Joint Classification and Prediction CNN Framework for Automatic Sleep Stage Classification

Comparison of Time-Frequency Analyzes for a Sleep Staging Application with CNN

Sleep staging is the process of acquiring biological signals during sleep and marking them according to the stages of sleep. The procedure is performed by an experienced physician and takes more time. When this process is automated, the processing load will be reduced and the time required to identify disease will also be reduced. In this paper, 8 different transform methods for automatic sleep-staging based on convolutional neural networks (CNNs) were compared to classify sleep stages using single-channel electroencephalogram (EEG) signals. Five different labels were used to stage the sleep. These are Wake (W), Non Rapid Eye Movement (NonREM)-1 (N1), NonREM-2 (N2), NonREM-3 (N3), and REM (R). The classifications were done end-to-end without any hand-crafted features, ie without requiring any feature engineering. Time-Frequency components obtained by Short Time Fourier Transform, Discrete Wavelet Transform, Discrete Cosine Transform, Hilbert-Huang Transform, Discrete Gabor Transform, Fast Walsh-Hadamard Transform, Choi-Williams Distribution, and Wigner-Willie Distribution were classified with a supervised deep convolutional neural network to perform sleep staging. The discrete Cosine Transform-CNN method (DCT-CNN) showed the highest performance among the methods suggested in this paper with an F1 score of 89% and a value of 0.86 kappa. The findings of this study revealed that the transformation techniques utilized for the most accurate representation of input data are far superior to traditional approaches based on manual feature extraction, which acquires time, frequency, or nonlinear characteristics. The results of this article are expected to be useful to researchers in the development of low-cost, and easily portable devices.

Automatic sleep staging of EEG signals: recent development, challenges, and future directions

Modern deep learning holds a great potential to transform clinical practice on human sleep. Teaching a machine to carry out routine tasks would be a tremendous reduction in workload for clinicians. Sleep staging, a fundamental step in sleep practice, is a suitable task for this and will be the focus in this article. Recently, automatic sleep staging systems have been trained to mimic manual scoring, leading to similar performance to human sleep experts, at least on scoring of healthy subjects. Despite tremendous progress, we have not seen automatic sleep scoring adopted widely in clinical environments. This review aims to give a shared view of the authors on the most recent state-of-the-art development in automatic sleep staging, the challenges that still need to be addressed, and the future directions for automatic sleep scoring to achieve clinical value.

Classification of Sleep Stage with Biosignal Images Using Convolutional Neural Networks

Clinicians and researchers divide sleep periods into different sleep stages to analyze the quality of sleep. Despite advances in machine learning, sleep-stage classification is still performed manually. The classification process is tedious and time-consuming, but its automation has not yet been achieved. Another problem is low accuracy due to inconsistencies between somnologists. In this paper, we propose a method to classify sleep stages using a convolutional neural network. The network is trained with EEG and EOG images of time and frequency domains. The images of the biosignal are appropriate as inputs to the network, as these are natural inputs provided to somnologists in polysomnography. To validate the network, the sleep-stage classifier was trained and tested using the public Sleep-EDFx dataset. The results show that the proposed method achieves state-of-the-art performance on the Sleep-EDFx (accuracy 94%, F1 94%). The results demonstrate that the classifier is able to learn features described in the sleep scoring manual from the sleep data.

Automatic and Accurate Sleep Stage Classification via a Convolutional Deep Neural Network and Nanomembrane Electrodes

Sleep stage classification is an essential process of diagnosing sleep disorders and related diseases. Automatic sleep stage classification using machine learning has been widely studied due to its higher efficiency compared with manual scoring. Typically, a few polysomnography data are selected as input signals, and human experts label the corresponding sleep stages manually. However, the manual process includes human error and inconsistency in the scoring and stage classification. Here, we present a convolutional neural network (CNN)-based classification method that offers highly accurate, automatic sleep stage detection, validated by a public dataset and new data measured by wearable nanomembrane dry electrodes. First, our study makes a training and validation model using a public dataset with two brain signal and two eye signal channels. Then, we validate this model with a new dataset measured by a set of nanomembrane electrodes. The result of the automatic sleep stage classification shows that our CNN model with multi-taper spectrogram pre-processing achieved 88.85% training accuracy on the validation dataset and 81.52% prediction accuracy on our laboratory dataset. These results validate the reliability of our classification method on the standard polysomnography dataset and the transferability of our CNN model for other datasets measured with the wearable electrodes.

A Deep Learning Approach to Analyze Airline Customer Propensities: The Case of South Korea

In the airline industry, customer satisfaction occurs when passengers’ expectations are met through the airline experience. Considering that airline service quality is the main factor in obtaining new and retaining existing customers, airline companies are applying various approaches to improve the quality of the physical and social servicescapes. It is common to use data analysis techniques for analyzing customer propensity in marketing. However, their application to the airline industry has traditionally focused solely on surveys; hence, there is a lack of attention paid to deep learning techniques based on survey results. This study has two purposes. The first purpose is to find the relationship between various factors influencing customer churn risk and satisfaction by analyzing the airline customer data. For this, we applied deep learning techniques to the survey data collected from the users who have used mostly Korean airplanes. To the best of our knowledge, this is the one of the few attempts at applying deep learning to analyze airline customer propensities. The second purpose is to analyze the influence of the social servicescape, including the viewpoints of the cabin crew and passengers using aircraft, on airline customer propensities. The experimental results demonstrated that the proposed method of considering human services increased the accuracy of predictive models by up to 10% and 9% in predicting customer churn risk and satisfaction, respectively.

SleepTransformer: Automatic Sleep Staging with Interpretability and Uncertainty Quantification

BACKGROUND

Black-box skepticism is one of the main hindrances impeding deep-learning-based automatic sleep scoring from being used in clinical environments.

