nunez P, Oostenveld R, Jeong J, Pascual-Marqui R, Valdes-Sosa P, Hallett M (2020) International Federation of Clinical Neurophysiology (IFCN) – EEG research workgroup: recommendations on frequency and topographic analysis of resting state EEG rhythms. Part 1: applications in clinical research studies. Clin Neurophysiol 131(1):285–307. https://doi.org/10.1016/j.clinph.2019.06.234

    Article  Google Scholar 

  16. Tremblay S, Rogasch NC, Premoli I, Blumberger DM, Casarotto S, Chen R, Di Lazzaro V, Farzan F, Ferrarelli F, Fitzgerald PB, Hui J, Ilmoniemi RJ, Kimiskidis VK, Kugiumtzis D, Lioumis P, Pascual-Leone A, Pellicciari MC, Rajji T, Thut G, ... Daskalakis ZJ (2019) Clinical utility and prospective of TMS–EEG. Clin Neurophysiol 130(5):802–844. https://doi.org/10.1016/j.clinph.2019.01.001

  17. Mazzotti DR (2021) Landscape of biomedical informatics standards and terminologies for clinical sleep medicine research: a systematic review. Sleep Med Rev 60:101529. https://doi.org/10.1016/j.smrv.2021.101529

    Article  Google Scholar 

  18. Sunil Kumar K, Arjun Kumar G, Gatti R, Santosh Kumar S, Bhyratae DA, Palle S (2023) Design and implementation of auto encoder based bio medical signal transmission to optimize power using convolution neural network. Neurosci Inform 3(1):100121. https://doi.org/10.1016/j.neuri.2023.100121

    Article  Google Scholar 

  19. Shen B, Lin Y, Bi C, Zhou S, Bai Z, Zheng G, Zhou J (2019) Translational informatics for parkinson’s disease: from big biomedical data to small actionable alterations. Genomics Proteome Bioinforma 17(4):415–429. https://doi.org/10.1016/j.gpb.2018.10.007

    Article  Google Scholar 

  20. Alhusaini S, Whelan CD, Sisodiya SM, Thompson PM (2016) Quantitative magnetic resonance imaging traits as endophenotypes for genetic mapping in epilepsy. NeuroImage: Clin 12:526–534. https://doi.org/10.1016/j.nicl.2016.09.005

    Article  Google Scholar 

  21. Sridhar C, Bhat S, Acharya UR, Adeli H, Bairy GM (2017) Diagnosis of attention deficit hyperactivity disorder using imaging and signal processing techniques. Comput Biol Med 88:93–99. https://doi.org/10.1016/j.compbiomed.2017.07.009

    Article  Google Scholar 

  22. Mushtaq F, Raza ZA, Batool SR, Zahid M, Onder OC, Rafique A, Nazeer MA (2022) Preparation, properties, and applications of gelatin-based hydrogels (GHs) in the environmental, technological, and biomedical sectors. Int J Biol Macromol 218:601–633. https://doi.org/10.1016/j.ijbiomac.2022.07.168

    Article  Google Scholar 

  23. Gallotto S, Seeck M (2023) EEG biomarker candidates for the identification of epilepsy. Clin Neurophysiol Pract 8:32–41. https://doi.org/10.1016/j.cnp.2022.11.004

    Article  Google Scholar 

  24. Peltola ME, Leitinger M, Halford JJ, Vinayan KP, Kobayashi K, Pressler RM, Mindruta I, Mayor LC, Lauronen L, Beniczky S (2023) Routine and sleep EEG: minimum recording standards of the international federation of clinical neurophysiology and the international league against epilepsy. Clin Neurophysiol 147:108–120. https://doi.org/10.1016/j.clinph.2023.01.002

    Article  Google Scholar 

  25. Lai N, Li Z, Xu C, Wang Y, Chen Z (2023) Diverse nature of interictal oscillations: EEG-based biomarkers in epilepsy. Neurobiol Dis 177:105999. https://doi.org/10.1016/j.nbd.2023.105999

    Article  Google Scholar 

  26. Frauscher B, Bénar C, Engel J, Grova C, Jacobs J, Kahane P, Wiebe S, Zjilmans M, Dubeau F (2023) Neurophysiology, neuropsychology, and epilepsy, in 2022: hills we have climbed and hills ahead. Neurophysiol Epilepsy Epilepsy Behav 143:109221. https://doi.org/10.1016/j.yebeh.2023.109221

