DeepSleepNet: A Model for Automatic Sleep Stage Scoring Based on Raw Single-Channel EEG

By Akara Supratak, Hao Dong, Chao Wu, Yike Guo. IEEE transactions on neural systems and rehabilitation engineering, 2017

1,220 citations recorded by the source corpus.

This paper proposes a deep learning model, named DeepSleepNet, for automatic sleep stage scoring based on raw single-channel EEG. Most of the existing methods rely on hand-engineered features, which require prior knowledge of sleep analysis. Only a few of them encode the temporal information, such as transition rules, which is important for identifying the next sleep stages, into the extracted features. In the proposed model, we utilize convolutional neural networks to extract time-invariant features, and bidirectional-long short-term memory to learn transition rules among sleep stages automatically from EEG epochs. We implement a two-step training algorithm to train our model efficiently. We evaluated our model using different single-channel EEGs (F4-EOG (left), Fpz-Cz, and Pz-Oz) from two public sleep data sets, that have different properties (e.g., sampling rate) and scoring standards (AASM and R&K). The results showed that our model achieved similar overall accuracy and macro F1-score (MASS: 86.2%−81.7, Sleep-EDF: 82.0%−76.9) compared with the state-of-the-art methods (MASS: 85.9%−80.5, Sleep-EDF: 78.9%−73.7) on both data sets. This demonstrated that, without changing the model architecture and the training algorithm, our model could automatically learn features for sleep stage scoring from different raw single-channel EEGs from different data sets without utilizing any hand-engineered features.

Subfields: Cognitive Neuroscience, Experimental and Cognitive Psychology

View Paper: https://www.semanticscholar.org/paper/95034bd320b25c266175179b7a512eaaa7e75697

How researchers see this paper

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

In Cognitive Neuroscience

In Experimental and Cognitive Psychology

Citations in the corpus

EEG-Based Brain-Computer Interfaces (BCIs): A Survey of Recent Studies on Signal Sensing Technologies and Computational Intelligence Approaches and Their Applications (2020, methodology): “[137] employed a CNN to extract time-invariable features and an LSTM bidirectional algorithm for transitional rule learning.”
A Deep Learning Architecture for Temporal Sleep Stage Classification Using Multivariate and Multimodal Time Series (2017, methodology): “We now introduce the three state-of-the-art approaches that we used for comparison with our approach: a gradient boosting classiﬁer [39] trained on hand-crafted features and two convolutional networks trained on raw univariate time series following the approach of [11] and [12].”
Joint Classification and Prediction CNN Framework for Automatic Sleep Stage Classification (2018, methodology): “More speciﬁcally, compared to the best opponent, DeepSleepNet [22], a margin of 2 .”
SleepTransformer: Automatic Sleep Staging With Interpretability and Uncertainty Quantification (2021, methodology): “74 × 10 6 828 DeepSleepNet [13] 2 .”
U-Time: A Fully Convolutional Network for Time Series Segmentation Applied to Sleep Staging (2019, methodology): “rovide other metrics or confusion matrices from which we could derive the F1 score. We only compare to EEG based methods. LSTM comparison We re-implemented the successful DeepSleepNet CNN-LSTM model [Supratak et al., 2017] for two purposes. First, we tried to push the performance of this model to th”
U-Sleep: resilient high-frequency sleep staging (2021, neutral): “While several high-performance deep-learning-based sleep staging systems have been proposed recently 28 – 38 , these have not yet been widely adopted in clinical practice because it is not clear if the reported results can be generalized.”
Deep learning-based electroencephalography analysis: a systematic review (2019, methodology): “Therefore, taking both data and code availability into account, only 11 out of 156 studies (7%) could easily be reproduced using both the same data and code [149, 160, 152, 224, 222, 167, 221, 104, 161, 164, 85].”
An Attention-Based Deep Learning Approach for Sleep Stage Classification With Single-Channel EEG (2021, methodology): “Some researchers combined CNN with RNN by using CNN for features extraction and RNN for modelling the time dependencies [20]–[23].”
SeqSleepNet: End-to-End Hierarchical Recurrent Neural Network for Sequence-to-Sequence Automatic Sleep Staging (2018, positive): “Combinations of different architectures, such as DNN+RNN [25] and CNN+RNN [9], [12] have also been exploited.”
Data Augmentation for Deep-Learning-Based Electroencephalography. (2020, methodology): “Cost-sensitive learning [45], oversampling of the minority class [92, 94, 107], and subsampling the majority class [98, 108] are common techniques to address imbalanced classes.”
Deep convolutional neural networks for interpretable analysis of EEG sleep stage scoring (2017, background): “More recently, recurrent neural network variants have been used to capture long-term dependencies or stage transition rules [6, 7].”
SleepEEGNet: Automated sleep stage scoring with sequence to sequence deep learning approach (2019, methodology): “We applied almost the same CNN architecture provided by [22].”
XSleepNet: Multi-View Sequential Model for Automatic Sleep Staging (2020, neutral): “Particularly, for SleepEDF-20 and SleepEDF-78, we experimented with two common ways these databases were used in literature: (1) only in-bed parts of the recordings were used as recommended in [55], [56]; (2) 30 minutes of data before and after in-bed parts were further included in the experiments f”