METHODS

Towards interpretability, this work proposes a sequence-to-sequence sleep staging model, namely SleepTransformer. It is based on the transformer backbone and offers interpretability of the models decisions at both the epoch and sequence level. We further propose a simple yet efficient method to quantify uncertainty in the models decisions. The method, which is based on entropy, can serve as a metric for deferring low-confidence epochs to a human expert for further inspection.

RESULTS

Making sense of the transformers self-attention scores for interpretability, at the epoch level, the attention scores are encoded as a heat map to highlight sleep-relevant features captured from the input EEG signal. At the sequence level, the attention scores are visualized as the influence of different neighboring epochs in an input sequence (i.e. the context) to recognition of a target epoch, mimicking the way manual scoring is done by human experts.

CONCLUSION

Additionally, we demonstrate that SleepTransformer performs on par with existing methods on two databases of different sizes.

SIGNIFICANCE

Equipped with interpretability and the ability of uncertainty quantification, SleepTransformer holds promise for being integrated into clinical settings.

Hybrid Sleep Stage Classification for Clinical Practices across Different Polysomnography Systems Using Frontal EEG

Automatic bio-signal processing and scoring have been a popular topic in recent years. This includes sleep stage classification, which is time-consuming when carried out by hand. Multiple sleep stage classification has been proposed in recent years. While effective, most of these processes are trained and validated against a singular set of data in uniformed pre-processing, whilst in a clinical environment, polysomnography (PSG) may come from different PSG systems that use different signal processing methods. In this study, we present a generalized sleep stage classification method that uses power spectra and entropy. To test its generality, we first trained our system using a uniform dataset and then validated it against another dataset with PSGs from different PSG systems. We found that the system achieved an accuracy of 0.80 and that it is highly consistent across most PSG records. A few samples of NREM3 sleep were classified poorly, and further inspection showed that these samples lost crucial NREM3 features due to aggressive filtering. This implies that the system’s effectiveness can be evaluated by human knowledge. Overall, our classification system shows consistent performance against PSG records that have been collected from different PSG systems, which gives it high potential in a clinical environment.

A System-on-Chip for Closed-loop Optogenetic Sleep Modulation

Stimulation of target neuronal populations using optogenetic techniques during specific sleep stages has begun to elucidate the mechanisms and effects of sleep. To conduct closed-loop optogenetic sleep studies in untethered animals, we designed a fully integrated, low-power system-on-chip (SoC) for real-time sleep stage classification and stage-specific optical stimulation. The SoC consists of a 4-channel analog front-end for recording polysomnography signals, a mixed-signal machine-learning (ML) core, and a 16-channel optical stimulation back-end. A novel ML algorithm and innovative circuit design techniques improved the online classification performance while minimizing power consumption. The SoC was designed and simulated in 180 nm CMOS technology. In an evaluation using an expert labeled sleep database with 20 subjects, the SoC achieves a high sensitivity of 0.806 and a specificity of 0.947 in discriminating 5 sleep stages. Overall power consumption in continuous operation is 97 µW.

LightSleepNet: A Lightweight Deep Model for Rapid Sleep Stage Classification with Spectrograms

Deep learning has achieved unprecedented success in sleep stage classification tasks, which starts to pave the way for potential real-world applications. However, due to its enormous size, deployment of deep neural networks is hindered by high cost at various aspects, such as computation power, storage, network bandwidth, power consumption, and hardware complexity. For further practical applications (e.g., wearable sleep monitoring devices), there is a need for simple and compact models. In this paper, we propose a lightweight model, namely LightSleepNet, for rapid sleep stage classification based on spectrograms. Our model is assembled by a much fewer number of model parameters compared to existing ones. Furthermore, we convert the raw EEG data into spectrograms to speed up the training process. We evaluate the model performance on several public sleep datasets with different characteristics. Experimental results show that our lightweight model using spectrogram as input can achieve comparable overall accuracy and Cohen's kappa (SHHS100: 86.7%-81.3%, Sleep-EDF: 83.7%-77.5%, Sleep-EDF-v1: 88.3%-84.5%) compared to the state-of-the-art methods on experimental datasets.

Feasibility Analysis of Symbolic Representation for Single-Channel EEG-Based Sleep Stages

Sleep screening based on the construction of sleep stages is one of the major tool for the assessment of sleep quality and early detection of sleep-related disorders. Due to the inherent variability such as inter-users anatomical variability and the inter-systems differences, representation learning of sleep stages in order to obtain the stable and reliable characteristics is runoff for downstream tasks in sleep science. In this paper, we investigated feasibility of the EEG-based symbolic representation for sleep stages. By combining the Latent Dirichlet Allocation topic model and comparing with different feature extraction methods, the work proved the feasibility of multi-topics representation for sleep stages and physiological signals.

Self-Applied Home Sleep Recordings: The Future of Sleep Medicine

Sleep disorders form a massive global health burden and there is an increasing need for simple and cost-efficient sleep recording devices. Recent machine learning-based approaches have already achieved scoring accuracy of sleep recordings on par with manual scoring, even with reduced recording montages. Simple and inexpensive monitoring over multiple consecutive nights with automatic analysis could be the answer to overcome the substantial economic burden caused by poor sleep and enable more efficient initial diagnosis, treatment planning, and follow-up monitoring for individuals suffering from sleep disorders.

A Novel Sleep Staging Network Based on Data Adaptation and Multimodal Fusion

Sleep staging is one of the important methods to diagnosis and treatment of sleep diseases. However, it is laborious and time-consuming, therefore, computer assisted sleep staging is necessary. Most of the existing sleep staging researches using hand-engineered features rely on prior knowledges of sleep analysis, and usually single channel electroencephalogram (EEG) is used for sleep staging task. Prior knowledge is not always available, and single channel EEG signal cannot fully represent the patient’s sleeping physiological states. To tackle the above two problems, we propose an automatic sleep staging network model based on data adaptation and multimodal feature fusion using EEG and electrooculogram (EOG) signals. 3D-CNN is used to extract the time-frequency features of EEG at different time scales, and LSTM is used to learn the frequency evolution of EOG. The nonlinear relationship between the High-layer features of EEG and EOG is fitted by deep probabilistic network. Experiments on SLEEP-EDF and a private dataset show that the proposed model achieves state-of-the-art performance. Moreover, the prediction result is in accordance with that from the expert diagnosis.

