Development of an algorithm for detecting slow peak-wave activity in non-convulsive forms of epilepsy

A. S. Belokopytov ; M. M. Makarova ; M. I. Salamatin ; O. M. Redkozubova

Izvestiya VUZ. Applied Nonlinear Dynamics, Tome 32 (2024) no. 2, pp. 223-238.

Résumé

The purpose of this study is to develop a classifier capable of detecting typical absence seizures in real-time using electroencephalogram (EEG) data and a Support Vector Machine (SVM) model. Methods. Sections of the EEG, previously identified by a specialist as containing typical absences, were used to train the SVM model. Key features for classification include the number of zero crossings, cross-correlation between two consecutive windows, spectral power across various frequency bands, and the standard deviation of instantaneous signal power. Results. Training and testing datasets were established, consisting of EEG windows with various types of artifacts. The SVM model was successfully trained and tested, achieving high performance metrics. The developed algorithm can be integrated into a mobile application and used in conjunction with a wearable EEG device with dry electrodes for real-time detection of typical absences. Conclusion. The study results affirm the potential for using machine learning techniques for the automatic detection and logging of epileptic activity. However, additional testing on a larger dataset is needed for more conclusive results, including data acquired through a wireless EEG device using dry electrodes. Future work will involve selecting a suitable EEG device and developing a mobile application for real-time data collection and analysis.

Détail

Keywords: absence epilepsy, Support vector machine, dynamic classifier, electroencephalography, real-time detection, machine learning

Bibliographie

[1] Reichsoellner J., Larch J., Unterberger I., Dobesberger J., Kuchukhidze G., Luef G., Bauer G., Trinka E., “Idiopathic generalised epilepsy of late onset: a separate nosological entity?”, J. Neurol. Neurosurg. Psychiatry, 81:11 (2010), 1218–1222 | DOI

[2] Epilepsiya i epilepticheskii status u vzroslykh i detei. Klinicheskie rekomendatsii, Ministerstvo zdravookhraneniya Rossiiskoi Federatsii, 2022, 291 pp.

[3] Cortez M. A., Snead III O. C., “Pharmacologic models of generalized absence seizures in rodents”, Models of Seizures and Epilepsy, eds. Pitkänen A., Schwartzkroin P. A., Moshé S. L., Academic Press, Burlington, 2006, 111–126 | DOI

[4] Destexhe A., “Network models of absence seizures”, Neuronal Networks in Brain Function, CNS Disorders, and Therapeutics, eds. Faingold C. L., Blumenfeld H., Academic Press, San Diego, 2014, 11–35 | DOI

[5] Elger C. E., Hoppe C., “Diagnostic challenges in epilepsy: seizure under-reporting and seizure detection”, Lancet Neurology, 17:3 (2018), 279–288 | DOI

[6] Bruno E., Viana P. F., Sperling M. R., Richardson M. P., “Seizure detection at home: Do devices on the market match the needs of people living with epilepsy and their caregivers?”, Epilepsia, 61:S1 (2020), S11–S24 | DOI

[7] Elmali A. D., Begley K., Chester H., Cooper J., Moreira C., Sharma S., Whelan A., Leschziner G., Richardson M. P., Stern W., Koutroumanidis M., “Evaluation of absences and myoclonic seizures in adults with genetic (idiopathic) generalized epilepsy: a comparison between self-evaluation and objective evaluation based on home video-EEG telemetry”, Epileptic Disorders, 23:5 (2021), 719–732 | DOI

[8] Tatum 4th W. O., Winters L., Gieron M., Passaro E. A., Benbadis S., Ferreira J., Liporace J., “Outpatient seizure identification: results of 502 patients using computer-assisted ambulatory EEG”, Journal of Clinical Neurophysiology, 18:1 (2001), 14–19 | DOI

[9] Beniczky S., Wiebe S., Jeppesen J., Tatum W. O., Brazdil M., Wang Y., Herman S. T., Ryvlin P., “Automated seizure detection using wearable devices: A clinical practice guideline of the International League Against Epilepsy and the International Federation of Clinical Neurophysiology”, Clinical Neurophysiology, 132:5 (2021), 1173–1184 | DOI

[10] Wirrell E. C., Camfield C. S., Camfield P. R., Dooley J. M., Gordon K. E., Smith B., “Long-term psychosocial outcome in typical absence epilepsy. Sometimes a wolf in sheeps' clothing”, Arch. Pediatr. Adolesc. Med, 151:2 (1997), 152–158 | DOI

