Search

Sleep staging plays an important role in the diagnosis and treatment of clinical sleep disorders. The sleep staging standard defines every 30 seconds as a sleep period, which may mean that there exist similar brain activity patterns during the same sleep period. Thus, in this work, we propose a novel time-related synchronization analysis framework named time-related multimodal sleep scoring model (TRMSC) to explore the potential time-related patterns of sleeping. In the proposed TRMSC, the time-related synchronization analysis is first conducted on the single channel electrophysiological signal, i.e., Electroencephalogram (EEG) and Electrooculogram (EOG), to explore the time-related patterns, and the spectral activation features are also extracted by spectrum analysis to obtain the multimodal features. With the extracted multimodal features, the feature fusion and selection strategy is utilized to obtain the optimal feature set and achieve robust sleep staging. To verify the effectiveness of the proposed TRMSC, sleep staging experiments were conducted on the Sleep-EDF dataset, and the experimental results indicate that the proposed TRMSC has achieved better performance than other existing strategies, which proves that the time-related synchronization features can make up for the shortcomings of traditional spectrum-based strategies and achieve a higher classification accuracy. The proposed TRMSC model may be helpful for portable sleep analyzers and provide a new analytical method for clinical sleeping research., Competing Interests: Declaration of Competing Interest All authors disclosed no relevant relationships., (Copyright © 2024 The Authors. Published by Elsevier Inc. All rights reserved.)

The electroencephalogram (EEG) is a fundamental diagnostic procedure that explores brain function. This manuscript describes the characteristics of a sample of healthy at-term infants. One hundred and three (103) infants from Mexico between 15 days and 12.5 months of age were recorded during physiological sleep. Referential EEG recordings were obtained using linked ear lobes as reference. The amplifier gain was 10,000, the bandwidth was set between 0.3 and 30 Hz, and the sample rate was 200 Hz. Sample windows of 2.56 s were marked for later quantitative analysis. To our knowledge, this is the first dataset of normal infants during the first year of age., (© 2024. The Author(s).)

Time irreversibility (TIR) refers to the manifestation of nonequilibrium brain activity influenced by various physiological conditions; however, the influence of sleep on electroencephalogram (EEG) TIR has not been sufficiently investigated. In this paper, a comprehensive study on permutation TIR (pTIR) of EEG data under different sleep stages is conducted. Two basic ordinal patterns (i.e., the original and amplitude permutations) are distinguished to simplify sleep EEGs, and then the influences of equal values and forbidden permutation on pTIR are elucidated. To detect pTIR of brain electric signals, five groups of EEGs in the awake, stages I, II, III, and rapid eye movement (REM) stages are collected from the public Polysomnographic Database in PhysioNet. Test results suggested that the pTIR of sleep EEGs significantly decreases as the sleep stage increases (p<0.001), with the awake and REM EEGs demonstrating greater differences than others. Comparative analysis and numerical simulations support the importance of equal values. Distribution of equal states, a simple quantification of amplitude fluctuations, significantly increases with the sleep stage (p<0.001). If these equalities are ignored, incorrect probabilistic differences may arise in the forward-backward and symmetric permutations of TIR, leading to contradictory results; moreover, the ascending and descending orders for symmetric permutations also lead different outcomes in sleep EEGs. Overall, pTIR in sleep EEGs contributes to our understanding of quantitative TIR and classification of sleep EEGs.

Brain states (wake, sleep, general anesthesia, etc.) are profoundly associated with the spatiotemporal dynamics of brain oscillations. Previous studies showed that the EEG alpha power shifted from the occipital cortex to the frontal cortex (alpha anteriorization) after being induced into a state of general anesthesia via propofol. The sleep research literature suggests that slow waves and sleep spindles are generated locally and propagated gradually to different brain regions. Since sleep and general anesthesia are conceptualized under the same framework of consciousness, the present study examines whether alpha anteriorization similarly occurs during sleep and how the EEG power in other frequency bands changes during different sleep stages. The results from the analysis of three polysomnography datasets of 234 participants show consistent alpha anteriorization during the sleep stages N2 and N3, beta anteriorization during stage REM, and theta posteriorization during stages N2 and N3. Although it is known that the neural circuits responsible for sleep are not exactly the same for general anesthesia, the findings of alpha anteriorization in this study suggest that, at macro level, the circuits for alpha oscillations are organized in the similar cortical areas. The spatial shifts of EEG power in different frequency bands during sleep may offer meaningful neurophysiological markers for the level of consciousness., (© 2024 Wiley Periodicals LLC.)

Sleep recordings are increasingly being conducted in patients' homes where patients apply the sensors themselves according to instructions. However, certain sensor types such as cup electrodes used in conventional polysomnography are unfeasible for self-application. To overcome this, self-applied forehead montages with electroencephalography and electro-oculography sensors have been developed. We evaluated the technical feasibility of a self-applied electrode set from Nox Medical (Reykjavik, Iceland) through home sleep recordings of healthy and suspected sleep-disordered adults (n = 174) in the context of sleep staging. Subjects slept with a double setup of conventional type II polysomnography sensors and self-applied forehead sensors. We found that the self-applied electroencephalography and electro-oculography electrodes had acceptable impedance levels but were more prone to losing proper skin-electrode contact than the conventional cup electrodes. Moreover, the forehead electroencephalography signals recorded using the self-applied electrodes expressed lower amplitudes (difference 25.3%-43.9%, p < 0.001) and less absolute power (at 1-40 Hz, p < 0.001) than the polysomnography electroencephalography signals in all sleep stages. However, the signals recorded with the self-applied electroencephalography electrodes expressed more relative power (p < 0.001) at very low frequencies (0.3-1.0 Hz) in all sleep stages. The electro-oculography signals recorded with the self-applied electrodes expressed comparable characteristics with standard electro-oculography. In conclusion, the results support the technical feasibility of the self-applied electroencephalography and electro-oculography for sleep staging in home sleep recordings, after adjustment for amplitude differences, especially for scoring Stage N3 sleep., (© 2023 The Authors. Journal of Sleep Research published by John Wiley & Sons Ltd on behalf of European Sleep Research Society.)

Healthy sleep plays an essential role in human daily life. Classification of sleep stages is a crucial tool for assisting physicians in diagnosing and treating sleep disorders. In this study, a strong ensemble learning model is proposed to enhance the ability of classification models in accurate sleep staging, particularly in multi-class classification. We asserted that high-accuracy sleep classification is achievable using only single-channel electroencephalogram (EEG) and electrocardiogram (ECG) by combining their best-extractable features in the time and frequency domains we recommended. More importantly, the superiority of the recommended method, which is the simultaneous use of stacking and bagging, over conventional machine learning classifiers in sleep staging was demonstrated, using the MIT-BIH Polysomnographic and Sleep-EDF expanded databases. Finally, K-fold cross-validation was used to fairly estimate these models. The best mean test accuracy rates for distinguishing between two classes of "sleep vs. wake," "rapid vs. non-rapid eye movement," and "deep vs. light sleep," were obtained 99.93%, 99.64%, and 99.69%, respectively. Furthermore, our proposed method achieved accuracies of 97.14%, 95.18%, 92.7%, and 85.64% for separating three, four, five, and six sleep classes, respectively. Compared to recent studies, our method outperforms other sleep stage classification schemes, especially in multi-class staging., (© 2023. International Federation for Medical and Biological Engineering.)