An Attention Based CNN-LSTM Approach for Sleep-Wake Detection With Heterogeneous Sensors

In this article, we propose an attention based convolutional neural network long short-term memory (CNN-LSTM) approach for sleep-wake detection with heterogeneous sensor data, i.e., acceleration and heart rate variability (HRV). Since the three-dimensional acceleration data was sampled with a high frequency, we firstly design a CNN-LSTM structure to effectively learn latent features from the acceleration. Meanwhile, considering the unique format of the HRV data, some effective features are extracted based on domain knowledge. Next, we design a unified architecture to efficiently merge the features learned by CNN-LSTM approach from the acceleration and the extracted features from the HRV, which enables us to make full use of all the available information from these two heterogeneous sources. Taking into consideration that these two heterogeneous sources may have distinct contributions for the sleep and wake states, we propose an attention network to dynamically adjust the importance of features from the two sources. Real-world experiments have been conducted to verify the effectiveness of the proposed approach for sleep-wake detection. The results demonstrate that the proposed method outperforms all existing approaches for sleep-wake classification. In the evaluation of leave-one-subject-out (LOSO) cross-validation which is more challenging and practical, the proposed method achieves remarkable improvements ranging from 5% to 46% over the benchmark approaches.

EEG-Based Brain-Computer Interfaces (BCIs): A Survey of Recent Studies on Signal Sensing Technologies and Computational Intelligence Approaches and Their Applications

Brain-Computer interfaces (BCIs) enhance the capability of human brain activities to interact with the environment. Recent advancements in technology and machine learning algorithms have increased interest in electroencephalographic (EEG)-based BCI applications. EEG-based intelligent BCI systems can facilitate continuous monitoring of fluctuations in human cognitive states under monotonous tasks, which is both beneficial for people in need of healthcare support and general researchers in different domain areas. In this review, we survey the recent literature on EEG signal sensing technologies and computational intelligence approaches in BCI applications, compensating for the gaps in the systematic summary of the past five years. Specifically, we first review the current status of BCI and signal sensing technologies for collecting reliable EEG signals. Then, we demonstrate state-of-the-art computational intelligence techniques, including fuzzy models and transfer learning in machine learning and deep learning algorithms, to detect, monitor, and maintain human cognitive states and task performance in prevalent applications. Finally, we present a couple of innovative BCI-inspired healthcare applications and discuss future research directions in EEG-based BCI research.

Attention based convolutional network for automatic sleep stage classification

Sleep staging is an important basis for diagnosing sleep-related problems. In this paper, an attention based convolutional network for automatic sleep staging is proposed. The network takes time-frequency image as input and predict sleep stage for each 30-s epoch as output. For each CNN feature maps, our model generate attention maps along two separate dimensions, time and filter, and then multiplied to form the final attention map. Residual-like fusion structure is used to append the attention map to the input feature map for adaptive feature refinement. In addition, to get the global feature representation with less information loss, the generalized mean pooling is introduced. To prove the efficacy of the proposed method, we have compared with two baseline method on sleep-EDF data set with different setting of the framework and input channel type, the experimental results show that the paper model has achieved significant improvements in terms of overall accuracy, Cohen's kappa, MF1, sensitivity and specificity. The performance of the proposed network is compared with that of the state-of-the-art algorithms with an overall accuracy of 83.4%, a macro F1-score of 77.3%, κ = 0.77, sensitivity = 77.1% and specificity = 95.4%, respectively. The experimental results demonstrate the superiority of the proposed network.

A Systematic Review of Sleep in Patients with Disorders of Consciousness: From Diagnosis to Prognosis

With the development of intensive care technology, the number of patients who survive acute severe brain injury has increased significantly. At present, it is difficult to diagnose the patients with disorders of consciousness (DOCs) because motor responses in these patients may be very limited and inconsistent. Electrophysiological criteria, such as event-related potentials or motor imagery, have also been studied to establish a diagnosis and prognosis based on command-following or active paradigms. However, the use of such task-based techniques in DOC patients is methodologically complex and requires careful analysis and interpretation. The present paper focuses on the analysis of sleep patterns for the evaluation of DOC and its relationships with diagnosis and prognosis outcomes. We discuss the concepts of sleep patterns in patients suffering from DOC, identification of this challenging population, and the prognostic value of sleep. The available literature on individuals in an unresponsive wakefulness syndrome (UWS) or minimally conscious state (MCS) following traumatic or nontraumatic severe brain injury is reviewed. We can distinguish patients with different levels of consciousness by studying sleep patients with DOC. Most MCS patients have sleep and wake alternations, sleep spindles and rapid eye movement (REM) sleep, while UWS patients have few EEG changes. A large number of sleep spindles and organized sleep-wake patterns predict better clinical outcomes. It is expected that this review will promote our understanding of sleep EEG in DOC.

Transferring Structured Knowledge in Unsupervised Domain Adaptation of a Sleep Staging Network

Automatic sleep staging based on deep learning (DL) has been attracting attention for analyzing sleep quality and determining treatment effects. It is challenging to acquire long-term sleep data from numerous subjects and manually labeling them even though most DL-based models are trained using large-scale sleep data to provide state-of-the-art performance. One way to overcome this data shortage is to create a pre-trained network with an existing large-scale dataset (source domain) that is applicable to small cohorts of datasets (target domain); however, discrepancies in data distribution between the domains prevent successful refinement of this approach. In this paper, we propose an unsupervised domain adaptation method for sleep staging networks to reduce discrepancies by realigning the domains in the same space and producing domain-invariant features. Specifically, in addition to a classical domain discriminator, we introduce local dis-criminators-subject and stage-to maintain the intrinsic structure of sleep data to decrease local misalignments while using adversarial learning to play a minimax game between the feature extractor and discriminators. Moreover, we present several optimization schemes during training because the conventional adversarial learning is not effective to our training scheme. We evaluate the performance of the proposed method by examining the staging performances of a baseline network compared with direct transfer (DT) learning in various conditions. The experimental results demonstrate that the proposed domain adaptation significantly improves the performance though it needs no labeled sleep data in target domain.