[11] Wirrell E. C., Camfield P. R., Camfield C. S., Dooley J. M., Gordon K. E., “Accidental injury is a serious risk in children with typical absence epilepsy”, Arch. Neurol, 53:9 (1996), 929–932 | DOI

[12] Vega C., Guo J., Killory B., Danielson N., Vestal M., Berman R., Martin L., Gonzalez J. L., Blumenfeld H., Spann M. N., “Symptoms of anxiety and depression in childhood absence epilepsy”, Epilepsia, 52:8 (2011), e70–e74 | DOI

[13] Killory B. D., Bai X., Negishi M., Vega C., Spann M. N., Vestal M., Guo J., Berman R., Danielson N., Trejo G., Shisler D., Novotny Jr. E. J., Constable R. T., Blumenfeld H., “Impaired attention and network connectivity in childhood absence epilepsy”, NeuroImage, 56:4 (2011), 2209–2217 | DOI

[14] Fiest K. M., Birbeck G. L., Jacoby A., Jette N., “Stigma in epilepsy”, Current Neurology and Neuroscience Reports, 14:5 (2014), 444 | DOI

[15] Kjaer T. W., Sorensen H. B. D., Groenborg S., Pedersen C. R., Duun-Henriksen J., “Detection of paroxysms in long-term, single-channel EEG-monitoring of patients with typical absence seizures”, IEEE Journal of Translational Engineering in Health and Medicine, 5 (2017), 2000108 | DOI

[16] Tovar Quiroga D. F., Britton J. W., Wirrell E. C., “Patient and caregiver view on seizure detection devices: A survey study”, Seizure, 41 (2016), 179–181 | DOI

[17] Ovchinnikov A., Lüttjohann A., Hramov A., van Luijtelaar G., “An algorithm for real-time detection of spike-wave discharges in rodents”, Journal of Neuroscience Methods, 194:1 (2010), 172–178 | DOI

[18] Sitnikova E., Hramov A. E., Koronovsky A. A., van Luijtelaar G., “Sleep spindles and spike–wave discharges in EEG: Their generic features, similarities and distinctions disclosed with Fourier transform and continuous wavelet analysis”, Journal of Neuroscience Methods, 180:2 (2009), 304–316 | DOI

[19] Nazimov A. I., Pavlov A. N., Khramov A. E., Grubov V. V., Sitnikova E. Yu., Khramova M. V., “Raspoznavanie ostsillyatornykh patternov na elektroentsefalogramme na osnove adaptivnogo veivlet-analiza”, Vestnik Tambovskogo universiteta. Seriya: Estestvennye i tekhnicheskie nauki, 18:4 (2013), 1431–1434

[20] Grubov V. V., Koronovskii A. A., Sitnikova E. Yu., Khramov A. E., “Chastotno-vremennoi analiz kharakternykh patternov aktivnosti neironnykh ansamblei golovnogo mozga pri pomoschi nepreryvnogo veivletnogo preobrazovaniya”, Izvestiya Rossiiskoi akademii nauk. Seriya fizicheskaya, 78:12 (2014), 1525–1529 | DOI

[21] Sitnikova E. Yu., Smirnova K. S., Grubov V. V., Khramov A. E., “Printsipy diagnostiki nezreloi epilepticheskoi (proepilepticheskoi) aktivnosti na EEG u krys s geneticheskoi predraspolozhennostyu k absans-epilepsii”, Informatsionno-upravlyayuschie sistemy, 2019, no. 1, 89–97 | DOI

[22] van Luijtelaar G., Lüttjohann A., Makarov V. V., Maksimenko V. A., Koronovskii A. A., Hramov A. E., “Methods of automated absence seizure detection, interference by stimulation, and possibilities for prediction in genetic absence models”, Journal of Neuroscience Methods, 260 (2016), 144–158 | DOI

[23] Grubov V. V., Sitnikova E. Yu., Kurovskaya M. K., Koronovskii A. A., Khramov A. E., “Perspektivy ispolzovaniya metoda empiricheskikh mod i veivletnogo analiza dlya vyyavleniya proepilepticheskoi aktivnosti na signalakh elektroentsefalogramm”, Uchenye zapiski fizicheskogo fakulteta Moskovskogo universiteta, 2016, no. 5, 165404

[24] Jandó G., Siegel R. M., Horváth Z., Buzsáki G., “Pattern recognition of the electroencephalogram by artificial neural networks”, Electroencephalography and Clinical Neurophysiology, 86:2 (1993), 100–109 | DOI