Study Objectives: Hypnograms contain a wealth of information and play an important role in sleep medicine. However, interpretation of the hypnogram is a difficult task and requires domain knowledge and "clinical intuition." This study aimed to uncover which features of the hypnogram drive interpretation by physicians. In other words, make explicit which features physicians implicitly look for in hypnograms., Methods: Three sleep experts evaluated up to 612 hypnograms, indicating normal or abnormal sleep structure and suspicion of disorders. ElasticNet and convolutional neural network classification models were trained to predict the collected expert evaluations using hypnogram features and stages as input. The models were evaluated using several measures, including accuracy, Cohen's kappa, Matthew's correlation coefficient, and confusion matrices. Finally, model coefficients and visual analytics techniques were used to interpret the models to associate hypnogram features with expert evaluation., Results: Agreement between models and experts (Kappa between 0.47 and 0.52) is similar to agreement between experts (Kappa between 0.38 and 0.50). Sleep fragmentation, measured by transitions between sleep stages per hour, and sleep stage distribution were identified as important predictors for expert interpretation., Conclusions: By comparing hypnograms not solely on an epoch-by-epoch basis, but also on these more specific features that are relevant for the evaluation of experts, performance assessment of (automatic) sleep-staging and surrogate sleep trackers may be improved. In particular, sleep fragmentation is a feature that deserves more attention as it is often not included in the PSG report, and existing (wearable) sleep trackers have shown relatively poor performance in this aspect., (© The Author(s) 2023. Published by Oxford University Press on behalf of Sleep Research Society. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.)

Automatic sleep staging offers a quick and objective assessment for quantitatively interpreting sleep stages in neonates. However, most of the existing studies either do not encompass any temporal information, or simply apply neural networks to exploit temporal information at the expense of high computational overhead and modeling ambiguity. This limits the application of these methods to multiple scenarios. In this paper, a sequential end-to-end sleep staging model, SeqEESleepNet, which is competent for parallelly processing sequential epochs and has a fast training rate to adapt to different scenarios, is proposed. SeqEESleepNet consists of a sequence epoch generation (SEG) module, a sequential multi-scale convolution neural network (SMSCNN) and squeeze and excitation (SE) blocks. The SEG module expands independent epochs into sequential signals, enabling the model to learn the temporal information between sleep stages. SMSCNN is a multi-scale convolution neural network that can extract both multi-scale features and temporal information from the signal. Subsequently, the followed SE block can reassign the weights of features through mapping and pooling. Experimental results exhibit that in a clinical dataset, the proposed method outperforms the state-of-the-art approaches, achieving an overall accuracy, F1-score, and Kappa coefficient of 71.8%, 71.8%, and 0.684 on a three-class classification task with a single channel EEG signal. Based on our overall results, we believe the proposed method could pave the way for convenient multi-scenario neonatal sleep staging methods.

The majority of EEG microstate analyses concern wakefulness, and the existing sleep studies have focused on changes in spatial microstate properties and on microstate transitions between adjacent time points, the shortest available time scale. We present a more extensive time series analysis of unsmoothed EEG microstate sequences in wakefulness and non-REM sleep stages across many time scales. Very short time scales are assessed with Markov tests, intermediate time scales by the entropy rate and long time scales by a spectral analysis which identifies characteristic microstate frequencies. During the descent from wakefulness to sleep stage N3, we find that the increasing mean microstate duration is a gradual phenomenon explained by a continuous slowing of microstate dynamics as described by the relaxation time of the transition probability matrix. The finite entropy rate, which considers longer microstate histories, shows that microstate sequences become more predictable (less random) with decreasing vigilance level. Accordingly, the Markov property is absent in wakefulness but in sleep stage N3, 10/19 subjects have microstate sequences compatible with a second-order Markov process. A spectral microstate analysis is performed by comparing the time-lagged mutual information coefficients of microstate sequences with the autocorrelation function of the underlying EEG. We find periodic microstate behavior in all vigilance states, linked to alpha frequencies in wakefulness, theta activity in N1, sleep spindle frequencies in N2, and in the delta frequency band in N3. In summary, we show that EEG microstates are a dynamic phenomenon with oscillatory properties that slow down in sleep and are coupled to specific EEG frequencies across several sleep stages., (© 2023. The Author(s).)

This work attempts to design an effective sleep staging system, making the best use of the available signals, strategies, and features in the literature. It must not only perform well on different datasets comprising healthy and clinical populations but also achieve good accuracy in cross-dataset experiments. Toward this end, we propose a model comprising multiple binary classifiers in a hierarchical fashion, where, at each level, one or more of EEG, EOG, and EMG are selected to best differentiate between two sleep stages. The best set of 100 features is chosen out of all the features derived from selected signals. The class imbalance in data is addressed by random undersampling and boosting techniques with decision trees as weak learners. Temporal context and data augmentation are used to improve the performance. We also evaluate the performance of our model by training and testing on different datasets. We compare the results of five approaches: using only EEG, EEG+EOG, EEG+EMG+EOG, EEG+EMG, and selective modality with a specific combination of EEG, EMG, and/or EOG at each level. The best results are obtained by considering features from EEG+EMG+EOG at each hierarchical level. The proposed model achieves average accuracies of 83.1%, 90.0%, 84.4%, 82.1%, 81.5%, 79.9%, and 73.7% on Sleep-EDF, Exp Sleep-EDF, ISRUC-S1, S2 and S3, DRMS-SUB, and DRMS-PAT datasets, respectively. For all the datasets except DRMS-SUB, the proposed method outperforms all the state-of-the-art approaches. Cross-dataset performance exceeds 80% for all datasets except DRMS-PAT; independent of whether the test data is from normal subjects or patients.

There is nothing we spend as much time on in our lives as we do sleeping, which makes it even more surprising that we currently do not know why we need to sleep. Most of the research addressing this question is performed in rodents to allow for invasive, mechanistic approaches. However, in contrast to human sleep, we currently do not have shared and agreed upon standards on sleep states in rodents. In this article, we present an overview on sleep stages in humans and rodents and a historical perspective on the development of automatic sleep scoring systems in rodents. Further, we highlight specific issues in rodent sleep that also call into question some of the standards used in human sleep research., (© 2022 The Authors. European Journal of Neuroscience published by Federation of European Neuroscience Societies and John Wiley & Sons Ltd.)