Automatic analysis of single-channel sleep EEG in a large spectrum of sleep disorders

STUDY OBJECTIVES

To assess the performance of the single-channel automatic sleep staging (AS) software ASEEGA in adult patients diagnosed with various sleep disorders.

METHODS

Sleep recordings were included of 95 patients (38 women, 40.5 ± 13.7 years) diagnosed with insomnia (n = 23), idiopathic hypersomnia (n = 24), narcolepsy (n = 24), and obstructive sleep apnea (n = 24). Visual staging (VS) was performed by two experts (VS1 and VS2) according to the American Academy of Sleep Medicine rules. AS was based on the analysis of a single electroencephalogram channel (Cz-Pz), without any information from electro-oculography nor electromyography. The epoch-by-epoch agreement (concordance and Conger's coefficient [κ]) was compared pairwise (VS1-VS2, AS-VS1, AS-VS2) and between AS and consensual VS. Sleep parameters were also compared.

RESULTS

The pairwise agreements were: between AS and VS1, 78.6% (κ = 0.70); AS and VS2, 75.0% (0.65); and VS1 and VS2, 79.5% (0.72). Agreement between AS and consensual VS was 85.6% (0.80), with the following distribution: insomnia 85.5% (0.80), narcolepsy 83.8% (0.78), idiopathic hypersomnia 86.1% (0.68), and obstructive sleep disorder 87.2% (0.82). A significant low-amplitude scorer effect was observed for most sleep parameters, not always driven by the same scorer. Hypnograms obtained with AS and VS exhibited very close sleep organization, except for 80% of rapid eye movement sleep onset in the group diagnosed with narcolepsy missed by AS.

CONCLUSIONS

Agreement between AS and VS in sleep disorders is comparable to that reported in healthy individuals and to interexpert agreement in patients. ASEEGA could therefore be considered as a complementary sleep stage scoring tool in clinical practice, after improvement of rapid eye movement sleep onset detection.

A deep learning algorithm based on 1D CNN-LSTM for automatic sleep staging

BACKGROUND

Sleep staging is an important part of sleep research. Traditional automatic sleep staging based on machine learning requires extensive feature extraction and selection.

OBJECTIVE

This paper proposed a deep learning algorithm without feature extraction based on one-dimensional convolutional neural network and long short-term memory.

METHODS

The algorithm can automatically divide sleep into 5 phases including awake period, non-rapid eye movement sleep period (N1 ∼ N3) and rapid eye movement using the electroencephalogram signals. The raw signal was processed by the wavelet transform. Then, the processed signal was directly input into the deep learning algorithm to obtain the staging result.

RESULTS

The accuracy of staging is 93.47% using the Fpz-Cz electroencephalogram signal. When using the Fpz-Cz and electroencephalogram signal, the algorithm can obtain the highest accuracy of 94.15%.

CONCLUSION

These results show that this algorithm is suitable for different physiological signals and can realize end-to-end automatic sleep staging without any manual feature extraction.

MetaSleepLearner: A Pilot Study on Fast Adaptation of Bio-Signals-Based Sleep Stage Classifier to New Individual Subject Using Meta-Learning

Identifying bio-signals based-sleep stages requires time-consuming and tedious labor of skilled clinicians. Deep learning approaches have been introduced in order to challenge the automatic sleep stage classification conundrum. However, the difficulties can be posed in replacing the clinicians with the automatic system due to the differences in many aspects found in individual bio-signals, causing the inconsistency in the performance of the model on every incoming individual. Thus, we aim to explore the feasibility of using a novel approach, capable of assisting the clinicians and lessening the workload. We propose the transfer learning framework, entitled MetaSleepLearner, based on Model Agnostic Meta-Learning (MAML), in order to transfer the acquired sleep staging knowledge from a large dataset to new individual subjects (source code is available at https://github.com/IoBT-VISTEC/MetaSleepLearner). The framework was demonstrated to require the labelling of only a few sleep epochs by the clinicians and allow the remainder to be handled by the system. Layer-wise Relevance Propagation (LRP) was also applied to understand the learning course of our approach. In all acquired datasets, in comparison to the conventional approach, MetaSleepLearner achieved a range of 5.4% to 17.7% improvement with statistical difference in the mean of both approaches. The illustration of the model interpretation after the adaptation to each subject also confirmed that the performance was directed towards reasonable learning. MetaSleepLearner outperformed the conventional approaches as a result from the fine-tuning using the recordings of both healthy subjects and patients. This is the first work that investigated a non-conventional pre-training method, MAML, resulting in a possibility for human-machine collaboration in sleep stage classification and easing the burden of the clinicians in labelling the sleep stages through only several epochs rather than an entire recording.

Automatic Sleep Stage Classification Using Temporal Convolutional Neural Network and New Data Augmentation Technique from Raw Single-Channel EEG

BACKGROUND AND OBJECTIVE

This paper presents a new framework for automatic classification of sleep stages using a deep learning algorithm from single-channel EEG signals. Each segmented EEG signal appended with its label of stages is fed into a deep learning model to create an automatic sleep stage classification. This is one of the most important problems that is critical to the realization of monitoring patients with sleep disorder.

METHODS

In the present study, a neural network architecture is introduced utilizing Convolutional Neural Networks (CNNs) to extract features, followed by Temporal Convolutional Neural Network to extract the temporal features from the extracted features vector of CNN. Finally, the performance of our model is improved by a Conditional Random Field layer. We also employed a new data augmentation technique to enhance the CNNs training which has auxiliary effects.