[25] Buteneers P., Schrauwen B., Verstraeten D., Stroobandt D., “Real-time epileptic seizure detection on intra-cranial rat data using reservoir computing”, Advances in Neuro-Information Processing, ICONIP 2008, v. 5506, Lecture Notes in Computer Science, eds. Köppen M., Kasabov N., Coghill G., Springer, Berlin, Heidelberg, 2009, 56–63 | DOI

[26] Xanthopoulos P., Rebennack S., Liu C.-C., Zhang J., Holmes G. L., Uthman B. M., Pardalos P. M., “A novel wavelet based algorithm for spike and wave detection in absence epilepsy”, 2010 IEEE International Conference on BioInformatics and BioEngineering (31 May 2010 - 3 June 2010, Philadelphia, PA, USA), IEEE, New York, 2010, 14–19 | DOI

[27] Startceva S. A., Lüettjohann A., Sysoev I. V., van Luijtelaar G., “A new method for automatic marking epileptic spike-wave discharges in local field potential signals”, Proc. SPIE, Saratov Fall Meeting 2014: Optical Technologies in Biophysics and Medicine XVI; Laser Physics and Photonics XVI; and Computational Biophysics, 2015, 94481R | DOI

[28] Baser O., Yavuz M., Ugurlu K., Onat F., Demirel B. U., “Automatic detection of the spike-and-wave discharges in absence epilepsy for humans and rats using deep learning”, Biomedical Signal Processing and Control, 76 (2022), 103726 | DOI

[29] Guo L., Rivero D., Dorado J., Rabuñal J. R., Pazos A., “Automatic epileptic seizure detection in EEGs based on line length feature and artificial neural networks”, Journal of Neuroscience Methods, 191:1 (2010), 101–109 | DOI | MR

[30] Dan J., Vandendriessche B., Van Paesschen W., Weckhuysen D., Bertrand A., “Computationally-efficient algorithm for real-time absence seizure detection in wearable electroencephalography”, International Journal of Neural Systems, 30:11 (2020), 2050035 | DOI

[31] Glukhova L. Yu., “Klinicheskoe znachenie epileptiformnoi aktivnosti na elektroentsefalogramme”, Rossiiskii zhurnal detskoi nevrologii, 11:4 (2016), 8–19 | DOI

[32] Volnova A. B., Lenkov D. N., “Absansnaya epilepsiya: mekhanizmy gipersinkhronizatsii neironnykh ansamblei”, Meditsinskii fkademicheskii zhurnal, 12:1 (2012), 7–19

[33] Karlov V. A., “Absans”, Zhurnal nevrologii i psikhiatrii im. S. S. Korsakova, 3 (2005), 55-60

[34] Petersen E. B., Duun-Henriksen J., Mazzaretto A., Kjær T. W., Thomsen C. E., Sorensen H. B. D., “Generic single-channel detection of absence seizures”, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (30 August 2011 - 3 September 2011, Boston, MA, USA), IEEE, New York, 2011, 4820–4823 | DOI

[35] Chatzichristos C., Swinnen L., Macea J., Bhagubai M., Van Paesschen W., De Vos M., “Multimodal detection of typical absence seizures in home environment with wearable electrodes”, Frontiers in Signal Processing, 2 (2022), 1014700 | DOI

[36] Japaridze G., Loeckx D., Buckinx T., Larsen S. A., Proost R., Jansen K., MacMullin P., Paiva N., Kasradze S., Rotenberg A., Lagae L., Beniczky S., “Automated detection of absence seizures using a wearable electroencephalographic device: a phase 3 validation study and feasibility of automated behavioral testing”, Epilepsia, 2022 | DOI

[37] Makarov V. V., Metody i algoritmy avtomaticheskoi klassifikatsii psikhofiziologicheskikh kharakteristik cheloveka:, diss. ... kand. tekhn. nauk: 05.13.17, Federalnyi issledovatelskii tsentr «Informatika i upravlenie» Rossiiskoi akademii nauk, M., 2022, 104 pp.

[38] Sitnikova E. Yu., Koronovskii A. A., Khramov A. E., “Analiz elektricheskoi aktivnosti golovnogo mozga pri absans-epilepsii: prikladnye aspekty nelineinoi dinamiki”, Izvestiya vuzov. PND, 19:6 (2011), 173–182 | DOI | Zbl

[39] Beniczky S., Rubboli G., Covanis A., Sperling M. R., “Absence-to-bilateral-tonic-clonic seizure”, Neurology, 95:14 (2020), e2009–e2015 | DOI

[40] Shoeb A., CHB-MIT Scalp EEG Database, PhysioNet, 2010 https://physionet.org/content/chbmit/1.0.0/

[41] NeuroPlay - NeuroPlay-6C, https://neuroplay.ru/catalog/neuroplay-6c/