Single-channel EEG based sleep staging is of interest to researchers due to its broad application prospect in daily sleep monitoring recently. We proposed using contextual scalograms as input and developed a convolutional neural network with attention modules named Co-ScaleNet for sleep staging. The contextual scalograms were obtained by combining the same color channels of three original RGB scalograms from consecutive epochs, and a simple and efficient data augmentation was designed according to their various forms. The Co-ScaleNet consists of two main parts. Firstly, three parallel convolutional branches with attention modules correspondingly extract and fuse features from contextual scalograms at the top layers. The remaining part is a stack of lightweight blocks. We achieved an overall accuracy of 87.0% for healthy individuals, 84.7% for depressed patients. And we obtained comparable performance on the public Sleep-EDFx (82.8%), ISRUC (84.6%) and SHHS datasets (87.7%), including a high recall of N1. The contextual scalograms of R channel as input achieved the best performance, which conform to the features of interest in visual scoring. The attention modules improved the recall of N1 and N3. Overall, the contextual scalograms provided a novel scheme for both contextual information extraction and data augmentation. Our study successfully expanded its application to depression datasets, as well as patients with sleep apnea, demonstrating its wide applicability.

We propose a two-step procedure for atomic decomposition of multichannel EEGs, based upon multivariate matching pursuit and dipolar inverse solution, from which atoms representing relevant EEG structures are selected according to prior knowledge. We detect sleep spindles in 147 polysomnographic recordings from the Montreal Archive of Sleep Studies. Detection is compared with human scorers and two state-of-the-art algorithms, which find only about a third of the structures conforming to the definition of sleep spindles and detected by the proposed method. We provide arguments supporting the thesis that the previously undetectable sleep spindles share the same properties as those marked by human experts and previously applied methods, and were previously omitted only because of unfavorable local signal-to-noise ratios, obscuring their visibility to both human experts and algorithms replicating their markings. All detected EEG structures are automatically parametrized by their time and frequency centers, width duration, phase, and spatial location of an equivalent dipolar source within the brain. It allowed us, for the first time, to estimate the spatial gradient of sleep spindles frequencies, which not only confirmed quantitatively the well-known prevalence of higher frequencies in posterior regions, but also revealed a significant gradient in the sagittal plane. The software used in this study is freely available.

Nowadays, many sleep staging algorithms have not been widely used in practical situations due to the lack of persuasiveness of generalization outside the given datasets. Thus, to improve generalization, we select seven highly heterogeneous datasets covering 9970 records with over 20k hours among 7226 subjects spanning 950 days for training, validation, and evaluation. In this paper, we propose an automatic sleep staging architecture called TinyUStaging using single-lead EEG and EOG. The TinyUStaging is a lightweight U-Net with multiple attention modules to perform adaptive recalibration of the features, including Channel and Spatial Joint Attention (CSJA) block and Squeeze and Excitation (SE) block. Noteworthily, to address the class imbalance problem, we design sampling strategies with probability compensation and propose a class-aware Sparse Weighted Dice and Focal (SWDF) loss function to improve the recognition rate for minority classes (N1) and hard-to-classify samples (N3) especially for OSA patients. Additionally, two hold-out sets containing healthy and sleep-disordered subjects are considered to verify the generalization. Facing the background of large-scale imbalanced heterogeneous data, we perform subject-wise 5-fold cross-validation on each dataset, and the results demonstrate that our model outperforms many methods, especially in N1, achieving an average overall accuracy, macro F1-score (MF1), and kappa of 84.62%, 79.6%, and 0.764 on heterogeneous datasets under optimal partitioning, providing a solid foundation for out-of-hospital sleep monitoring. Moreover, the overall standard deviation of MF1 under different folds remains within 0.175, indicating that the model is relatively stable., Competing Interests: Declaration of competing interest None Declared, (Copyright © 2023 Elsevier Ltd. All rights reserved.)

Sleep is crucial for human health. Automatic sleep stage classification based on polysomnogram (PSG) is meaningful for the diagnosis of sleep disorders, which has attracted extensive attention in recent years. Most existing methods could not fully consider the different transitions of sleep stages and fit the visual inspection of sleep experts simultaneously. To this end, we propose a temporal multi-scale hybrid attention network, namely TMHAN, to automatically achieve sleep staging. The temporal multi-scale mechanism incorporates short-term abrupt and long-term periodic transitions of the successive PSG epochs. Furthermore, the hybrid attention mechanism includes 1-D local attention, 2-D global attention, and 2-D contextual sparse multi-head self-attention for three kinds of sequence-level representations. The concatenated representation is subsequently fed into a softmax layer to train an end-to-end model. Experimental results on two benchmark sleep datasets show that TMHAN obtains the best performance compared with several baselines, demonstrating the effectiveness of our model. In general, our work not only provides good classification performance, but also fits the actual sleep staging processes, which makes contribution for the combination of deep learning and sleep medicine., (© 2023. International Federation for Medical and Biological Engineering.)

Objective: To assess the longitudinal evolution of EEG findings in children with Zika related-microcephaly (ZRM) and to evaluate the associations of these patterns with the children's clinical and neuroimaging characteristics., Methods: As part of the follow-up of the Microcephaly Epidemic Research Group Pediatric Cohort (MERG-PC) in Recife, Brazil, we performed serial EEG recordings in a subgroup of children with ZRM to evaluate changes in background rhythms and epileptiform activity (EA). Latent class analysis was used to identify patterns in the evolution of EA over time; clinical and neuroimaging findings were compared across the identified groups., Results: Out of the 72 children with ZRM who were evaluated during 190 EEGs/videoEEGs, all participants presented with abnormal background activity, 37.5% presented with an alpha-theta rhythmic activity, and 25% presented with sleep spindles, which were less commonly observed in children with epilepsy. EA changed over time in 79.2% of children, and three distinct trajectories were identified: (i) multifocal EA over time, (ii) no discharges/focal EA evolving to focal/multifocal EA, and (iii) focal/multifocal EA evolving to epileptic encephalopathy patterns (e.g., hypsarrhythmia or continuous EA in sleep). The multifocal EA over time trajectory was associated with periventricular and thalamus/basal ganglia calcifications, brainstem and corpus callosum atrophy and had less focal epilepsy, whereas the children in the trajectory which evolved to epileptic encephalopathy patterns had more frequently focal epilepsy., Significance: These findings suggest that, in most children with ZRM, trajectories of changes in EA can be identified and associated with neuroimaging and clinical features., Competing Interests: Declaration of Competing Interest None of the authors has any conflicts of interest to disclose., (Copyright © 2023. Published by Elsevier Ltd.)