RESULTS

We evaluated our model by two different single-channel EEG signals (i.e., Fpz-Cz and Pz-Oz EEG channels) from two public sleep datasets, named Sleep-EDF-2013 and Sleep-EDF-2018. The evaluation results on both datasets showed that our model obtains the best total accuracy and kappa score (EDF-2013: 85.39%- 0.80, EDF-2018: 82.46%- 0.76) compared to the state-of-the-art methods.

CONCLUSIONS

This study will possibly allow us to have a wearable sleep monitoring system with a single-channel EEG. Also, unlike hand-crafted features methods, our model finds its own patterns through training epochs, and therefore, it may minimize engineering bias.

Towards More Accurate Automatic Sleep Staging via Deep Transfer Learning

BACKGROUND

Despite recent significant progress in the development of automatic sleep staging methods, building a good model still remains a big challenge for sleep studies with a small cohort due to the data-variability and data-inefficiency issues. This work presents a deep transfer learning approach to overcome these issues and enable transferring knowledge from a large dataset to a small cohort for automatic sleep staging.

METHODS

We start from a generic end-to-end deep learning framework for sequence-to-sequence sleep staging and derive two networks as the means for transfer learning. The networks are first trained in the source domain (i.e. the large database). The pretrained networks are then finetuned in the target domain (i.e. the small cohort) to complete knowledge transfer. We employ the Montreal Archive of Sleep Studies (MASS) database consisting of 200 subjects as the source domain and study deep transfer learning on three different target domains: the Sleep Cassette subset and the Sleep Telemetry subset of the Sleep-EDF Expanded database, and the Surrey-cEEGrid database. The target domains are purposely adopted to cover different degrees of data mismatch to the source domains.

RESULTS

Our experimental results show significant performance improvement on automatic sleep staging on the target domains achieved with the proposed deep transfer learning approach.

CONCLUSIONS

These results suggest the efficacy of the proposed approach in addressing the above-mentioned data-variability and data-inefficiency issues.

SIGNIFICANCE

As a consequence, it would enable one to improve the quality of automatic sleep staging models when the amount of data is relatively small.¹¹The source code and the pretrained models are published at https://github.com/pquochuy/sleep_transfer_learning.

An Attention-Based Deep Learning Approach for Sleep Stage Classification With Single-Channel EEG

Automatic sleep stage mymargin classification is of great importance to measure sleep quality. In this paper, we propose a novel attention-based deep learning architecture called AttnSleep to classify sleep stages using single channel EEG signals. This architecture starts with the feature extraction module based on multi-resolution convolutional neural network (MRCNN) and adaptive feature recalibration (AFR). The MRCNN can extract low and high frequency features and the AFR is able to improve the quality of the extracted features by modeling the inter-dependencies between the features. The second module is the temporal context encoder (TCE) that leverages a multi-head attention mechanism to capture the temporal dependencies among the extracted features. Particularly, the multi-head attention deploys causal convolutions to model the temporal relations in the input features. We evaluate the performance of our proposed AttnSleep model using three public datasets. The results show that our AttnSleep outperforms state-of-the-art techniques in terms of different evaluation metrics. Our source codes, experimental data, and supplementary materials are available at https://github.com/emadeldeen24/AttnSleep.

Automatic sleep stage classification with deep residual networks in a mixed-cohort setting

STUDY OBJECTIVES

Sleep stage scoring is performed manually by sleep experts and is prone to subjective interpretation of scoring rules with low intra- and interscorer reliability. Many automatic systems rely on few small-scale databases for developing models, and generalizability to new datasets is thus unknown. We investigated a novel deep neural network to assess the generalizability of several large-scale cohorts.

METHODS

A deep neural network model was developed using 15,684 polysomnography studies from five different cohorts. We applied four different scenarios: (1) impact of varying timescales in the model; (2) performance of a single cohort on other cohorts of smaller, greater, or equal size relative to the performance of other cohorts on a single cohort; (3) varying the fraction of mixed-cohort training data compared with using single-origin data; and (4) comparing models trained on combinations of data from 2, 3, and 4 cohorts.

RESULTS

Overall classification accuracy improved with increasing fractions of training data (0.25%: 0.782 ± 0.097, 95% CI [0.777-0.787]; 100%: 0.869 ± 0.064, 95% CI [0.864-0.872]), and with increasing number of data sources (2: 0.788 ± 0.102, 95% CI [0.787-0.790]; 3: 0.808 ± 0.092, 95% CI [0.807-0.810]; 4: 0.821 ± 0.085, 95% CI [0.819-0.823]). Different cohorts show varying levels of generalization to other cohorts.

CONCLUSIONS

Automatic sleep stage scoring systems based on deep learning algorithms should consider as much data as possible from as many sources available to ensure proper generalization. Public datasets for benchmarking should be made available for future research.

Deep Learning in Automatic Sleep Staging With a Single Channel Electroencephalography

This study centers on automatic sleep staging with a single channel electroencephalography (EEG), with some significant findings for sleep staging. In this study, we proposed a deep learning-based network by integrating attention mechanism and bidirectional long short-term memory neural network (AT-BiLSTM) to classify wakefulness, rapid eye movement (REM) sleep and non-REM (NREM) sleep stages N1, N2 and N3. The AT-BiLSTM network outperformed five other networks and achieved an accuracy of 83.78%, a Cohen's kappa coefficient of 0.766 and a macro F1-score of 82.14% on the PhysioNet Sleep-EDF Expanded dataset, and an accuracy of 81.72%, a Cohen's kappa coefficient of 0.751 and a macro F1-score of 80.74% on the DREAMS Subjects dataset. The proposed AT-BiLSTM network even achieved a higher accuracy than the existing methods based on traditional feature extraction. Moreover, better performance was obtained by the AT-BiLSTM network with the frontal EEG derivations than with EEG channels located at the central, occipital or parietal lobe. As EEG signal can be easily acquired using dry electrodes on the forehead, our findings might provide a promising solution for automatic sleep scoring without feature extraction and may prove very useful for the screening of sleep disorders.

