Joint Classification and Prediction CNN Framework for Automatic Sleep Stage Classification

By Huy P Phan, Fernando Andreotti, Navin Cooray, Oliver Y. Chen, M. de Vos. IEEE Transactions on Biomedical Engineering, 2018

400 citations recorded by the source corpus.

Correctly identifying sleep stages is important in diagnosing and treating sleep disorders. This paper proposes a joint classification-and-prediction framework based on convolutional neural networks (CNNs) for automatic sleep staging, and, subsequently, introduces a simple yet efficient CNN architecture to power the framework. Given a single input epoch, the novel framework jointly determines its label (classification) and its neighboring epochs’ labels (prediction) in the contextual output. While the proposed framework is orthogonal to the widely adopted classification schemes, which take one or multiple epochs as contextual inputs and produce a single classification decision on the target epoch, we demonstrate its advantages in several ways. First, it leverages the dependency among consecutive sleep epochs while surpassing the problems experienced with the common classification schemes. Second, even with a single model, the framework has the capacity to produce multiple decisions, which are essential in obtaining a good performance as in ensemble-of-models methods, with very little induced computational overhead. Probabilistic aggregation techniques are then proposed to leverage the availability of multiple decisions. To illustrate the efficacy of the proposed framework, we conducted experiments on two public datasets: Sleep-EDF Expanded (Sleep-EDF), which consists of 20 subjects, and Montreal Archive of Sleep Studies (MASS) dataset, which consists of 200 subjects. The proposed framework yields an overall classification accuracy of 82.3% and 83.6%, respectively. We also show that the proposed framework not only is superior to the baselines based on the common classification schemes but also outperforms existing deep-learning approaches. To our knowledge, this is the first work going beyond the standard single-output classification to consider multitask neural networks for automatic sleep staging. This framework provides avenues for further studies of different neural-network architectures for automatic sleep staging.

Subfields: Biomedical Engineering, Cognitive Neuroscience, Experimental and Cognitive Psychology

View Paper: https://www.semanticscholar.org/paper/6d37dace192a0530e5bd1de61101e58ef203d8ff

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

In Cognitive Neuroscience

In Experimental and Cognitive Psychology

Citations in the corpus

U-Time: A Fully Convolutional Network for Time Series Segmentation Applied to Sleep Staging (2019, neutral): “, 2017], [3] [Phan et al., 2018], [4] [Tsinalis et al.”
SleepTransformer: Automatic Sleep Staging With Interpretability and Uncertainty Quantification (2021, background): “For sleep particularly, the transitioning epochs (whose sleep stages are different from those of its preceding and/or succeeding neighbors [48]) are usually difficult ones as human scorers also tend to disagree and machine scoring systems often make mistakes.”
EEG-Based Brain-Computer Interfaces (BCIs): A Survey of Recent Studies on Signal Sensing Technologies and Computational Intelligence Approaches and Their Applications (2020, background): “also considered for automatic sleep classification in a recent study [105].”
SeqSleepNet: End-to-End Hierarchical Recurrent Neural Network for Sequence-to-Sequence Automatic Sleep Staging (2018, positive): “The work in [8] showed that while the contextual input does not always lead to performance improvement regardless of the choice of classification model, it also suffers from the modelling ambiguity and high computational overhead.”
An Attention-Based Deep Learning Approach for Sleep Stage Classification With Single-Channel EEG (2021, methodology): “Second, MultitaskCNN [17] and SeqSleepNet [37]”
Deep learning-based electroencephalography analysis: a systematic review (2019, background): “Active Grasp and lift [8] Mental tasks [125] [68, 133] Motor imagery [226, 94] [43, 146, 172, 150, 36, 104, 170, 147, 204] [216] [9] [27, 107, 59, 113] [121] [224] [222, 23] RSVP [154] Slow cortical potentials [37] Speech decoding [162] [166] Active & Reactive MI & ERP [87] Reactive ERP [211, 191, 1”
XSleepNet: Multi-View Sequential Model for Automatic Sleep Staging (2020, neutral): “1 Multitask CNN [10], [21] − − − − − − − − − − 83.”