Objective . Sleep staging studies on single-channel EEG mainly exploit deep learning methods that combine convolutional neural networks (CNNs) and recurrent neural networks. However, when typical brain waves (such as K-complexes or sleep spindles) that identify sleep stages span two epochs, the abstract process of a CNN extracting features from each sleep stage may cause the loss of boundary context information. This study attempts to capture the boundary context, which contains the characteristics of brain waves during sleep stage transition, to improve the performance of sleep staging. Approach . In this paper we propose a fully convolutional network with boundary temporal context refinement, called BTCRSleep (Boundary Temporal Context Refinement Sleep). The boundary temporal context refinement module refines the boundary information on sleep stages on the basis of extracting multi-scale temporal dependences between epochs and enhances the abstract capability of the boundary temporal context. In addition, we design a class-aware data augmentation method to effectively learn the boundary temporal context between the minority class and other sleep stages. Main results . We evaluate the performance of our proposed network using four public datasets: the 2013 version of Sleep-EDF Expanded (SEDF), the 2018 version of Sleep-EDF Expanded (SEDFX), the Sleep Heart Health Study (SHHS) and CAP Sleep Database (CAP). The evaluation results on the four datasets showed that our model obtains the best total accuracy and kappa score compared with state-of-the-art methods. On average, accuracies of 84.9% in SEDF, 82.9% in SEDFX, 85.2% in SHHS and 76.9% in CAP are obtained under subject-independent cross-validation. We demonstrate that the boundary temporal context contributes to the improvement in capturing the temporal dependences across different epochs., (© 2023 Institute of Physics and Engineering in Medicine.)

The supervised sleep staging methods are challenged by their strict requirements of a labelled and large dataset. This study considers an unsupervised dimensionality reduction method, the Deep Boltzmann Machine (DBM), trained to a transient state for binary classification of sleep stages. First, the joint time-frequency domain features from the polysomnographic recordings are extracted. Second, the extracted features are smoothed using 2 min rolling window to include contextual temporal information, and finally, they serve as an input for unsupervised training of DBM&#95;transient. The results show that our method effectively separates the sleep stages in two-dimensional feature space with a large Fisher's discriminant value. The classification performance by the DBM&#95;transient achieves a 96.1% F1 score, which is higher than DBM converged to an equilibrium state (95.2%), Principal Component Analysis (92.5%), Isometric Feature Mapping (95.9%), t-distributed Stochastic Neighbor Embedding (94.9%), and Uniform Manifold Approximation (95.0%) on the widely used sleep-EDF database. Additionally, Fisher's discriminant function demonstrates the superiority of the DBM&#95;transient. The significance of the DBM transient lies in its ease of interpretability in two-dimensional space, and future multi-class implementation of the method may facilitate its usage in clinical applications.

Sleep staging is essential for sleep assessment and plays a vital role as a health indicator. Many recent studies have devised various machine/deep learning methods for sleep staging. However, two key challenges hinder the practical use of those methods: 1) effectively capturing salient waveforms in sleep signals and 2) correctly classifying confusing stages in transitioning epochs. In this study, we propose a novel deep neural-network structure, TransSleep, that captures distinctive local temporal patterns and distinguishes confusing stages using two auxiliary tasks. In particular, TransSleep captures salient waveforms in sleep signals by an attention-based multiscale feature extractor and correctly classifies confusing stages in transitioning epochs, while modeling contextual relationships with two auxiliary tasks. Results show that TransSleep achieves promising performance in automatic sleep staging. The validity of TransSleep is demonstrated by its state-of-the-art performance on two publicly available datasets: 1) Sleep-EDF and 2) MASS. Furthermore, we performed ablations to analyze our results from different perspectives. Based on our overall results, we believe that TransSleep has immense potential to provide new insights into deep-learning-based sleep staging.

Deep learning methods have become an important tool for automatic sleep staging in recent years. However, most of the existing deep learning-based approaches are sharply constrained by the input modalities, where any insertion, substitution, and deletion of input modalities would directly lead to the unusable of the model or a deterioration in the performance. To solve the modality heterogeneity problems, a novel network architecture named MaskSleepNet is proposed. It consists of a masking module, a multi-scale convolutional neural network (MSCNN), a squeezing and excitation (SE) block, and a multi-headed attention (MHA) module. The masking module consists of a modality adaptation paradigm that can cooperate with modality discrepancy. The MSCNN extracts features from multiple scales and specially designs the size of the feature concatenation layer to prevent invalid or redundant features from zero-setting channels. The SE block further optimizes the weights of the features to optimize the network learning efficiency. The MHA module outputs the prediction results by learning the temporal information between the sleeping features. The performance of the proposed model was validated on two publicly available datasets, Sleep-EDF Expanded (Sleep-EDFX) and Montreal Archive of Sleep Studies (MASS), and a clinical dataset, Huashan Hospital Fudan University (HSFU). The proposed MaskSleepNet can achieve favorable performance with input modality discrepancy, e.g. for single-channel EEG signal, it can reach 83.8%, 83.4%, 80.5%, for two-channel EEG+EOG signals it can reach 85.0%, 84.9%, 81.9% and for three-channel EEG+EOG+EMG signals, it can reach 85.7%, 87.5%, 81.1% on Sleep-EDFX, MASS, and HSFU, respectively. In contrast the accuracy of the state-of-the-art approach which fluctuated widely between 69.0% and 89.4%. The experimental results exhibit that the proposed model can maintain superior performance and robustness in handling input modality discrepancy issues.

Sleep spindles are developmentally relevant cortical oscillatory patterns; however, they have mostly been studied by considering the entire spindle frequency range (11-15 Hz) without a distinction between the functionally and topographically different slow and fast spindles, using relatively few electrodes and analysing wide age-ranges. Here, we employ high-density night sleep electroencephalography in three age-groups between 12 and 20 years of age (30 females and 30 males) and analyse the adolescent developmental pattern of the four major parameters of slow and fast sleep spindles. Most of our findings corroborate those very few previous studies that also make a distinction between slow and fast spindles in their developmental analysis. We find spindle frequency increasing with age. A spindle density change is not obvious in our study. We confirm the declining tendencies for amplitude and duration, although within narrower, more specific age-windows than previously determined. Spindle frequency seems to be higher in females in the oldest age-group. Based on the pattern of our findings, we suggest that high-density electroencephalography, specifically targeting slow and fast spindle ranges and relatively narrow age-ranges would advance the understanding of both adolescent cortical maturation and development and the functional relevance of sleep spindles in general., (© 2022 The Authors. Journal of Sleep Research published by John Wiley & Sons Ltd on behalf of European Sleep Research Society.)

Deep learning (DL)-based automatic sleep staging approaches have attracted much attention recently due in part to their outstanding accuracy. At the testing stage, however, the performance of these approaches is likely to be degraded, when applied in different testing environments, because of the problem of domain shift. This is because while a pre-trained model is typically trained on noise-free electroencephalogram (EEG) signals acquired from accurate medical equipment, deployment is carried out on consumer-level devices with undesirable noise. To alleviate this challenge, in this work, we propose an efficient training approach that is robust against unseen arbitrary noise. In particular, we propose to generate the worst-case input perturbations by means of adversarial transformation in an auxiliary model, to learn a wide range of input perturbations and thereby to improve reliability. Our approach is based on two separate training models: (i) an auxiliary model to generate adversarial noise and (ii) a target network to incorporate the noise signal to enhance robustness. Furthermore, we exploit novel class-wise robustness during the training of the target network to represent different robustness patterns of each sleep stage. Our experimental results demonstrated that our approach improved sleep staging performance on healthy controls, in the presence of moderate to severe noise levels, compared with competing methods. Our approach was able to effectively train and deploy a DL model to handle different types of noise, including adversarial, Gaussian, and shot noise.