STQS: Interpretable multi-modal Spatial-Temporal-seQuential model for automatic Sleep scoring

Sleep scoring is an important step for the detection of sleep disorders and usually performed by visual analysis. Since manual sleep scoring is time consuming, machine-learning based approaches have been proposed. Though efficient, these algorithms are black-box in nature and difficult to interpret by clinicians. In this paper, we propose a deep learning architecture for multi-modal sleep scoring, investigate the model's decision making process, and compare the model's reasoning with the annotation guidelines in the AASM manual. Our architecture, called STQS, uses convolutional neural networks (CNN) to automatically extract spatio-temporal features from 3 modalities (EEG, EOG and EMG), a bidirectional long short-term memory (Bi-LSTM) to extract sequential information, and residual connections to combine spatio-temporal and sequential features. We evaluated our model on two large datasets, obtaining an accuracy of 85% and 77% and a macro F1 score of 79% and 73% on SHHS and an in-house dataset, respectively. We further quantify the contribution of various architectural components and conclude that adding LSTM layers improves performance over a spatio-temporal CNN, while adding residual connections does not. Our interpretability results show that the output of the model is well aligned with AASM guidelines, and therefore, the model's decisions correspond to domain knowledge. We also compare multi-modal models and single-channel models and suggest that future research should focus on improving multi-modal models.

Learning fine-grained estimation of physiological states from coarse-grained labels by distribution restoration

Due to its importance in clinical science, the estimation of physiological states (e.g., the severity of pathological tremor) has aroused growing interest in machine learning community. While the physiological state is a continuous variable, its continuity is lost when the physiological state is quantized into a few discrete classes during recording and labeling. The discreteness introduces misalignment between the true value and its label, meaning that these labels are unfortunately imprecise and coarse-grained. Most previous work did not consider the inaccuracy and directly utilized the coarse labels to train the machine learning algorithms, whose predictions are also coarse-grained. In this work, we propose to learn a precise, fine-grained estimation of physiological states using these coarse-grained ground truths. Established on mathematical rigorous proof, we utilize imprecise labels to restore the probabilistic distribution of precise labels in an approximate order-preserving fashion, then the deep neural network learns from this distribution and offers fine-grained estimation. We demonstrate the effectiveness of our approach in assessing the pathological tremor in Parkinson's Disease and estimating the systolic blood pressure from bioelectrical signals.

Automated Detection of Sleep Stages Using Deep Learning Techniques: A Systematic Review of the Last Decade (2010–2020)

Sleep is vital for one’s general well-being, but it is often neglected, which has led to an increase in sleep disorders worldwide. Indicators of sleep disorders, such as sleep interruptions, extreme daytime drowsiness, or snoring, can be detected with sleep analysis. However, sleep analysis relies on visuals conducted by experts, and is susceptible to inter- and intra-observer variabilities. One way to overcome these limitations is to support experts with a programmed diagnostic tool (PDT) based on artificial intelligence for timely detection of sleep disturbances. Artificial intelligence technology, such as deep learning (DL), ensures that data are fully utilized with low to no information loss during training. This paper provides a comprehensive review of 36 studies, published between March 2013 and August 2020, which employed DL models to analyze overnight polysomnogram (PSG) recordings for the classification of sleep stages. Our analysis shows that more than half of the studies employed convolutional neural networks (CNNs) on electroencephalography (EEG) recordings for sleep stage classification and achieved high performance. Our study also underscores that CNN models, particularly one-dimensional CNN models, are advantageous in yielding higher accuracies for classification. More importantly, we noticed that EEG alone is not sufficient to achieve robust classification results. Future automated detection systems should consider other PSG recordings, such as electroencephalogram (EEG), electrooculogram (EOG), and electromyogram (EMG) signals, along with input from human experts, to achieve the required sleep stage classification robustness. Hence, for DL methods to be fully realized as a practical PDT for sleep stage scoring in clinical applications, inclusion of other PSG recordings, besides EEG recordings, is necessary. In this respect, our report includes methods published in the last decade, underscoring the use of DL models with other PSG recordings, for scoring of sleep stages.

Multi-Branch Convolutional Neural Network for Automatic Sleep Stage Classification with Embedded Stage Refinement and Residual Attention Channel Fusion

Automatic sleep stage classification of multi-channel sleep signals can help clinicians efficiently evaluate an individual's sleep quality and assist in diagnosing a possible sleep disorder. To obtain accurate sleep classification results, the processing flow of results from signal preprocessing and machine-learning-based classification is typically employed. These classification results are refined based on sleep transition rules. Neural networks-i.e., machine learning algorithms-are powerful at solving classification problems. Some methods apply them to the first two processes above; however, the refinement process continues to be based on traditional methods. In this study, the sleep stage refinement process was incorporated into the neural network model to form real end-to-end processing. In addition, for multi-channel signals, the multi-branch convolutional neural network was combined with a proposed residual attention method. This approach further improved the model classification accuracy. The proposed method was evaluated on the Sleep-EDF Expanded Database (Sleep-EDFx) and University College Dublin Sleep Apnea Database (UCDDB). It achieved respective accuracy rates of 85.7% and 79.4%. The results also showed that sleep stage refinement based on a neural network is more effective than the traditional refinement method. Moreover, the proposed residual attention method was determined to have a more robust channel-information fusion ability than the respective average and concatenation methods.

Automatic sleep scoring: A deep learning architecture for multi-modality time series

BACKGROUND

Sleep scoring is an essential but time-consuming process, and therefore automatic sleep scoring is crucial and urgent to help address the growing unmet needs for sleep research. This paper aims to develop a versatile deep-learning architecture to automate sleep scoring using raw polysomnography recordings.

METHOD

The model adopts a linear function to address different numbers of inputs, thereby extending model applications. Two-dimensional convolution neural networks are used to learn features from multi-modality polysomnographic signals, a "squeeze and excitation" block to recalibrate channel-wise features, together with a long short-term memory module to exploit long-range contextual relation. The learnt features are finally fed to the decision layer to generate predictions for sleep stages.

