This article focuses on the development of a system to help epileptologists use an automated search for epileptic seizures in electroencephalographic records. Purpose: Development of software that implements the analysis of EEG signals for the subsequent detection of epileptic seizures Materials and methods: EEG data from 10 patients with symptomatic epilepsy, which are characterized by recurrent, stereotyped seizures after exposure to a provoking factor were used in the study. The data was recorded by 25 EEG channels with additional channels for recording cardioactivity and service markers. The sampling rate of EEG signals was 128 Hz. To obtain the required characteristics, the recording processing was based on the wavelet transform. Results: The software was developed, the result of which is a discrete marking, which shows in which minute fragments of the EEG the appearance of epileptic seizures is possible. Findings: Further directions of software modification to improve its efficiency and usability have been formulated.
References
1. Gusev EI, Konovalov AN, Skvortsova VI. Neurology and neurosurgery. A.V. Kozlova , A.N. Konovalova , editors. M: GEOTAR-Media, 2 009. 624 p. (In Russ ).
2. Sidorenko KV, Darenskaya EYu. The prevalence of epilepsy in the world [Electronic resource]. 2014; 6: 128-130. Available at: http://natural-sciences.ru/ru/article/view?id=33829. Last accessed on : Oct 04 , 2021. (In Russ).
3. Mozhaev SV, Skoromets AA, Skoromets TA. Neurosurgery. SPb.: Polytechnic, 2001. 355 p. (In Russ).
4. Kolyagin VV. Epilepsy. Irkutsk: RIO GBOU DPO IGM APO, 2013. 232 p. (In Russ).
5. Kraik A, He U, Conteras -Vidal J. Deep Learning for EEG Classification Problems. Journal of Neural Engineering. 2019; 16: 1-38.
6. Gotman J. Automatic detection of seizures and spikes. Journal of Clinical Neurophysiology. 1999; 16: 130-140.
7. Shoebi A, Gassemi N, Alizadehsani R, Rouhani M, Hosseini- Nejad H, Khosravi A, et al. Comprehensive comparison of created functions and convolutional autoencoders for detecting epileptic seizures from EEG signals. Expert systems. 2021; 18: 1-32.
8. Wei Z, Wenbing Z, Wenfeng V, Xiaolu J, Xiaodong Z, Yonghong P, Baokan Z, Guokai Z. New neural network for detecting seizures on EEG signals. Computational and mathematical methods in medicine. 2020; 2020: 1-9 p.
9. Hejlsberg A, Torgersen M, Viltamut S, Gold P, The C # Programming Language. Classics of Computers Science. SPb.: Peter, 2012.784 p. (In Russ).
10. Yakovlev AN. Introduction to wavelet transformations. Novosibirsk: Publishing house of NSTU, 2003.104 p. (In Russ).
11. Koronovskii AA, Hramov AE. Continuous wavelet analysis and applications. Moscow: Fizmatli t , 2003. 176 p. (In Russ ).
12. Sitnikova EYu , Khramov AE, Grubov VV, Koronovskiy AA. Time-frequency characteristics and dynamics of dreams in WAG / Rij rats with absence epilepsy. Brain Research. 2014; 1543: 290-299.
13. Vyugin VV. Mathematical foundations of the theory of machine learning and forecasting. M.: MTSNMO, 2013. 390 p. (In Russ).
14. Belousov YuB , Belousov DYu , Chikina ES, Grigoriev VYu , Mednikov OI, Beketov AS. Research of medical and social problems of epilepsy in Russia. Special is sue. 2004; 4: 2-90. (In Russ).
15. Sadlair LG, Sheffer IE, Smith S, Carstensen B, Farrell K, Connolly MB. Features of absence EEG in idiopathic generalized epilepsy: the effect of syndrome, age and condition. Epilepsy. 2009; 50(6): 1572-1578.