    Article  Google Scholar 

  27. Wong ZW, Engel T (2023) More than a drug target: purinergic signalling as a source for diagnostic tools in epilepsy. Neuropharmacology 222:109303. https://doi.org/10.1016/j.neuropharm.2022.109303

    Article  Google Scholar 

  28. Jirsa V, Wang H, Triebkorn P, Hashemi M, Jha J, Gonzalez-Martinez J, Guye M, Makhalova J, Bartolomei F (2023) Personalised virtual brain models in epilepsy. Lancet Neurol 22(5):443–454. https://doi.org/10.1016/S1474-4422(23)00008-X

    Article  Google Scholar 

  29. Norata D, Broggi S, Alvisi L, Lattanzi S, Brigo F, Tinuper P (2023) The EEG pen-on-paper sound: history and recent advances. Seizure 107:67–70. https://doi.org/10.1016/j.seizure.2023.03.011

    Article  Google Scholar 

  30. Jiang J, Yu Y (2023) Pharmacologically targeting transient receptor potential channels for seizures and epilepsy: emerging preclinical evidence of druggability. Pharmacol Ther 244:108384. https://doi.org/10.1016/j.pharmthera.2023.108384

    Article  Google Scholar 

  31. Smith ML, Risse G, Sziklas V, Banks S, Small D, Frasnelli J, Klein D (2023) Neurophysiology, neuropsychology, epilepsy, 2022: hills we have climbed and the hills ahead. Cognition and sensory systems in healthy and diseased subjects. Epilepsy Behav 140:109119. https://doi.org/10.1016/j.yebeh.2023.109119

    Article  Google Scholar 

  32. Li Z, Chen L, Xu C, Chen Z, Wang Y (2023) Non-invasive sensory neuromodulation in epilepsy: updates and future perspectives. Neurobiol Dis 179:106049. https://doi.org/10.1016/j.nbd.2023.106049

    Article  Google Scholar 

  33. Becchetti A, Grandi LC, Cerina M, Amadeo A (2023) Nicotinic acetylcholine receptors and epilepsy. Pharmacol Res 189:106698. https://doi.org/10.1016/j.phrs.2023.106698

    Article  Google Scholar 

Download references

Acknowledgements

The authors would like to acknowledge the support provided by AlMaarefa University while conducting this research.

Funding

There is no funding for this research.

Author information

Authors and Affiliations

  1. Department of Computer Science and Information Systems, College of Applied Sciences, AlMaarefa University, Ad Diriyah, Riyadh, 13713, Kingdom of Saudi Arabia

    Ashit Kumar Dutta

  2. Alphabet Life Science, Dallas, TX, 7506, USA

    Mohan Raparthi

  3. Department of Computer Science, Al-Maarif University College, Al Anbar, 31001, Iraq

    Mahmood Alsaadi

  4. Model Institute of Engineering and Technology, Jammu, J&K, India

    Mohammed Wasim Bhatt

  5. Software Engineer, Central Michigan University, Dallas, TX, 75009, USA

    Sarath Babu Dodda

  6. Department of Computer Science, Texas Tech University, Lubbock, 79409, USA

    Prashant G. C.

  7. Skill Faculty of Engineering & Technology, Shri Vishwakarma Skill University, Palwal, Haryana, India

    Mukta Sandhu

  8. CSE, School of advance Computing, Alliance University, Bengaluru, India

    Jagdish Chandra Patni

Authors
  1. Ashit Kumar Dutta
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mohan Raparthi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mahmood Alsaadi
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Mohammed Wasim Bhatt
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Sarath Babu Dodda
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Prashant G. C.
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Mukta Sandhu
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Jagdish Chandra Patni
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mohammed Wasim Bhatt.

Ethics declarations

Compliance with ethical standards

There is no human or animal participation in this research.

Conflict of interest

The authors do not have any conflict of Interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

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.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Dutta, A.K., Raparthi, M., Alsaadi, M. et al. Deep learning-based multi-head self-attention model for human epilepsy identification from EEG signal for biomedical traits. Multimed Tools Appl (2024). https://doi.org/10.1007/s11042-024-18918-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11042-024-18918-1

Keywords

Search

Navigation