Cargando…

Monitoring Depth of Anesthesia Based on Hybrid Features and Recurrent Neural Network

Electroencephalogram (EEG) signals contain valuable information about the different physiological states of the brain, with a variety of linear and nonlinear features that can be used to investigate brain activity. Monitoring the depth of anesthesia (DoA) with EEG is an ongoing challenge in anesthes...

Descripción completa

Detalles Bibliográficos
Autores principales: Li, Ronglin, Wu, Qiang, Liu, Ju, Wu, Qi, Li, Chao, Zhao, Qibin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7020827/
https://www.ncbi.nlm.nih.gov/pubmed/32116494
http://dx.doi.org/10.3389/fnins.2020.00026
_version_ 1783497821443325952
author Li, Ronglin
Wu, Qiang
Liu, Ju
Wu, Qi
Li, Chao
Zhao, Qibin
author_facet Li, Ronglin
Wu, Qiang
Liu, Ju
Wu, Qi
Li, Chao
Zhao, Qibin
author_sort Li, Ronglin
collection PubMed
description Electroencephalogram (EEG) signals contain valuable information about the different physiological states of the brain, with a variety of linear and nonlinear features that can be used to investigate brain activity. Monitoring the depth of anesthesia (DoA) with EEG is an ongoing challenge in anesthesia research. In this paper, we propose a novel method based on Long Short-Term Memory (LSTM) and a sparse denoising autoencoder (SDAE) to combine the hybrid features of EEG to monitor the DoA. The EEG signals were preprocessed using filtering, etc., and then more than ten features including sample entropy, permutation entropy, spectra, and alpha-ratio were extracted from the EEG signal. We then integrated the optional features such as permutation entropy and alpha-ratio to extract the essential structure and learn the most efficient temporal model for monitoring the DoA. Compared with using a single feature, the proposed model could accurately estimate the depth of anesthesia with higher prediction probability (P(k)). Experimental results evaluated on the datasets demonstrated that our proposed method provided better performance than the methods using permutation entropy, alpha-ratio, LSTM, and other traditional indices.
format Online
Article
Text
id pubmed-7020827
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-70208272020-02-28 Monitoring Depth of Anesthesia Based on Hybrid Features and Recurrent Neural Network Li, Ronglin Wu, Qiang Liu, Ju Wu, Qi Li, Chao Zhao, Qibin Front Neurosci Neuroscience Electroencephalogram (EEG) signals contain valuable information about the different physiological states of the brain, with a variety of linear and nonlinear features that can be used to investigate brain activity. Monitoring the depth of anesthesia (DoA) with EEG is an ongoing challenge in anesthesia research. In this paper, we propose a novel method based on Long Short-Term Memory (LSTM) and a sparse denoising autoencoder (SDAE) to combine the hybrid features of EEG to monitor the DoA. The EEG signals were preprocessed using filtering, etc., and then more than ten features including sample entropy, permutation entropy, spectra, and alpha-ratio were extracted from the EEG signal. We then integrated the optional features such as permutation entropy and alpha-ratio to extract the essential structure and learn the most efficient temporal model for monitoring the DoA. Compared with using a single feature, the proposed model could accurately estimate the depth of anesthesia with higher prediction probability (P(k)). Experimental results evaluated on the datasets demonstrated that our proposed method provided better performance than the methods using permutation entropy, alpha-ratio, LSTM, and other traditional indices. Frontiers Media S.A. 2020-02-07 /pmc/articles/PMC7020827/ /pubmed/32116494 http://dx.doi.org/10.3389/fnins.2020.00026 Text en Copyright © 2020 Li, Wu, Liu, Wu, Li and Zhao. http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Li, Ronglin
Wu, Qiang
Liu, Ju
Wu, Qi
Li, Chao
Zhao, Qibin
Monitoring Depth of Anesthesia Based on Hybrid Features and Recurrent Neural Network
title Monitoring Depth of Anesthesia Based on Hybrid Features and Recurrent Neural Network
title_full Monitoring Depth of Anesthesia Based on Hybrid Features and Recurrent Neural Network
title_fullStr Monitoring Depth of Anesthesia Based on Hybrid Features and Recurrent Neural Network
title_full_unstemmed Monitoring Depth of Anesthesia Based on Hybrid Features and Recurrent Neural Network
title_short Monitoring Depth of Anesthesia Based on Hybrid Features and Recurrent Neural Network
title_sort monitoring depth of anesthesia based on hybrid features and recurrent neural network
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7020827/
https://www.ncbi.nlm.nih.gov/pubmed/32116494
http://dx.doi.org/10.3389/fnins.2020.00026
work_keys_str_mv AT lironglin monitoringdepthofanesthesiabasedonhybridfeaturesandrecurrentneuralnetwork
AT wuqiang monitoringdepthofanesthesiabasedonhybridfeaturesandrecurrentneuralnetwork
AT liuju monitoringdepthofanesthesiabasedonhybridfeaturesandrecurrentneuralnetwork
AT wuqi monitoringdepthofanesthesiabasedonhybridfeaturesandrecurrentneuralnetwork
AT lichao monitoringdepthofanesthesiabasedonhybridfeaturesandrecurrentneuralnetwork
AT zhaoqibin monitoringdepthofanesthesiabasedonhybridfeaturesandrecurrentneuralnetwork