A Deep Learning Architecture for Temporal Sleep Stage Classification Using Multivariate and Multimodal Time Series

By Stanislas Chambon, Mathieu N. Galtier, Pierrick J. Arnal, Gilles Wainrib, Alexandre Gramfort. IEEE transactions on neural systems and rehabilitation engineering, 2017

565 citations recorded by the source corpus.

Sleep stage classification constitutes an important preliminary exam in the diagnosis of sleep disorders. It is traditionally performed by a sleep expert who assigns to each 30 s of the signal of a sleep stage, based on the visual inspection of signals such as electroencephalograms (EEGs), electrooculograms (EOGs), electrocardiograms, and electromyograms (EMGs). We introduce here the first deep learning approach for sleep stage classification that learns end-to-end without computing spectrograms or extracting handcrafted features, that exploits all multivariate and multimodal polysomnography (PSG) signals (EEG, EMG, and EOG), and that can exploit the temporal context of each 30-s window of data. For each modality, the first layer learns linear spatial filters that exploit the array of sensors to increase the signal-to-noise ratio, and the last layer feeds the learnt representation to a softmax classifier. Our model is compared to alternative automatic approaches based on convolutional networks or decisions trees. Results obtained on 61 publicly available PSG records with up to 20 EEG channels demonstrate that our network architecture yields the state-of-the-art performance. Our study reveals a number of insights on the spatiotemporal distribution of the signal of interest: a good tradeoff for optimal classification performance measured with balanced accuracy is to use 6 EEG with 2 EOG (left and right) and 3 EMG chin channels. Also exploiting 1 min of data before and after each data segment offers the strongest improvement when a limited number of channels are available. As sleep experts, our system exploits the multivariate and multimodal nature of PSG signals in order to deliver the state-of-the-art classification performance with a small computational cost.

Subfields: Biomedical Engineering, Cardiology and Cardiovascular Medicine, Cognitive Neuroscience

View Paper: https://www.semanticscholar.org/paper/0504b7cc39d2e601a5eaec344c2c188544294d43

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

Cuntai Guan

In Cardiology and Cardiovascular Medicine

In Cognitive Neuroscience

Citations in the corpus

A Survey of Learning Causality with Data: Problems and Methods (2018, methodology): “representation of data for many influential applications such as speech recognition [50], sleep stage classification [23], and quantitative trading [4].”
Deep learning-based electroencephalography analysis: a systematic review (2019, methodology): “As highlighted in [33, 220], it is often preferable to use metrics that are robust to class imbalance, such as balanced accuracy, f1-score, and the ROC AUC for binary problems.”
Joint Classification and Prediction CNN Framework for Automatic Sleep Stage Classification (2018, background): “[37], both of which recently reported the”
SeqSleepNet: End-to-End Hierarchical Recurrent Neural Network for Sequence-to-Sequence Automatic Sleep Staging (2018, unknown): “With the deep learning methods evolving, automatic sleep staging performance has been boosted considerably as state-of-the-art results have been reported on several datasets [8], [9], [12], [13].”
SleepTransformer: Automatic Sleep Staging With Interpretability and Uncertainty Quantification (2021, background): “It is, therefore, free of convolutional and recurrent components which are the main ingredients in existing deep-learning models for sleep staging, such as [12], [13], [15]–[17], [44]– [46].”
XSleepNet: Multi-View Sequential Model for Automatic Sleep Staging (2020, unknown): “The standard oneto-one [18], [19] and many-to-one [17], [20] are beginning to be replaced with one-to-many (i.”
An Attention-Based Deep Learning Approach for Sleep Stage Classification With Single-Channel EEG (2021, methodology): “Additionally in [16], the authors used 2D convolution along with MaxPooling layers This work is licensed under a Creative Commons Attribution 4.0 License.”