16. Gutnikov VS. Filtration of measuring signals. L.: Energoatom izdat., 1990. 192 p. ( In Russ ).
17. Gulyaev SA, Archipenko IV. Artifacts in electroencephalographic examination: identification and differential diagnosis. Russian Journal of Child Neurology. 2012; 7: 3-16. ( In Russ ).
18. Zvezdochkina NV. Study of the electrical activity of the brain. Kazan: Kazan University, 2014. 59 p. ( In Russ ).
2. Sidorenko KV, Darenskaya EYu. The prevalence of epilepsy in the world [Electronic resource]. 2014; 6: 128-130. Available at: http://natural-sciences.ru/ru/article/view?id=33829. Last accessed on : Oct 04 , 2021. (In Russ).
3. Mozhaev SV, Skoromets AA, Skoromets TA. Neurosurgery. SPb.: Polytechnic, 2001. 355 p. (In Russ).
4. Kolyagin VV. Epilepsy. Irkutsk: RIO GBOU DPO IGM APO, 2013. 232 p. (In Russ).
5. Kraik A, He U, Conteras -Vidal J. Deep Learning for EEG Classification Problems. Journal of Neural Engineering. 2019; 16: 1-38.
6. Gotman J. Automatic detection of seizures and spikes. Journal of Clinical Neurophysiology. 1999; 16: 130-140.
7. Shoebi A, Gassemi N, Alizadehsani R, Rouhani M, Hosseini- Nejad H, Khosravi A, et al. Comprehensive comparison of created functions and convolutional autoencoders for detecting epileptic seizures from EEG signals. Expert systems. 2021; 18: 1-32.
8. Wei Z, Wenbing Z, Wenfeng V, Xiaolu J, Xiaodong Z, Yonghong P, Baokan Z, Guokai Z. New neural network for detecting seizures on EEG signals. Computational and mathematical methods in medicine. 2020; 2020: 1-9 p.
9. Hejlsberg A, Torgersen M, Viltamut S, Gold P, The C # Programming Language. Classics of Computers Science. SPb.: Peter, 2012.784 p. (In Russ).
10. Yakovlev AN. Introduction to wavelet transformations. Novosibirsk: Publishing house of NSTU, 2003.104 p. (In Russ).
11. Koronovskii AA, Hramov AE. Continuous wavelet analysis and applications. Moscow: Fizmatli t , 2003. 176 p. (In Russ ).
12. Sitnikova EYu , Khramov AE, Grubov VV, Koronovskiy AA. Time-frequency characteristics and dynamics of dreams in WAG / Rij rats with absence epilepsy. Brain Research. 2014; 1543: 290-299.
13. Vyugin VV. Mathematical foundations of the theory of machine learning and forecasting. M.: MTSNMO, 2013. 390 p. (In Russ).
14. Belousov YuB , Belousov DYu , Chikina ES, Grigoriev VYu , Mednikov OI, Beketov AS. Research of medical and social problems of epilepsy in Russia. Special is sue. 2004; 4: 2-90. (In Russ).
15. Sadlair LG, Sheffer IE, Smith S, Carstensen B, Farrell K, Connolly MB. Features of absence EEG in idiopathic generalized epilepsy: the effect of syndrome, age and condition. Epilepsy. 2009; 50(6): 1572-1578.
16. Gutnikov VS. Filtration of measuring signals. L.: Energoatom izdat., 1990. 192 p. ( In Russ ).
17. Gulyaev SA, Archipenko IV. Artifacts in electroencephalographic examination: identification and differential diagnosis. Russian Journal of Child Neurology. 2012; 7: 3-16. ( In Russ ).
18. Zvezdochkina NV. Study of the electrical activity of the brain. Kazan: Kazan University, 2014. 59 p. ( In Russ ).
For citation
Kuchin A.S., Grubov V.V., Maximenko V.A., Utyashev N.P. Software implementation of the algorithm for searching for epilepsy seizures. Medical doctor and information technology. 2021; 3: 62-73. (In Russ.). doi : 1025881/18110193_2021_3_62.
Keywords