RESULT

Model performance is evaluated on three public datasets. For all tasks with different available channels, our model achieves outstanding performance not only on healthy subjects but even on patients with sleep disorders (SHHS: Acc-0.87, K-0.81; ISRUC: Acc-0.86, K-0.82; Sleep-EDF: Acc-0.86, K-0.81). The highest classification accuracy is achieved by a fusion of multiple polysomnographic signals.

COMPARISON

Compared to state-of-the-art methods that use the same dataset, the proposed model achieves a comparable or better performance, and exhibits low computational cost.

CONCLUSIONS

The model demonstrates its transferability among different datasets, without changing model architecture or hyper-parameters across tasks. Good model transferability promotes the application of transfer learning on small group studies with mismatched channels. Due to demonstrated availability and versatility, the proposed method can be integrated with diverse polysomnography systems, thereby facilitating sleep monitoring in clinical or routine care.

End-to-End Automatic Sleep Stage Classification Using Spectral-Temporal Sleep Features

Sleep disorder is one of many neurological diseases that can affect greatly the quality of daily life. It is very burdensome to manually classify the sleep stages to detect sleep disorders. Therefore, the automatic sleep stage classification techniques are needed. However, the previous automatic sleep scoring methods using raw signals are still low classification performance. In this study, we proposed an end-to-end automatic sleep staging framework based on optimal spectral-temporal sleep features using a sleep-edf dataset. The input data were modified using a bandpass filter and then applied to a convolutional neural network model. For five sleep stage classification, the classification performance 85.6% and 91.1% using the raw input data and the proposed input, respectively. This result also shows the highest performance compared to conventional studies using the same dataset. The proposed framework has shown high performance by using optimal features associated with each sleep stage, which may help to find new features in the automatic sleep stage method.Clinical Relevance- The proposed framework would help to diagnose sleep disorders such as insomnia by improving sleep stage classification performance.

Making Sense of Sleep

Traditionally, sleep monitoring has been performed in hospital or clinic environments, requiring complex and expensive equipment set-up and expert scoring. Wearable devices increasingly provide a viable alternative for sleep monitoring and are able to collect movement and heart rate (HR) data. In this work, we present a set of algorithms for sleep-wake and sleep-stage classification based upon actigraphy and cardiac sensing amongst 1,743 participants. We devise movement and cardiac features that could be extracted from research-grade wearable sensors and derive models and evaluate their performance in the largest open-access dataset for human sleep science. Our results demonstrated that neural network models outperform traditional machine learning methods and heuristic models for both sleep-wake and sleep-stage classification. Convolutional neural networks (CNNs) and long-short term memory (LSTM) networks were the best performers for sleep-wake and sleep-stage classification, respectively. Using SHAP (SHapley Additive exPlanation) with Random Forest we identified that frequency features from cardiac sensors are critical to sleep-stage classification. Finally, we introduced an ensemble-based approach to sleep-stage classification, which outperformed all other baselines, achieving an accuracy of 78.2% and F1 score of 69.8% on the classification task for three sleep stages. Together, this work represents the first systematic multimodal evaluation of sleep-wake and sleep-stage classification in a large, diverse population. Alongside the presentation of an accurate sleep-stage classification approach, the results highlight multimodal wearable sensing approaches as scalable methods for accurate sleep-classification, providing guidance on optimal algorithm deployment for automated sleep assessment. The code used in this study can be found online at: https://github.com/bzhai/multimodal_sleep_stage_benchmark.git

Neonatal sleep stage identification using long short-term memory learning system

Neonatal sleep analysis at the neonatal intensive care units (NICU) is critical for the diagnosis of any brain growth risks during the early stages of life. In this paper, an investigation is carried out on the use of a long short-term memory (LSTM) learning system in automatic sleep stage scoring in neonates. The developed algorithm automatically classifies sleep stages based on inputs from a single channel EEG recording. Up to this date, only a single study have developed an approach for automatic sleep stage scoring in neonatal sleep signals using deep neural network (DNN). A total of 5095 sleep stages signals acquired from EEG recordings of the University of Pittsburgh are used in this study. The sleep stages are annotated by a medical doctor from the Pediatric Neurology Department of Case Western Reserve University for three neonatal sleep stages including the awake (W), active sleep (AS), and quiet sleep (QS) stages on every 60-s epoch. The signals are pre-processed through normalization and filtering. The resulted signals are divided following 4-, 6-, and 10-fold cross-validation schemes. The training and classification process is done using a bi-directional LSTM network classifier built with pre-defined training parameters. At the end, the developed algorithm is evaluated along with a complete summary table that reports the results of this study and other state-of-the-art studies. The current study achieved high levels of Cohen's kappa (κ), accuracy, and F1 score with 91.37%, 96.81%, and 94.43%, respectively. Based on the confusion matrix, the overall true positives percentage reached 95.21%. The developed algorithm gave promising results in automatic sleep stage scoring in neonatal sleep signals. Future work include LSTM architecture and training parameters improvements to enhance the overall accuracy of the classifier.

A Systematic Review of Closed-Loop Feedback Techniques in Sleep Studies-Related Issues and Future Directions

Advances in computer processing technology have enabled researchers to analyze real-time brain activity and build real-time closed-loop paradigms. In many fields, the effectiveness of these closed-loop protocols has proven to be better than that of the simple open-loop paradigms. Recently, sleep studies have attracted much attention as one possible application of closed-loop paradigms. To date, several studies that used closed-loop paradigms have been reported in the sleep-related literature and recommend a closed-loop feedback system to enhance specific brain activity during sleep, which leads to improvements in sleep's effects, such as memory consolidation. However, to the best of our knowledge, no report has reviewed and discussed the detailed technical issues that arise in designing sleep closed-loop paradigms. In this paper, we reviewed the most recent reports on sleep closed-loop paradigms and offered an in-depth discussion of some of their technical issues. We found 148 journal articles strongly related with 'sleep and stimulation' and reviewed 20 articles on closed-loop feedback sleep studies. We focused on human sleep studies conducting any modality of feedback stimulation. Then we introduced the main component of the closed-loop system and summarized several open-source libraries, which are widely used in closed-loop systems, with step-by-step guidelines for closed-loop system implementation for sleep. Further, we proposed future directions for sleep research with closed-loop feedback systems, which provide some insight into closed-loop feedback systems.

