Show simple item record

dc.contributor.author
Malafeev, Alexander
dc.contributor.author
Hertig-Godeschalk, Anneke
dc.contributor.author
Schreier, David R.
dc.contributor.author
Skorucak, Jelena
dc.contributor.author
Mathis, Johannes
dc.contributor.author
Achermann, Peter
dc.date.accessioned
2021-04-16T09:49:30Z
dc.date.available
2021-04-16T04:32:49Z
dc.date.available
2021-04-16T09:49:30Z
dc.date.issued
2021-03
dc.identifier.issn
1662-453X
dc.identifier.issn
1662-4548
dc.identifier.other
10.3389/fnins.2021.564098
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/478957
dc.identifier.doi
10.3929/ethz-b-000478957
dc.description.abstract
Brief fragments of sleep shorter than 15 s are defined as microsleep episodes (MSEs), often subjectively perceived as sleepiness. Their main characteristic is a slowing in frequency in the electroencephalogram (EEG), similar to stage N1 sleep according to standard criteria. The maintenance of wakefulness test (MWT) is often used in a clinical setting to assess vigilance. Scoring of the MWT in most sleep-wake centers is limited to classical definition of sleep (30 s epochs), and MSEs are mostly not considered in the absence of established scoring criteria defining MSEs but also because of the laborious work. We aimed for automatic detection of MSEs with machine learning, i.e., with deep learning based on raw EEG and EOG data as input. We analyzed MWT data of 76 patients. Experts visually scored wakefulness, and according to recently developed scoring criteria MSEs, microsleep episode candidates (MSEc), and episodes of drowsiness (ED). We implemented segmentation algorithms based on convolutional neural networks (CNNs) and a combination of a CNN with a long-short term memory (LSTM) network. A LSTM network is a type of a recurrent neural network which has a memory for past events and takes them into account. Data of 53 patients were used for training of the classifiers, 12 for validation and 11 for testing. Our algorithms showed a good performance close to human experts. The detection was very good for wakefulness and MSEs and poor for MSEc and ED, similar to the low inter-expert reliability for these borderline segments. We performed a visualization of the internal representation of the data by the artificial neuronal network performing best using t-distributed stochastic neighbor embedding (t-SNE). Visualization revealed that MSEs and wakefulness were mostly separable, though not entirely, and MSEc and ED largely intersected with the two main classes. We provide a proof of principle that it is feasible to reliably detect MSEs with deep neuronal networks based on raw EEG and EOG data with a performance close to that of human experts. The code of the algorithms (https://github.com/alexander-malafeev/microsleep-detection) and data (https://zenodo.org/record/3251716) are available.
en_US
dc.format
application/pdf
en_US
dc.language.iso
en
en_US
dc.publisher
Frontiers Media
dc.rights.uri
http://creativecommons.org/licenses/by/4.0/
dc.subject
Microsleep episodes
en_US
dc.subject
Excessive daytime sleepiness
en_US
dc.subject
Drowsiness
en_US
dc.subject
Deep learning
en_US
dc.subject
Machine learning
en_US
dc.title
Automatic Detection of Microsleep Episodes With Deep Learning
en_US
dc.type
Journal Article
dc.rights.license
Creative Commons Attribution 4.0 International
dc.date.published
2021-03-24
ethz.journal.title
Frontiers in Neuroscience
ethz.journal.volume
15
en_US
ethz.journal.abbreviated
Front Neurosci
ethz.pages.start
564098
en_US
ethz.size
12 p.
en_US
ethz.version.deposit
publishedVersion
en_US
ethz.identifier.wos
ethz.identifier.scopus
ethz.publication.place
Lausanne
ethz.publication.status
published
en_US
ethz.date.deposited
2021-04-16T04:33:14Z
ethz.source
SCOPUS
ethz.eth
yes
en_US
ethz.availability
Open access
en_US
ethz.rosetta.installDate
2021-04-16T09:49:40Z
ethz.rosetta.lastUpdated
2024-02-02T13:31:44Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Automatic%20Detection%20of%20Microsleep%20Episodes%20With%20Deep%20Learning&rft.jtitle=Frontiers%20in%20Neuroscience&rft.date=2021-03&rft.volume=15&rft.spage=564098&rft.issn=1662-453X&1662-4548&rft.au=Malafeev,%20Alexander&Hertig-Godeschalk,%20Anneke&Schreier,%20David%20R.&Skorucak,%20Jelena&Mathis,%20Johannes&rft.genre=article&rft_id=info:doi/10.3389/fnins.2021.564098&
 Search print copy at ETH Library

Files in this item

Thumbnail

Publication type

Show simple item record