ISRUC-Sleep: A comprehensive public dataset for sleep researchers

Jumping Knowledge Based Spatial-temporal Graph Convolutional Networks for Automatic Sleep Stage Classification

A novel jumping knowledge spatial-temporal graph convolutional network (JK-STGCN) is proposed in this paper to classify sleep stages. Based on this method, different types of multi-channel bio-signals, including electroencephalography (EEG), electromyogram (EMG), electrooculogram (EOG), and electrocardiogram (ECG) are utilized to classify sleep stages, after extracting features by a standard convolutional neural network (CNN) named FeatureNet. Intrinsic connections among different bio-signal channels from the identical epoch and neighboring epochs can be obtained through two adaptive adjacency matrices learning methods. A jumping knowledge spatial-temporal graph convolution module helps the JK-STGCN model to extract spatial features from the graph convolutions efficiently and temporal features are extracted from its common standard convolutions to learn the transition rules among sleep stages. Experimental results on the ISRUC-S3 dataset showed that the overall accuracy achieved 0.831 and the F1-score and Cohen kappa reached 0.814 and 0.782, respectively, which are the competitive classification performance with the state-of-the-art baselines. Further experiments on the ISRUC-S3 dataset are also conducted to evaluate the execution efficiency of the JK-STGCN model. The training time on 10 subjects is 2621s and the testing time on 50 subjects is 6.8s, which indicates its highest calculation speed compared with the existing high-performance graph convolutional networks and U-Net architecture algorithms. Experimental results on the ISRUC-S1 dataset also demonstrate its generality, whose accuracy, F1-score, and Cohen kappa achieve 0.820, 0.798, and 0.767 respectively.

Automatic sleep stage classification based on two-channel EOG and one-channel EMG

OBJECTIVE

The sleep monitoring with Polysomnography (PSG) severely degrades the sleep quality. In order to reduce the load of sleep monitoring, an approach to automatic sleep stage classification without electroencephalogram (EEG) was proposed.

APPROACH

Totally 124 records from the public dataset ISRUC-Sleep with AASM standard were used, in which only 10 records were from the healthy group while the rest ones were from sleep disorder groups. The 124 records were collected from 116 subjects (8 subjects with two records for each subject, others with one record per subject) with their ages range in [20, 85] years. Totally 108 features were extracted from two-channel electrooculogram (EOG), and 6 features were extracted from one-channel electromyogram (EMG). A novel 'quasi-normalization' method was proposed and used for feature normalization. Then the random forest (RF) was used to classify five stages, including wakefulness, REM sleep, N1 sleep, N2 sleep and N3 sleep.

MAIN RESULTS

Using 114 normalized features from the combination of EOG (108 features) and EMG (6 features), the Cohen's kappa coefficient was 0.749 and the accuracy was 80.8% by leave-one-out cross-validation (LOOCV). As a reference for AASM standard using computer assisted method, the Cohen's kappa coefficient was 0.801 and the accuracy was 84.7% for the same dataset based on 438 normalized features from the combination of EEG (324 features), EOG (108 features) and EMG (6 features).

SIGNIFICANCE

The combination of EOG and EMG can reduce the load of sleep monitoring, and achieves comparable performances with the "gold standard" signals of EEG, EOG and EMG on sleep stage classification.

An Attention-Guided Spatiotemporal Graph Convolutional Network for Sleep Stage Classification

Sleep staging has been widely used as an approach in sleep diagnoses at sleep clinics. Graph neural network (GNN)-based methods have been extensively applied for automatic sleep stage classifications with significant results. However, the existing GNN-based methods rely on a static adjacency matrix to capture the features of the different electroencephalogram (EEG) channels, which cannot grasp the information of each electrode. Meanwhile, these methods ignore the importance of spatiotemporal relations in classifying sleep stages. In this work, we propose a combination of a dynamic and static spatiotemporal graph convolutional network (ST-GCN) with inter-temporal attention blocks to overcome two shortcomings. The proposed method consists of a GCN with a CNN that takes into account the intra-frame dependency of each electrode in the brain region to extract spatial and temporal features separately. In addition, the attention block was used to capture the long-range dependencies between the different electrodes in the brain region, which helps the model to classify the dynamics of each sleep stage more accurately. In our experiments, we used the sleep-EDF and the subgroup III of the ISRUC-SLEEP dataset to compare with the most current methods. The results show that our method performs better in accuracy from 4.6% to 5.3%, in Kappa from 0.06 to 0.07, and in macro-F score from 4.9% to 5.7%. The proposed method has the potential to be an effective tool for improving sleep disorders.