Long Short-Term Memory Networks for Unconstrained Sleep Stage Classification Using Polyvinylidene Fluoride Film Sensor

Sleep stage scoring is the first step towards quantitative analysis of sleep using polysomnography (PSG) recordings. However, although PSG is a gold standard method for assessing sleep, it is obtrusive and difficult to apply for long-term sleep monitoring. Further, because human experts manually classify sleep stages, it is time-consuming and exhibits inter-rater variability. Therefore, this article proposes a long short-term memory (LSTM) model for automatic sleep stage scoring using a polyvinylidene fluoride (PVDF) film sensor that can provide unconstrained long-term physiological monitoring. Signals were recorded using a PVDF sensor during PSG. From 60 recordings, 30 were used for training, 10 for validation, and 20 for testing. Sixteen parameters, including movement, respiration-related, and heart rate variability, were extracted from the recorded signals and then normalized. From the selected LSTM architecture, four sleep stage classification performances were evaluated for a test dataset and the results were compared with those of conventional machine learning methods. According to epoch-by-epoch (30 s) analysis, the classification performance for the four sleep stages had an average accuracy of 73.9% and a Cohen's kappa coefficient of 0.55. When compared with other machine learning methods, the proposed method achieved the highest classification performance. The use of LSTM networks with the PVDF film sensor has potential for facilitating automatic sleep scoring, and it can be applied for long-term sleep monitoring at home.

A convolutional neural network outperforming state-of-the-art sleep staging algorithms for both preterm and term infants

OBJECTIVE

To classify sleep states using electroencephalogram (EEG) that reliably works over a wide range of preterm ages, as well as term age.

APPROACH

A convolutional neural network is developed to perform 2- and 4-class sleep classification in neonates. The network takes as input an 8-channel 30 s EEG segment and outputs the sleep state probabilities. Apart from simple downsampling of the input and smoothing of the output, the suggested network is an end-to-end algorithm that avoids the need for hand-crafted feature selection or complex pre/post processing steps. To train and test this method, 113 EEG recordings from 42 infants are used.

MAIN RESULTS

For quiet sleep detection (the 2-class problem), mean kappa between the network estimate and the ground truth annotated by EEG human experts is 0.76. The sensitivity and specificity are 90% and 88%, respectively. For 4-class classification, mean kappa is 0.64. The averaged sensitivity and specificity (1 versus all) respectively equal 72% and 91%. The results outperform current state-of-the-art methods for which kappa ranges from 0.66 to 0.70 in preterm and from 0.51 to 0.61 in term infants, based on training and testing using the same database.

SIGNIFICANCE

The proposed method has the highest reported accuracy for EEG sleep state classification for both preterm and term age neonates.

Orthogonal convolutional neural networks for automatic sleep stage classification based on single-channel EEG

BACKGROUND AND OBJECTIVE

In recent years, several automatic sleep stage classification methods based on convolutional neural networks (CNN) by learning hierarchical feature representation automatically from raw EEG data have been proposed. However, the state-of-the-art of such methods are quite complex. Using a simple CNN architecture to classify sleep stages is important for portable sleep devices. In addition, employing CNNs to learn rich and diverse representations remains a challenge. Therefore, we propose a novel CNN model for sleep stage classification.

METHODS

Generally, EEG signals are better described in the frequency domain; thus, we convert EEG data to a time-frequency representation via Hilbert-Huang transform. To learn rich and effective feature representations, we propose an orthogonal convolutional neural network (OCNN). First, we construct an orthogonal initialization of weights. Second, to avoid destroying the orthogonality of the weights in the training process, orthogonality regularizations are proposed to maintain the orthogonality of weights. Simultaneously, a squeeze-and-excitation (SE) block is employed to perform feature recalibration across different channels.

RESULTS

The proposed method achieved a total classification accuracy of 88.4% and 87.6% on two public datasets, respectively. The classification performances of different convolutional neural networks models were compared to that of the proposed method. The experiment results demonstrated that the proposed method is effective for sleep stage classification.

CONCLUSIONS

Experiment results indicate that the proposed OCNN can learn rich and diverse feature representations from time-frequency images of EEG data, which is important for deep learning. In addition, the proposed orthogonality regularization is simple and can be easily adapted to other architectures.

Texture Classification Using Spectral Entropy of Acoustic Signal Generated by a Human Echolocator

Human echolocation is a biological process wherein the human emits a punctuated acoustic signal, and the ear analyzes the echo in order to perceive the surroundings. The peculiar acoustic signal is normally produced by clicking inside the mouth. This paper utilized this unique acoustic signal from a human echolocator as a source of transmitted signal in a synthetic human echolocation technique. Thus, the aim of the paper was to extract information from the echo signal and develop a classification scheme to identify signals reflected from different textures at various distance. The scheme was based on spectral entropy extracted from Mel-scale filtering output in the Mel-frequency cepstrum coefficient of a reflected echo signal. The classification process involved data mining, features extraction, clustering, and classifier validation. The reflected echo signals were obtained via an experimental setup resembling a human echolocation scenario, configured for synthetic data collection. Unlike in typical speech signals, extracted entropy from the formant characteristics was likely not visible for the human mouth-click signals. Instead, multiple peak spectral features derived from the synthesis signal of the mouth-click were assumed as the entropy obtained from the Mel-scale filtering output. To realize the classification process, K-means clustering and K-nearest neighbor processes were employed. Moreover, the impacts of sound propagation toward the extracted spectral entropy used in the classification outcome were also investigated. The outcomes of the classifier performance herein indicated that spectral entropy is essential for human echolocation.