Bispectral Analysis of Electroencephalogram Using Neural Networks to Assess the Depth of Anesthesia
- Authors: Lavrov N.G.1,2,3, Bulaev V.V.1, Solouhin E.N.1, Taratuhin S.A.1, Chistyakov A.V.1
-
Affiliations:
- Triton Electronics LLC
- Krasovsky Institute of Mathematics and Mechanics
- Ural Federal University
- Issue: Vol 49, No 6 (2016)
- Pages: 380-384
- Section: Article
- URL: https://journals.rcsi.science/0006-3398/article/view/234297
- DOI: https://doi.org/10.1007/s10527-016-9571-9
- ID: 234297
Cite item
Abstract
The article reviews algorithms of bispectral analysis of the electroencephalogram (EEG) signal of a patient to determine the level of brain activity during sedative-assisted treatment. The proposed algorithms are based on construction of multiple convolutions of complex amplitudes of the EEG signal, combined into so-called bispectra. Artificial neural networks (ANNs) are used to perform bispectral analysis and form a conclusion on the degree of patient brain activity. The article also shows individual results of functioning of the algorithms on real EEG signals and compares these results with expert judgments of doctors (anesthesiologists and neurophysiologists).
About the authors
N. G. Lavrov
Triton Electronics LLC; Krasovsky Institute of Mathematics and Mechanics; Ural Federal University
Author for correspondence.
Email: lavrov_ng@mail.ru
Russian Federation, Ekaterinburg; Ekaterinburg; Ekaterinburg
V. V. Bulaev
Triton Electronics LLC
Email: lavrov_ng@mail.ru
Russian Federation, Ekaterinburg
E. N. Solouhin
Triton Electronics LLC
Email: lavrov_ng@mail.ru
Russian Federation, Ekaterinburg
S. A. Taratuhin
Triton Electronics LLC
Email: lavrov_ng@mail.ru
Russian Federation, Ekaterinburg
A. V. Chistyakov
Triton Electronics LLC
Email: lavrov_ng@mail.ru
Russian Federation, Ekaterinburg
Supplementary files