The analysis of sleep stages for children plays an important role in early diagnosis and treatment. This paper introduces our sleep stage classification method addressing the following two challenges: the first is the data imbalance problem, i.e., the highly skewed class distribution with underrepresented minority classes. For this, a Gaussian Noise Data Augmentation (GNDA) algorithm was applied to polysomnography recordings to seek the balance of data sizes for different sleep stages. The second challenge is the difficulty in identifying a minority class of sleep stages, given their short sleep duration and similarities to other stages in terms of EEG characteristics. To overcome this, we developed a DeConvolution- and Self-Attention-based Model (DCSAM) which can inverse the feature map of a hidden layer to the input space to extract local features and extract the correlations between all possible pairs of features to distinguish sleep stages. The results on our dataset show that DCSAM based on GNDA obtains an accuracy of 90.26% and a macro F1-score of 86.51% which are higher than those of our previous method. We also tested DCSAM on a well-known public dataset-Sleep-EDFX-to prove whether it is applicable to sleep data from adults. It achieves a comparable performance to state-of-the-art methods, especially accuracies of 91.77%, 92.54%, 94.73%, and 95.30% for six-stage, five-stage, four-stage, and three-stage classification, respectively. These results imply that our DCSAM based on GNDA has a great potential to offer performance improvements in various medical domains by considering the data imbalance problems and correlations among features in time series data.

Sleep scoring is one of the primary tasks for the classification of sleep stages in Electroencephalogram (EEG) signals. Manual visual scoring of sleep stages is time-consuming as well as being dependent on the experience of a highly qualified sleep expert. This paper aims to address these issues by developing a new method to automatically classify sleep stages in EEG signals. In this research, a robust method has been presented based on the clustering approach, coupled with probability distribution features, to identify six sleep stages with the use of EEG signals. Using this method, each 30-second EEG signal is firstly segmented into small epochs and then each epoch is divided into 60 sub-segments. Each sub-segment is decomposed into five levels by using a discrete wavelet transform (DWT) to obtain the approximation and detailed coefficient. The wavelet coefficient of each level is clustered using the k-means algorithm. Subsequently, features are extracted based on the probability distribution for each wavelet coefficient. The extracted features then are forwarded to the least squares support vector machine classifier (LS-SVM) to identify sleep stages. Comparisons with several existing methods are also made in this study. The proposed method for the classification of the sleep stages achieves an average accuracy rate of 97.4%. It can be an effective tool for sleep stages classification and can be useful for doctors and neurologists for diagnosing sleep disorders., Competing Interests: Conflicts of interest The authors declare no conflicts of interest for this work., (Copyright © 2022 Japan Neuroscience Society and Elsevier Ltd. All rights reserved.)

Sleep stage classification is a fundamental task in diagnosing and monitoring sleep diseases. There are 2 challenges that remain open: (1) Since most methods only rely on input from a single channel, the spatial-temporal relationship of sleep signals has not been fully explored. (2) Lack of sleep data makes models hard to train from scratch. Here, we propose a vision Transformer-based architecture to process multi-channel polysomnogram signals. The method is an end-to-end framework that consists of a spatial encoder, a temporal encoder, and an MLP head classifier. The spatial encoder using a pre-trained Vision Transformer captures spatial information from multiple PSG channels. The temporal encoder utilizing the self-attention mechanism understands transitions between nearby epochs. In addition, we introduce a tailored image generation method to extract features within multi-channel and reshape them for transfer learning. We validate our method on 3 datasets and outperform the state-of-the-art algorithms. Our method fully explores the spatial-temporal relationship among different brain regions and addresses the problem of data insufficiency in clinical environments. Benefiting from reformulating the problem as image classification, the method could be applied to other 1D-signal problems in the future.

Sleep staging is the essential step in sleep quality assessment and sleep disorders diagnosis. However, most current automatic sleep staging approaches use recurrent neural networks (RNN), resulting in a relatively large training burden. Moreover, these methods only extract information of the whole epoch or adjacent epochs, ignoring the local signal variations within epoch. To address these issues, a novel deep learning architecture named segmented attention network (SAN) is proposed in this paper. The architecture can be divided into feature extraction (FE) and time sequence encoder (TSE). The FE module consists of multiple multiscale CNN (MMCNN) and residual squeeze and excitation block (SE block). The former extracts features from multiple equal-length EEG segments and the latter reinforced the features. The TSE module based on a multi-head attention mechanism could capture the temporal information in the features extracted by FE module. Noteworthy, in SAN, we replaced the RNN module with a TSE module for temporal learning and made the network faster. The evaluation of the model was performed on two widely used public datasets, Montreal Archive of Sleep Studies (MASS) and Sleep-EDFX, and one clinical dataset from Huashan Hospital of Fudan University, Shanghai, China (HSFU). The proposed model achieved the accuracy of 85.5%, 86.4%, 82.5% on Sleep-EDFX, MASS and HSFU, respectively. The experimental results exhibited favorable performance and consistent improvements of SAN on different datasets in comparison with the state-of-the-art studies. It also proved the necessity of sleep staging by integrating the local characteristics within epochs and adjacent informative features among epochs.

Sleep staging is crucial for diagnosing sleep-related disorders. The heavy and time-consuming task of manual staging can be released by automatic techniques. However, the automatic staging model would have a relatively poor performance when working on unseen new data due to individual differences. In this research, a developed LSTM-Ladder-Network (LLN) model is proposed for automatic sleep stage classification. Several features are extracted for each epoch and combined with the following epochs to form a cross-epoch vector. The long short-term memory (LSTM) network is added into the basic ladder network (LN) to learn the sequential information of adjacent epochs. The developed model is implemented based on a transductive learning scheme to avoid the issue of accuracy loss caused by individual differences. In this process, the labeled data pre-trains the encoder, and the unlabeled data re- fine the model parameters by minimizing the reconstruction loss. The proposed model is evaluated on the data from public database and hospital. Comparison experiments were conducted where the developed LLN model achieved rather satisfied performance while dealing with the unseen new data. The obtained results demonstrate the effectiveness of the proposed approach in addressing individual differences. This can improve the quality of automatic sleep staging when assessed on different individuals and has strong application potential as a computer aided approach for sleep staging.