Automated Classification of Sleep Stages Using Single-Channel EEG A Machine Learning-Based Method

The main contribution of this paper is to present a novel approach for classifying the sleep stages based on optimal feature selection with ensemble learning stacking model using single-channel EEG signals.To find the suitable features from extracted feature vector, we obtained the ReliefF (ReF), Fisher Score (FS) and Online Stream Feature Selection (OSFS) selection algorithms.The proposed research work was performed on two different subgroups of sleep data of ISRUC-Sleep dataset. The experimental results of the proposed methodology signify that single-channel of EEG signal superior to other machine learning classification models with overall accuracies of 97.93%, 97%, and 95.96% using ISRUC-Sleep subgroup-I (SG-I) data and similarly the proposed model achieved an overall accuracies of 98.16%, 98.78%, and 95.26% using ISRUC-Sleep subgroup-III (SG-III) data with FS, ReF and OSFS respectively.

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.

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 Clinical Decision Support System for Sleep Staging Tasks With Explanations From Artificial Intelligence: User-Centered Design and Evaluation Study

Background

Despite the unprecedented performance of deep learning algorithms in clinical domains, full reviews of algorithmic predictions by human experts remain mandatory. Under these circumstances, artificial intelligence (AI) models are primarily designed as clinical decision support systems (CDSSs). However, from the perspective of clinical practitioners, the lack of clinical interpretability and user-centered interfaces hinders the adoption of these AI systems in practice.

Objective

This study aims to develop an AI-based CDSS for assisting polysomnographic technicians in reviewing AI-predicted sleep staging results. This study proposed and evaluated a CDSS that provides clinically sound explanations for AI predictions in a user-centered manner.

Methods

Our study is based on a user-centered design framework for developing explanations in a CDSS that identifies why explanations are needed, what information should be contained in explanations, and how explanations can be provided in the CDSS. We conducted user interviews, user observation sessions, and an iterative design process to identify three key aspects for designing explanations in the CDSS. After constructing the CDSS, the tool was evaluated to investigate how the CDSS explanations helped technicians. We measured the accuracy of sleep staging and interrater reliability with macro-F1 and Cohen κ scores to assess quantitative improvements after our tool was adopted. We assessed qualitative improvements through participant interviews that established how participants perceived and used the tool.

Results

The user study revealed that technicians desire explanations that are relevant to key electroencephalogram (EEG) patterns for sleep staging when assessing the correctness of AI predictions. Here, technicians wanted explanations that could be used to evaluate whether the AI models properly locate and use these patterns during prediction. On the basis of this, information that is closely related to sleep EEG patterns was formulated for the AI models. In the iterative design phase, we developed a different visualization strategy for each pattern based on how technicians interpreted the EEG recordings with these patterns during their workflows. Our evaluation study on 9 polysomnographic technicians quantitatively and qualitatively investigated the helpfulness of the tool. For technicians with <5 years of work experience, their quantitative sleep staging performance improved significantly from 56.75 to 60.59 with a P value of .05. Qualitatively, participants reported that the information provided effectively supported them, and they could develop notable adoption strategies for the tool.

Conclusions

Our findings indicate that formulating clinical explanations for automated predictions using the information in the AI with a user-centered design process is an effective strategy for developing a CDSS for sleep staging.

