Automatic Detection of Microsleep Episodes With Deep Learning
Open Access
- 24 March 2021
- journal article
- research article
- Published by Frontiers Media SA in Frontiers in Neuroscience
- Vol. 15
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.Keywords
All Related Versions
Funding Information
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung
This publication has 24 references indexed in Scilit:
- Trends in insomnia and excessive daytime sleepiness among US adults from 2002 to 2012Sleep Medicine, 2015
- In-Flight Automatic Detection of Vigilance States Using a Single EEG ChannelIEEE Transactions on Biomedical Engineering, 2014
- Automatic detection of drowsiness in EEG records based on multimodal analysisMedical Engineering & Physics, 2013
- EEG Vigilance Regulation Patterns and Their Discriminative Power to Separate Patients with Major Depression from Healthy ControlsNeuropsychobiology, 2012
- Survey of Clustering AlgorithmsIEEE Transactions on Neural Networks, 2005
- Prevalence of excessive daytime sleepiness and associated factors in a Brazilian community: the Bambuı́ studySleep Medicine, 2004
- Long Short-Term MemoryNeural Computation, 1997
- Occurrence of ‘microsleeps’ during daytime sleep onset in normal subjectsElectroencephalography and Clinical Neurophysiology, 1996
- Neocognitron: A Self-Organizing Neural Network Model for a Mechanism of Visual Pattern Recognition1982
- A Coefficient of Agreement for Nominal ScalesEducational and Psychological Measurement, 1960