Skip to main content

Deep Neural Networks for Automatic Classification of Anesthetic-Induced Unconsciousness

Patlatzoglou, Konstantinos and Chennu, Srivas and Boly, Melanie and Noirhomme, Quentin and Bonhomme, Vincent and Brichant, Jean-Francois and Gosseries, Olivia and Laureys, Steven (2018) Deep Neural Networks for Automatic Classification of Anesthetic-Induced Unconsciousness. In: Brain Informatics. Springer. (doi:10.1007/978-3-030-05587-5_21) (KAR id:69530)

PDF Author's Accepted Manuscript
Language: English
Download (640kB) Preview
[img]
Preview
Official URL
https://link.springer.com/chapter/10.1007/978-3-03...

Abstract

Despite the common use of anesthetics to modulate consciousness in the clinic, brain-based monitoring of consciousness is uncommon. We com-bined electroencephalographic measurement of brain activity with deep neural networks to automatically discriminate anesthetic states induced by propofol. Our results with leave-one-participant-out-cross-validation show that convolutional neural networks significantly outperform multilayer perceptrons in discrimination accuracy when working with raw time series. Perceptrons achieved comparable accuracy when provided with power spec-tral densities. These findings highlight the potential of deep convolutional networks for completely automatic extraction of useful spatio-temporo-spectral features from human EEG.

Item Type: Book section
DOI/Identification number: 10.1007/978-3-030-05587-5_21
Subjects: T Technology
Divisions: Faculties > Sciences > School of Computing
Depositing User: Srivas Chennu
Date Deposited: 11 Oct 2018 13:33 UTC
Last Modified: 21 May 2020 15:26 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/69530 (The current URI for this page, for reference purposes)
Patlatzoglou, Konstantinos: https://orcid.org/0000-0002-5888-8490
Chennu, Srivas: https://orcid.org/0000-0002-6840-2941
  • Depositors only (login required):

Downloads

Downloads per month over past year