Multi-View Spatial-Temporal Graph Convolutional Networks With Domain Generalization for Sleep Stage Classification

Sleep stage classification is essential for sleep assessment and disease diagnosis. Although previous attempts to classify sleep stages have achieved high classification performance, several challenges remain open: 1) How to effectively utilize time-varying spatial and temporal features from multi-channel brain signals remains challenging. Prior works have not been able to fully utilize the spatial topological information among brain regions. 2) Due to the many differences found in individual biological signals, how to overcome the differences of subjects and improve the generalization of deep neural networks is important. 3) Most deep learning methods ignore the interpretability of the model to the brain. To address the above challenges, we propose a multi-view spatial-temporal graph convolutional networks (MSTGCN) with domain generalization for sleep stage classification. Specifically, we construct two brain view graphs for MSTGCN based on the functional connectivity and physical distance proximity of the brain regions. The MSTGCN consists of graph convolutions for extracting spatial features and temporal convolutions for capturing the transition rules among sleep stages. In addition, attention mechanism is employed for capturing the most relevant spatial-temporal information for sleep stage classification. Finally, domain generalization and MSTGCN are integrated into a unified framework to extract subject-invariant sleep features. Experiments on two public datasets demonstrate that the proposed model outperforms the state-of-the-art baselines.

Classification of Sleep Apnea Based on Sub-Band Decomposition of EEG Signals

To classify between normal and sleep apnea subjects based on sub-band decomposition of electroencephalogram (EEG) signals. This study comprised 159 subjects obtained from the ISRUC (Institute of System and Robotics—University of Coimbra), Sleep-EDF (European Data Format), and CAP (Cyclic Alternating Pattern) Sleep database, which consists of normal and sleep apnea subjects. The wavelet packet decomposition method was incorporated to categorize the EEG signals into five frequency bands, namely, alpha, beta, delta, gamma, and theta. Entropy and energy (non-linear) for all bands was calculated and as a result, 10 features were obtained for each EEG signal. The ratio of EEG bands included four parameters, including heart rate, brain perfusion, neural activity, and synchronization. In this study, a support vector machine with kernels and random forest classifiers was used for classification. The performance measures demonstrated that the improved results were obtained from the support vector machine classifier with a kernel polynomial order 2. The accuracy (90%), sensitivity (100%), and specificity (83%) with 14 features were estimated using the data obtained from ISRUC database. The proposed study is feasible and seems to be accurate in classifying the subjects with sleep apnea based on the extracted features from EEG signals using a support vector machine classifier.

EEG microstate in obstructive sleep apnea patients

Obstructive sleep apnea (OSA) is a common sleep respiratory disease. Previous studies have found that the wakefulness electroencephalogram (EEG) of OSA patients has changed, such as increased EEG power. However, whether the microstates reflecting the transient state of the brain is abnormal is unclear during obstructive hypopnea (OH). We investigated the microstates of sleep EEG in 100 OSA patients. Then correlation analysis was carried out between microstate parameters and EEG markers of sleep disturbance, such as power spectrum, sample entropy and detrended fluctuation analysis (DFA). OSA_OH patients showed that the microstate C increased presence and the microstate D decreased presence compared to OSA_withoutOH patients and controls. The fifth microstate E appeared during N1-OH, but the probability of other microstates transferring to microstate E was small. According to the correlation analysis, OSA_OH patients in N1-OH showed that the microstate D was positively correlated with delta power, and negatively correlated with beta and alpha power; the transition probability of the microstate B → C and E → C was positively correlated with alpha power. In other sleep stages, the microstate parameters were not correlated with power, sample entropy and FDA. We might interpret that the abnormal transition of brain active areas of OSA patients in N1-OH stage leads to abnormal microstates, which might be related to the change of alpha activity in the cortex.

Inter-database validation of a deep learning approach for automatic sleep scoring

STUDY OBJECTIVES

Development of inter-database generalizable sleep staging algorithms represents a challenge due to increased data variability across different datasets. Sharing data between different centers is also a problem due to potential restrictions due to patient privacy protection. In this work, we describe a new deep learning approach for automatic sleep staging, and address its generalization capabilities on a wide range of public sleep staging databases. We also examine the suitability of a novel approach that uses an ensemble of individual local models and evaluate its impact on the resulting inter-database generalization performance.