Most existing neonatal sleep staging appro- aches applied multiple EEG channels to obtain good performance. However, it potentially increased the computational complexity and led to an increased risk of skin disruption to neonates during data acquisition. In this paper, a multi-scale hierarchical neural network (MS-HNN) with a squeeze and excitation (SE) block for neonatal sleep staging is presented in this study on the basis of a single EEG channel. MS-HNN composes of multi-scale convolutional neural network (MSCNN), temporal information learning (TIL) module, and squeeze and excitation (SE) block. MSCNN can extract features from different scales and frequencies, and TIL module can acquire the transition information among adjacent stages. In addition, for these extracted features, SE block can selectively concentrate on informative features and weaken redundant features for achieving better performance. The proposed approach was validated on a clinical dataset involving 64 neonates from the Children's Hospital of Fudan University (CHFU). The proposed network achieves an accuracy of 75.4% and 76.5% for three-class automatic neonatal sleep staging with the single-EEG channel and the eight-EEG channels, respectively. The experimental results show that the proposed method can maintain good performance by making full use of the information in the single channel while reducing the channels to control the computational overhead.

Objective . Computerized classification of sleep stages based on single-lead electroencephalography (EEG) signals is important, but still challenging. In this paper, we proposed a deep neural network called MRASleepNet for automatic sleep stage classification using single-channel EEG signals. Approach . The proposed MRASleepNet model consisted of a feature extraction (FE) module, a multi-resolution attention (MRA) module, and a gated multilayer perceptron (gMLP) module, as well as a direct pathway for computing statistical features. The FE, MRA, and gMLP modules were used to extract features, establish feature attention, and obtain temporal relationships between features, respectively. EEG signals were normalized and cut into 30 s segments, and enhanced by incorporating contextual information from adjacent data segments. After data enhancement, the 40 s data segments were input to the MRASleepNet model. The model was evaluated on the SleepEDF and the cyclic alternating pattern (CAP) databases, using such metrics as the accuracy, Kappa, and macro-F1 (MF1). Main results. For the SleepEDF-20 database, the proposed model had an accuracy of 84.5%, an MF1 of 0.789, and a Kappa of 0.786. For the SleepEDF-78 database, the model had an accuracy of 81.4%, an MF1 of 0.754, and a Kappa of 0.743. For the CAP database, the model had an accuracy of 74.3%, an MF1 of 0.656, and a Kappa of 0.652. The proposed model achieved satisfactory performance in automatic sleep stage classification tasks. Significance . The time- and frequency-domain features extracted by the FE module and filtered by the MRA module, together with the temporal features extracted by the gMLP module and the statistical features extracted by the statistical highway, enabled the proposed model to obtain a satisfying performance in sleep staging. The proposed MRASleepNet model may be used as a new deep learning method for automatic sleep stage classification. The code of MRASleepNet will be made available publicly onhttps://github.com/YuRui8879/., (© 2022 IOP Publishing Ltd.)

Objective. The use of deep learning for electroencephalography (EEG) classification tasks has been rapidly growing in the last years, yet its application has been limited by the relatively small size of EEG datasets. Data augmentation, which consists in artificially increasing the size of the dataset during training, can be employed to alleviate this problem. While a few augmentation transformations for EEG data have been proposed in the literature, their positive impact on performance is often evaluated on a single dataset and compared to one or two competing augmentation methods. This work proposes to better validate the existing data augmentation approaches through a unified and exhaustive analysis. Approach. We compare quantitatively 13 different augmentations with two different predictive tasks, datasets and models, using three different types of experiments. Main results. We demonstrate that employing the adequate data augmentations can bring up to 45% accuracy improvements in low data regimes compared to the same model trained without any augmentation. Our experiments also show that there is no single best augmentation strategy, as the good augmentations differ on each task. Significance. Our results highlight the best data augmentations to consider for sleep stage classification and motor imagery brain-computer interfaces. More broadly, it demonstrates that EEG classification tasks benefit from adequate data augmentation., (© 2022 IOP Publishing Ltd.)

The polysomnogram (PSG) is the gold standard for evaluating sleep quality and disorders. Attempts to automate this process have been hampered by the complexity of the PSG signals and heterogeneity among subjects and recording hardwares. Most of the existing methods for automatic sleep stage scoring rely on hand-engineered features that require prior knowledge of sleep analysis. This paper presents an end-to-end deep transfer learning framework for automatic feature extraction and sleep stage scoring based on a single-channel EEG. The proposed framework was evaluated over the three primary signals recommended by the American Academy of Sleep Medicine (C4-M1, F4-M1, O2-M1) from two data sets that have different properties and are recorded with different hardware. Different Time-Frequency (TF) imaging approaches were evaluated to generate TF representations for the 30 s EEG sleep epochs, eliminating the need for complex EEG signal pre-processing or manual feature extraction. Several training and detection scenarios were investigated using transfer learning of convolutional neural networks (CNN) and combined with recurrent neural networks. Generating TF images from continuous wavelet transform along with a deep transfer architecture composed of a pre-trained GoogLeNet CNN followed by a bidirectional long short-term memory (BiLSTM) network showed the best scoring performance among all tested scenarios. Using 20-fold cross-validation applied on the C4-M1 channel, the proposed framework achieved an average per-class accuracy of 91.2%, sensitivity of 77%, specificity of 94.1%, and precision of 75.9%. Our results demonstrate that without changing the model architecture and the training algorithm, our model could be applied to different single-channel EEGs from different data sets. Most importantly, the proposed system receives a single EEG epoch as an input at a time and produces a single corresponding output label, making it suitable for real time monitoring outside sleep labs as well as to help sleep lab specialists arrive at a more accurate diagnoses.

An automated sleep stage categorization can readily face noise-contaminated EEG recordings, just as other signal processing applications. Therefore, the denoising of the contaminated signals is inevitable to ensure a reliable analysis of the EEG signals. In this research work, an empirical mode decomposition is used in combination with stacked autoencoders to conduct automatic sleep stage classification with reliable analytical performance. Due to the decomposition of the composite signal into several intrinsic mode functions, empirical mode decomposition offers an effective solution for denoising non-stationary signals such as EEG. Preliminary results showed that through these intrinsic modes, a signal with a high signal-to-noise ratio can be obtained, which can be used for further analysis with confidence. Therefore, later, when statistical features were extracted from the denoised signals and were classified using stacked autoencoders, improved results were obtained for Stage 1, Stage 2, Stage 3, Stage 4, and REM stage EEG signals using this combination.

