Cargando…
Detection of sleep apnea from single-channel electroencephalogram (EEG) using an explainable convolutional neural network (CNN)
Sleep apnea (SA) is a common disorder involving the cessation of breathing during sleep. It can cause daytime hypersomnia, accidents, and, if allowed to progress, serious, chronic conditions. Continuous positive airway pressure is an effective SA treatment. However, long waitlists impede timely diag...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9469966/ https://www.ncbi.nlm.nih.gov/pubmed/36099242 http://dx.doi.org/10.1371/journal.pone.0272167 |
_version_ | 1784788747648237568 |
---|---|
author | Barnes, Lachlan D. Lee, Kevin Kempa-Liehr, Andreas W. Hallum, Luke E. |
author_facet | Barnes, Lachlan D. Lee, Kevin Kempa-Liehr, Andreas W. Hallum, Luke E. |
author_sort | Barnes, Lachlan D. |
collection | PubMed |
description | Sleep apnea (SA) is a common disorder involving the cessation of breathing during sleep. It can cause daytime hypersomnia, accidents, and, if allowed to progress, serious, chronic conditions. Continuous positive airway pressure is an effective SA treatment. However, long waitlists impede timely diagnosis; overnight sleep studies involve trained technicians scoring a polysomnograph, which comprises multiple physiological signals including multi-channel electroencephalography (EEG). Therefore, it is important to develop simplified and automated approaches to detect SA. In the present study, we have developed an explainable convolutional neural network (CNN) to detect SA events from single-channel EEG recordings which generalizes across subjects. The network architecture consisted of three convolutional layers. We tuned hyperparameters using the Hyperband algorithm, optimized parameters using Adam, and quantified network performance with subjectwise 10-fold cross-validation. Our CNN performed with an accuracy of 69.9%, and a Matthews correlation coefficient (MCC) of 0.38. To explain the mechanisms of our trained network, we used critical-band masking (CBM): after training, we added bandlimited noise to test recordings; we parametrically varied the noise band center frequency and noise intensity, quantifying the deleterious effect on performance. We reconciled the effects of CBM with lesioning, wherein we zeroed the trained network’s 1st-layer filter kernels in turn, quantifying the deleterious effect on performance. These analyses indicated that the network learned frequency-band information consistent with known SA biomarkers, specifically, delta and beta band activity. Our results indicate single-channel EEG may have clinical potential for SA diagnosis. |
format | Online Article Text |
id | pubmed-9469966 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Public Library of Science |
record_format | MEDLINE/PubMed |
spelling | pubmed-94699662022-09-14 Detection of sleep apnea from single-channel electroencephalogram (EEG) using an explainable convolutional neural network (CNN) Barnes, Lachlan D. Lee, Kevin Kempa-Liehr, Andreas W. Hallum, Luke E. PLoS One Research Article Sleep apnea (SA) is a common disorder involving the cessation of breathing during sleep. It can cause daytime hypersomnia, accidents, and, if allowed to progress, serious, chronic conditions. Continuous positive airway pressure is an effective SA treatment. However, long waitlists impede timely diagnosis; overnight sleep studies involve trained technicians scoring a polysomnograph, which comprises multiple physiological signals including multi-channel electroencephalography (EEG). Therefore, it is important to develop simplified and automated approaches to detect SA. In the present study, we have developed an explainable convolutional neural network (CNN) to detect SA events from single-channel EEG recordings which generalizes across subjects. The network architecture consisted of three convolutional layers. We tuned hyperparameters using the Hyperband algorithm, optimized parameters using Adam, and quantified network performance with subjectwise 10-fold cross-validation. Our CNN performed with an accuracy of 69.9%, and a Matthews correlation coefficient (MCC) of 0.38. To explain the mechanisms of our trained network, we used critical-band masking (CBM): after training, we added bandlimited noise to test recordings; we parametrically varied the noise band center frequency and noise intensity, quantifying the deleterious effect on performance. We reconciled the effects of CBM with lesioning, wherein we zeroed the trained network’s 1st-layer filter kernels in turn, quantifying the deleterious effect on performance. These analyses indicated that the network learned frequency-band information consistent with known SA biomarkers, specifically, delta and beta band activity. Our results indicate single-channel EEG may have clinical potential for SA diagnosis. Public Library of Science 2022-09-13 /pmc/articles/PMC9469966/ /pubmed/36099242 http://dx.doi.org/10.1371/journal.pone.0272167 Text en © 2022 Barnes et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. |
spellingShingle | Research Article Barnes, Lachlan D. Lee, Kevin Kempa-Liehr, Andreas W. Hallum, Luke E. Detection of sleep apnea from single-channel electroencephalogram (EEG) using an explainable convolutional neural network (CNN) |
title | Detection of sleep apnea from single-channel electroencephalogram (EEG) using an explainable convolutional neural network (CNN) |
title_full | Detection of sleep apnea from single-channel electroencephalogram (EEG) using an explainable convolutional neural network (CNN) |
title_fullStr | Detection of sleep apnea from single-channel electroencephalogram (EEG) using an explainable convolutional neural network (CNN) |
title_full_unstemmed | Detection of sleep apnea from single-channel electroencephalogram (EEG) using an explainable convolutional neural network (CNN) |
title_short | Detection of sleep apnea from single-channel electroencephalogram (EEG) using an explainable convolutional neural network (CNN) |
title_sort | detection of sleep apnea from single-channel electroencephalogram (eeg) using an explainable convolutional neural network (cnn) |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9469966/ https://www.ncbi.nlm.nih.gov/pubmed/36099242 http://dx.doi.org/10.1371/journal.pone.0272167 |
work_keys_str_mv | AT barneslachland detectionofsleepapneafromsinglechannelelectroencephalogrameegusinganexplainableconvolutionalneuralnetworkcnn AT leekevin detectionofsleepapneafromsinglechannelelectroencephalogrameegusinganexplainableconvolutionalneuralnetworkcnn AT kempaliehrandreasw detectionofsleepapneafromsinglechannelelectroencephalogrameegusinganexplainableconvolutionalneuralnetworkcnn AT hallumlukee detectionofsleepapneafromsinglechannelelectroencephalogrameegusinganexplainableconvolutionalneuralnetworkcnn |