METHODS

A general deep learning network architecture for automatic sleep staging is presented. Different preprocessing and architectural variant options are tested. The resulting prediction capabilities are evaluated and compared on a heterogeneous collection of six public sleep staging datasets. Validation is carried out in the context of independent local and external dataset generalization scenarios.

RESULTS

Best results were achieved using the CNN_LSTM_5 neural network variant. Average prediction capabilities on independent local testing sets achieved 0.80 kappa score. When individual local models predict data from external datasets, average kappa score decreases to 0.54. Using the proposed ensemble-based approach, average kappa performance on the external dataset prediction scenario increases to 0.62. To our knowledge this is the largest study by the number of datasets so far on validating the generalization capabilities of an automatic sleep staging algorithm using external databases.

CONCLUSIONS

Validation results show good general performance of our method, as compared with the expected levels of human agreement, as well as to state-of-the-art automatic sleep staging methods. The proposed ensemble-based approach enables flexible and scalable design, allowing dynamic integration of local models into the final ensemble, preserving data locality, and increasing generalization capabilities of the resulting system at the same time.

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.

Investigation of low dimensional feature spaces for automatic sleep staging

BACKGROUND

Automatic sleep stage classification depends crucially on the selection of a good set of descriptive features. However, the selection of a feature set with an appropriate low computational cost without compromising classification performance is still a challenge. This study attempts to represent sleep EEG patterns using a minimum number of features, without significant performance loss.

METHODS

Three feature selection algorithms were applied to a high dimensional feature space comprising 84 features. These methods were based on a bootstrapping approach guided by Gini ranking and mutual information between the features. The algorithms were tested on three scalp electroencephalography (EEG) and one ear-EEG datasets. The relationship between the information carried by different features was investigated using mutual information and illustrated by a graphical clustering tool.

RESULTS

The minimum number of features that can represent the whole feature set without performance loss was found to range between 5 and 11 for different datasets. In ear-EEG, 7 features based on Continuous Wavelet Transform (CWT) resulted in similar performance as the whole set whereas in two scalp EEG datasets, the difference between minimal CWT set and the whole set was statistically significant (0.008 and 0.017 difference in average kappa). Features were divided into groups according to the type of information they carry. The group containing relative power features was identified as the most informative feature group in sleep stage classification, whereas the group containing non-linear features was found to be the least informative.

CONCLUSIONS

This study showed that EEG sleep staging can be performed based on a low dimensional feature space without significant decrease in sleep staging performance. This is especially important in the case of wearable devices like ear-EEG where low computational complexity is needed. The division of the feature space into groups of features, and the analysis of the distribution of feature groups for different feature set sizes, is helpful in the selection of an appropriate feature set.

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.

U-Sleep: resilient high-frequency sleep staging

Sleep disorders affect a large portion of the global population and are strong predictors of morbidity and all-cause mortality. Sleep staging segments a period of sleep into a sequence of phases providing the basis for most clinical decisions in sleep medicine. Manual sleep staging is difficult and time-consuming as experts must evaluate hours of polysomnography (PSG) recordings with electroencephalography (EEG) and electrooculography (EOG) data for each patient. Here, we present U-Sleep, a publicly available, ready-to-use deep-learning-based system for automated sleep staging ( sleep.ai.ku.dk ). U-Sleep is a fully convolutional neural network, which was trained and evaluated on PSG recordings from 15,660 participants of 16 clinical studies. It provides accurate segmentations across a wide range of patient cohorts and PSG protocols not considered when building the system. U-Sleep works for arbitrary combinations of typical EEG and EOG channels, and its special deep learning architecture can label sleep stages at shorter intervals than the typical 30 s periods used during training. We show that these labels can provide additional diagnostic information and lead to new ways of analyzing sleep. U-Sleep performs on par with state-of-the-art automatic sleep staging systems on multiple clinical datasets, even if the other systems were built specifically for the particular data. A comparison with consensus-scores from a previously unseen clinic shows that U-Sleep performs as accurately as the best of the human experts. U-Sleep can support the sleep staging workflow of medical experts, which decreases healthcare costs, and can provide highly accurate segmentations when human expertize is lacking.