Automatic sleep stage classification is an effective technology compared to conventional artificial visual inspection in the field of sleep staging. Numerous algorithms based on machine learning and deep learning on single-channel electroencephalogram (EEG) have been proposed in recent years, however, category imbalance and cross-subject discrepancy are still the main factors restricting the accuracy of existing methods. This study proposed an innovative end-to-end neural network to solve these problems, specifically, four data augmentation methods were designed to eliminate category imbalance, and domain adaptation modules were designed for the alignment of marginal distribution, conditional distribution, and channel and spatial level distribution of feature maps, as well as the capture of transferable regions on the feature maps using a transfer attention mechanism. We conducted experiments on two publicly available datasets (Sleep-EDF Database Expanded, 2013 and 2018 version), Cohen's kappa coefficient (k) of 0.77 (Fpz-Cz) and 0.73 (Pz-Oz) were realized on the Sleep-EDF-2013 dataset, and a k of 0.75 (Fpz-Cz) and 0.68 (Pz-Oz) were realized on the Sleep-EDF-2018 dataset. An experiment was also conducted on the dataset drawn from the 2018 Physionet challenge, which containing people with sleep disorders, and a performance improvement was still found. Our comparative experiments with similar studies showed that our model was superior to most other studies, indicating our proposed EEG data augmentation and domain adaptation based cross-subject discrepancy alleviation approach is effective to improve the performance of automatic sleep staging., Competing Interests: Declaration of competing interest None Declared., (Copyright © 2022 Elsevier Ltd. All rights reserved.)

Objective: Alternating Hemiplegia of Childhood (AHC) is characterised by paroxysmal hemiplegic episodes and seizures. Remission of hemiplegia upon sleep is a clinical diagnostic feature of AHC. We investigated whether: 1) Hemiplegic events are associated with spectral EEG changes 2) Sleep in AHC is associated with clinical or EEG spectral features that may explain its restorative effect., Methods: We retrospectively performed EEG spectral analysis in five adults with AHC and twelve age-/gender-matched epilepsy controls. Five-minute epochs of hemiplegic episodes and ten-minute epochs of four sleep stages were selected from video-EEGs. Arousals were counted per hour of sleep., Results: We found 1) hemispheric differences in pre-ictal and ictal spectral power (p = 0.034), during AHC hemiplegic episodes 2) 22% reduced beta power (p = 0.017) and 26% increased delta power (p = 0.025) during wakefulness in AHC versus controls. There were 98% more arousals in the AHC group versus controls (p = 0.0003)., Conclusions: There are hemispheric differences in spectral power preceding hemiplegic episodes in adults with AHC, and sleep is disrupted., Significance: Spectral EEG changes may be a potential predictive tool for AHC hemiplegic episodes. Significantly disrupted sleep is a feature of AHC., Competing Interests: The authors have declared that no competing interests exist.

Sleep stage classification is essential in diagnosing and treating sleep disorders. Many deep learning models have been proposed to classify sleep stages by automatic learning features and temporal context information. These temporal context features come from the intra-epoch temporal features, which represent the overall morphology of an epoch, and temporal features of adjacent epochs and long epochs, which represent the influence between epochs. However, most existing methods do not fully use the complementarity of the three-level temporal features, resulting in incomplete extracted temporal features. To solve this problem, we propose a multilevel temporal context network (MLTCN) to learn the temporal features from intra-epoch, adjacent epochs, and long epochs, which utilizes the complete temporal features to improve classification accuracy. We evaluate the performance of the proposed model on the Sleep-EDF datasets published in 2013 and 2018. The experimental results show that our MLTCN can achieve an overall accuracy of 84.2% and a kappa coefficient of 0.78 on the Sleep-EDF-2013 dataset. On the larger Sleep-EDF-2018 dataset, the overall accuracy is 81.0%, and a kappa coefficient is 0.74. Our model can better assist sleep experts in diagnosing sleep disorders., Competing Interests: The authors declare that they have no conflicts of interest., (Copyright © 2022 Xingfeng Lv et al.)

Objective . Automatic human alertness monitoring has recently become an important research topic with important applications in many areas such as the detection of drivers' fatigue, monitoring of monotonous tasks that require a high level of alertness such as traffic control and nuclear power plant monitoring, and sleep staging. In this study, we propose that balanced dynamics of Electroencephalography (EEG) (so called EEG temporal complexity) is a potentially useful feature for identifying human alertness states. Recently, a new signal entropy measure, called range entropy (RangeEn), was proposed to overcome some limitations of two of the most widely used entropy measures, namely approximate entropy (ApEn) and Sample Entropy (SampEn), and showed its relevance for the study of time domain EEG complexity. In this paper, we investigated whether the RangeEn holds discriminating information associated with human alertness states, namely awake, drowsy, and sleep and compare its performance against those of SampEn and ApEn. Approach . We used EEG data from 60 healthy subjects of both sexes and different ages acquired during whole night sleeps. Using a 30 s sliding window, we computed the three entropy measures of EEG and performed statistical analyses to evaluate the ability of these entropy measures to discriminate among the different human alertness states. Main results . Although the three entropy measures contained useful information about human alertness, RangeEn showed a higher discriminative capability compared to ApEn and SampEn especially when using EEG within the beta frequency band. Significance . Our findings highlight the EEG temporal complexity evolution through the human alertness states. This relationship can potentially be exploited for the development of automatic human alertness monitoring systems and diagnostic tools for different neurological and sleep disorders, including insomnia., (© 2022 Institute of Physics and Engineering in Medicine.)

Automating sleep staging is vital to scale up sleep assessment and diagnosis to serve millions experiencing sleep deprivation and disorders and enable longitudinal sleep monitoring in home environments. Learning from raw polysomnography signals and their derived time-frequency image representations has been prevalent. However, learning from multi-view inputs (e.g., both the raw signals and the time-frequency images) for sleep staging is difficult and not well understood. This work proposes a sequence-to-sequence sleep staging model, XSleepNet, 1 that is capable of learning a joint representation from both raw signals and time-frequency images. Since different views may generalize or overfit at different rates, the proposed network is trained such that the learning pace on each view is adapted based on their generalization/overfitting behavior. In simple terms, the learning on a particular view is speeded up when it is generalizing well and slowed down when it is overfitting. View-specific generalization/overfitting measures are computed on-the-fly during the training course and used to derive weights to blend the gradients from different views. As a result, the network is able to retain the representation power of different views in the joint features which represent the underlying distribution better than those learned by each individual view alone. Furthermore, the XSleepNet architecture is principally designed to gain robustness to the amount of training data and to increase the complementarity between the input views. Experimental results on five databases of different sizes show that XSleepNet consistently outperforms the single-view baselines and the multi-view baseline with a simple fusion strategy. Finally, XSleepNet also outperforms prior sleep staging methods and improves previous state-of-the-art results on the experimental databases.