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.

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.

An Automatic Sleep Stage Classification Algorithm Using Improved Model Based Essence Features

The automatic sleep stage classification technique can facilitate the diagnosis of sleep disorders and release the medical expert from labor-consumption work. In this paper, novel improved model based essence features (IMBEFs) were proposed combining locality energy (LE) and dual state space models (DSSMs) for automatic sleep stage detection on single-channel electroencephalograph (EEG) signals. Firstly, each EEG epoch is decomposed into low-level sub-bands (LSBs) and high-level sub-bands (HSBs) by wavelet packet decomposition (WPD), separately. Then, the DSSMs are estimated by the LSBs and the LE calculation is carried out on HSBs. Thirdly, the IMBEFs extracted from the DSSM and LE are fed into the appropriate classifier for sleep stage classification. The performance of the proposed method was evaluated on three public sleep databases. The experimental results show that under the Rechtschaffen's and Kale's (R&K) standard, the sleep stage classification accuracies of six classes on the Sleep EDF database and the Dreams Subjects database are 92.04% and 78.92%, respectively. Under the American Academy of Sleep Medicine (AASM) standard, the classification accuracies of five classes in the Dreams Subjects database and the ISRUC database reached 79.90% and 81.65%. The proposed method can be used for reliable sleep stage classification with high accuracy compared with state-of-the-art methods.

Reinventing polysomnography in the age of precision medicine

For almost 50 years, sleep laboratories around the world have been collecting massive amounts of polysomnographic (PSG) physiological data to diagnose sleep disorders, the majority of which are not utilized in the clinical setting. Only a small fraction of the information available within these signals is utilized to generate indices. For example, the apnea-hypopnea index (AHI) remains the primary tool for diagnostic and therapeutic decision-making for obstructive sleep apnea (OSA) despite repeated studies showing it to be inadequate in predicting clinical consequences. Today, there are many novel approaches to PSG signals, making it possible to extract more complex metrics and analyses that are potentially more clinically relevant for individual patients. However, the pathway to implement novel PSG metrics/analyses into routine clinical practice is unclear. Our goal with this review is to highlight some of the novel PSG metrics/analyses that are becoming available. We suggest that stronger academic-industry relationships would facilitate the development of state-of-the-art clinical research to establish the value of novel PSG metrics/analyses in clinical sleep medicine. Collectively, as a sleep community, it is time to reinvent how we utilize the polysomnography to move us towards Precision Sleep Medicine.

EEG sleep stages identification based on weighted undirected complex networks

BACKGROUND AND OBJECTIVE

Sleep scoring is important in sleep research because any errors in the scoring of the patient's sleep electroencephalography (EEG) recordings can cause serious problems such as incorrect diagnosis, medication errors, and misinterpretations of patient's EEG recordings. The aim of this research is to develop a new automatic method for EEG sleep stages classification based on a statistical model and weighted brain networks.

METHODS

Each EEG segment is partitioned into a number of blocks using a sliding window technique. A set of statistical features are extracted from each block. As a result, a vector of features is obtained to represent each EEG segment. Then, the vector of features is mapped into a weighted undirected network. Different structural and spectral attributes of the networks are extracted and forwarded to a least square support vector machine (LS-SVM) classifier. At the same time the network's attributes are also thoroughly investigated. It is found that the network's characteristics vary with their sleep stages. Each sleep stage is best represented using the key features of their networks.

RESULTS

In this paper, the proposed method is evaluated using two datasets acquired from different channels of EEG (Pz-Oz and C3-A2) according to the R&K and the AASM without pre-processing the original EEG data. The obtained results by the LS-SVM are compared with those by Naïve, k-nearest and a multi-class-SVM. The proposed method is also compared with other benchmark sleep stages classification methods. The comparison results demonstrate that the proposed method has an advantage in scoring sleep stages based on single channel EEG signals.

CONCLUSIONS

An average accuracy of 96.74% is obtained with the C3-A2 channel according to the AASM standard, and 96% with the Pz-Oz channel based on the R&K standard.

Cross-Channel Phase-Amplitude Transfer Entropy Conceptualize Long-Range Transmission in sleep: a case study

A causal algorithmic framework quantifying cross-channel phase-amplitude transfer entropy was proposed to measure long-range transmission dynamics between frontal and occipital brain areas during sleep. To this end, a noise-assisted multivariate empirical mode decomposition method was used to guarantee the consistent scales across multivariate signals. On the other side, transfer entropy was applied to measure information transfers from a low-frequency phase to a high-frequency amplitude across different brain regions. Our results showed δ phase may modulate either θ or α amplitude. The frontal cortex transferred information to the occipital brain area more than its inverse direction during Awake and N3 sleep stages, whereas N1 was more likely of serving as a transition state. On the other side, the information flow transferred from the occipital area to the frontal cortex surpassed its inverse flow in the N2 sleep stage. The proposed causal algorithmic framework facilitated identifying information flow and driving force across brain regions in sleep.

A New Fully Automated Random-Forest Algorithm for Sleep Staging

Rapid eye movement (REM) sleep behavior disorder is considered the prodromal stage of alpha-synucleinopathies. Its diagnosis requires careful detection of REM sleep and the gold standard manual sleep staging is inconsistent and expensive. This work proposes a new automatic sleep staging model to add robust automation to such applications, using only electroencephalography (EEG) and electrooculography (EOG) recordings. The publicly available ISRUC-Sleep database was used to optimize the design of the proposed model. The model was trained and tested on subgroup-I consisting of 100 subjects with evidence of having different sleep disorders and the polysomnographic data were manually scored by two individual experts. We divided the EOG and EEG recordings in overlapping moving 33-s epochs with step of 3s and for each of them we computed several time and frequency-domain features. The features were used to train a random forest classifier that was able to label each 33-s epoch with the probabilities of being wakefulness, REM and non-REM. The mean of the probability values of ten 33-s epochs were calculated, and the sleep stage with the highest probability was chosen to classify a 30-s epoch and matched with the manual staged hypnogram. The performance of the model was tested using 20-fold cross validation scheme. When the epochs where the scorers agreed were used, the classification achieved an overall accuracy of 92.6% and a Cohen's kappa of 0.856. Future validation on RBD patients is needed, but these performances are promising as first step of development of an automated diagnosis of RBD.

An automatic single-channel EEG-based sleep stage scoring method based on hidden Markov Model

OBJECTIVE

Sleep stage scoring is essential for diagnosing sleep disorders. Visual scoring of sleep stages is very time-consuming and prone to human errors. In this work, we introduce an efficient approach to improve the accuracy of sleep stage scoring and classification for sleep analysis.

METHOD

In this approach, a set of optimal features was first selected from a pool of features extracted from sleep EEG epochs by using a feature selection method based on the relevance and redundancy analysis. EEG segments were then classified using a random forest classifier. Finally, a Hidden Markov Model (HMM) was used to reduce false positives by incorporating knowledge of the temporal structure of transitions between sleep stages. We evaluated the proposed method using single-channel EEG signals from four public sleep EEG datasets scored according to R&K and AASM guidelines. We compared the performance of our method with existing methods using different cross validation strategies.

RESULTS

Using a leave-one-out validation strategy, our method achieved overall accuracies in the range of (79.4-87.4%) and (77.6-80.4%) with Kappa values in the range of 0.7-0.85 for six-stage (R&K) and five-stage (AASM) classification, respectively. Our method showed a reduction in overall accuracy up to 8% using the cross-dataset validation strategy in comparison with the subject cross-validation method.

COMPARISON WITH EXISTING METHOD(S)

Our method outperformed the existing methods for all multi-stage classification.

CONCLUSIONS

The proposed single-channel method can be used for robust and reliable sleep stage scoring with high accuracy and relatively low complexity required for real time applications.

The KIMORE Dataset: KInematic Assessment of MOvement and Clinical Scores for Remote Monitoring of Physical REhabilitation

This paper proposes a free dataset, available at the following link,¹named KIMORE, regarding different rehabilitation exercises collected by a RGB-D sensor. Three data inputs including RGB, depth videos, and skeleton joint positions were recorded during five physical exercises, specific for low back pain and accurately selected by physicians. For each exercise, the dataset also provides a set of features, specifically defined by the physicians, and relevant to describe its scope. These features, validated with respect to a stereophotogrammetric system, can be analyzed to compute a score for the subject's performance. The dataset also contains an evaluation of the same performance provided by the clinicians, through a clinical questionnaire. The impact of KIMORE has been analyzed by comparing the output obtained by an example of rule and template-based approaches and the clinical score. The dataset presented is intended to be used as a benchmark for human movement assessment in a rehabilitation scenario in order to test the effectiveness and the reliability of different computational approaches. Unlike other existing datasets, the KIMORE merges a large heterogeneous population of 78 subjects, divided into 2 groups with 44 healthy subjects and 34 with motor dysfunctions. It provides the most clinically-relevant features and the clinical score for each exercise.¹https://univpm-my.sharepoint.com/:f:/g/personal/p008099_staff_univpm_it/EiwbKIzk6N9NoJQx4J8aubIBx0o7tIa1XwclWp1NmRkA-w?e=F3jtBk.

A Motor Theory of Sleep-Wake Control: Arousal-Action Circuit

Wakefulness, rapid eye movement (REM) sleep, and non-rapid eye movement (NREM) sleep are characterized by distinct electroencephalogram (EEG), electromyogram (EMG), and autonomic profiles. The circuit mechanism coordinating these changes during sleep-wake transitions remains poorly understood. The past few years have witnessed rapid progress in the identification of REM and NREM sleep neurons, which constitute highly distributed networks spanning the forebrain, midbrain, and hindbrain. Here we propose an arousal-action circuit for sleep-wake control in which wakefulness is supported by separate arousal and action neurons, while REM and NREM sleep neurons are part of the central somatic and autonomic motor circuits. This model is well supported by the currently known sleep and wake neurons. It can also account for the EEG, EMG, and autonomic profiles of wake, REM, and NREM states and several key features of their transitions. The intimate association between the sleep and autonomic/somatic motor control circuits suggests that a primary function of sleep is to suppress motor activity.

Lying position classification based on ECG waveform and random forest during sleep in healthy people

BACKGROUND

Several different lying positions, such as lying on the left side, supine, lying on the right side and prone position, existed when healthy people fell asleep. This article explored the influence of lying positions on the shape of ECG (electrocardiograph) waveform during sleep, and then lying position classification based on ECG waveform features and random forest was achieved.

METHODS

By means of de-noising the overnight sleep ECG data from ISRUC website dataset, as well as extracting the waveform features, we calculated a total of 30 ECG waveform features, including 2 newly proposed features, S/R and ∠QSR. The means and significant difference level of these features within different lying positions were calculated, respectively. Then 12 features were selected for three kinds of classification schemes.

RESULTS

The lying positions had comparatively less effect on time-limit features. QT interval and RR interval were significantly lower than that in supine ([Formula: see text]). Significant differences appeared in most of the amplitude and double-direction features. When lying on the left side, the height of P wave and T wave, QRS area and T area, the QR potential difference and ∠QSR were significantly lower than those in supine ([Formula: see text]). However, S/R was significantly greater on left than those in supine ([Formula: see text]) and on right ([Formula: see text]). The height of T wave and area under T wave were significantly higher in supine than those on right ([Formula: see text]). For the subject specific classifier, a mean accuracy of 97.17% with Cohen's kappa statistic κ of 0.91, and AUC > 0.97 were achieved. While the accuracy and κ dropped to 63.87% and 0.32, AUC > 0.66, respectively when the subject independent classifier was considered.

CONCLUSIONS

When subjects were lying on the left side during sleep, due to the effect of gravity on heart, the position of heart changed, for example, turned and rotated, causing changes in the vectorcardiogram of frontal plane and horizontal plane, which lead to a change in ECG. When lying on the right side, the heart was upheld by the mediastinum, so that the degree of freedom was poor, and the ECG waveform was almost unchanged. The proposed method could be used as a technique for convenient lying position classification.