Study Objectives: To investigate sleep patterns in the camel by combining behavioral and polysomnography (PSG) methods., Methods: A noninvasive PSG study was conducted over four nights on four animals. Additionally, video recordings were used to monitor the sleep behaviors associated with different vigilance states., Results: During the night, short periods of sporadic sleep-like behavior corresponding to a specific posture, sternal recumbency (SR) with the head lying down on the ground, were observed. The PSG results showed rapid shifts between five vigilance states, including wakefulness, drowsiness, rapid eye movement (REM) sleep, non-REM (NREM) sleep, and rumination. The camels typically slept only 1.7 hours per night, subdivided into 0.5 hours of REM sleep and 1.2 hours of NREM sleep. Camels spent most of the night being awake (2.3 hours), ruminating (2.4 hours), or drowsing (1.9 hours). Various combinations of transitions between the different vigilance states were observed, with a notable transition into REM sleep directly from drowsiness (9%) or wakefulness (4%). Behavioral postures were found to correlate with PSG vigilance states, thereby allowing a reliable prediction of the sleep stage based on SR and the head position (erected, motionless, or lying down on the ground). Notably, 100% of REM sleep occurred during the Head Lying Down-SR posture., Conclusions: The camel is a diurnal species with a polyphasic sleep pattern at night. The best correlation between PSG and ethogram data indicates that sleep duration can be predicted by the behavioral method, provided that drowsiness is considered a part of sleep., (© The Author(s) 2022. Published by Oxford University Press on behalf of Sleep Research Society. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.)

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 model's decisions at both the epoch and sequence level. We further propose a simple yet efficient method to quantify uncertainty in the model's 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 transformer's 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.

Despite the progress recently made towards automatic sleep staging for adults, children have complicated sleep structures that require attention to the pediatric sleep staging. Semi-supervised learning, i.e., training networks with both labeled and unlabeled data, greatly reduces the burden of epoch-by-epoch annotation for physicians. However, the inherent class-imbalance problem in sleep staging task undermines the effectiveness of semi-supervised methods such as pseudo-labeling. In this paper, we propose a Bi-Stream Adversarial Learning network (BiSALnet) to generate pseudo-labels with higher confidence for network optimization. Adversarial learning strategy is adopted in Student and Teacher branches of the two-stream networks. The similarity measurement function minimizes the divergence between the outputs of the Student and Teacher branches, and the discriminator continuously enhances its discriminative ability. In addition, we employ a powerful symmetric positive definite (SPD) manifold structure in the Student branch to capture the desired feature distribution properties. The joint discriminative power of convolutional features and nonlinear complex information aggregated by SPD matrices is combined by the attention feature fusion module to improve the sleep stage classification performance. The BiSALnet is tested on pediatric dataset collected from local hospital. Experimental results show that our method yields the overall classification accuracy of 0.80, kappa of 0.73 and F1-score of 0.76. We also examine the generality of our method on a well-known public dataset Sleep-EDF. Our BiSALnet exhibits noticeable performance with accuracy of 0.91, kappa of 0.85 and F1-score of 0.77. Remarkably, we have obtained comparable performance with state-of-the-art supervised approaches with fairly limited labeled data., (Copyright © 2022 Elsevier Inc. All rights reserved.)

Recently there has seen promising results on auto-matic stage scoring by extracting spatio-temporal features from electroencephalogram (EEG). Such methods entail laborious manual feature engineering and domain knowledge. In this study, we propose an adaptive scheme to probabilistically encode, filter and accumulate the input signals and weight the resultant features by the half-Gaussian probabilities of signal intensities. The adaptive representations are subsequently fed into a transformer model to automatically mine the relevance between features and corresponding stages. Extensive exper-iments on the largest public dataset against state-of-the-art methods validate the effectiveness of our proposed method and reveal promising future directions.

Sleep staging is one of the most important parts of sleep assessment and it has an important role in early diagnosis and intervention of sleep disorders. Manual sleep staging requires a specialist and time which can be affected by subjective factors. So that, automatic sleep-scoring method with high accuracy is beneficial. In this work 50 patients sleep data taken from 19 sensors of Philips Alice clinic polysomnography (PSG) device. There is an average of 4772801 data for each individual in a single channel, and approximately 87 million data is processed in 19 channels. Due to the large amount of data, after under sampling technique, dataset is created and Random Forest, Extra Trees and Decision Tree classifiers are applied on it. Although accuracy values vary from one person to another, average of 95.258% for Extra Trees, 95.17% for Random Forest and 91.318% for Decision Tree obtained. Furthermore, precision, recall and F1-score values were also 0.95362, 0.95258 and 0.94568 on average. Beyond the previous works in the area of sleep stage scoring, proposed work differentiated from them by having own database, providing higher accuracy and employing 19 channels. The results showed that the proposed work may alleviate the burden of sleep doctors and speed up sleep scoring., (Copyright © 2022 Elsevier Ltd. All rights reserved.)

Supervised automatic sleep scoring algorithms are usually trained using sleep stage labels manually annotated on 30 s epochs of PSG data. In this study, we investigate the impact of using shorter epochs with various PSG input signals for training and testing a Long Short Term Memory (LSTM) neural network. An LSTM model is evaluated on the provided 30 s epoch sleep stage labels from a publicly available dataset, as well as on 10 s subdivisions. Additionally, three independent scorers re-labeled a subset of the dataset on shorter time windows. The automatic sleep scoring experiments were repeated on the re-annotated subset.The highest performance is achieved on features extracted from 30 s epochs of a single channel frontal EEG. The resulting accuracy, precision and recall were of 92.22%, 67.58% and 66.00% respectively. When using a shorter epoch as input, the performance decreased by approximately 20%. Re-annotating a subset of the dataset on shorter time epochs did not improve the results and further altered the sleep stage detection performance. Our results show that our feature-based LSTM classification algorithm performs better on 30 s PSG epochs when compared to 10 s epochs used as input. Future work could be oriented to determining whether varying the epoch size improves classification outcomes for different types of classification algorithms., (© 2022 Walter de Gruyter GmbH, Berlin/Boston.)

Background and Objective: Single-channel EEG is the most popular choice of sensing modality in sleep staging studies, because it widely conforms to the sleep staging guidelines. The current deep learning method using single-channel EEG signals for sleep staging mainly extracts the features of its surrounding epochs to obtain the short-term temporal context information of EEG epochs, and ignore the influence of the long-term temporal context information on sleep staging. However, the long-term context information includes sleep stage transition rules in a sleep cycle, which can further improve the performance of sleep staging. The aim of this research is to develop a temporal context network to capture the long-term context between EEG sleep stages., Methods: In this paper, we design a sleep staging network named SleepContextNet for sleep stage sequence. SleepContextNet can extract and utilize the long-term temporal context between consecutive EEG epochs, and combine it with the short-term context. we utilize Convolutional Neural Network(CNN) layers for learning representative features from each sleep stage and the representation features sequence learned are fed into a Recurrent Neural Network(RNN) layer for learning long-term and short-term context information among sleep stage in chronological order. In addition, we design a data augmentation algorithm for EEG to retain the long-term context information without changing the number of samples., Results: We evaluate the performance of our proposed network using four public datasets, the 2013 version of Sleep-EDF (SEDF), the 2018 version of Sleep-EDF Expanded (SEDFX), Sleep Heart Health Study (SHHS) and the CAP Sleep Database. The experimental results demonstrate that SleepContextNet outperforms state-of-the-art techniques in terms of different evaluation metrics by capturing long-term and short-term temporal context information. On average, accuracy of 84.8% in SEDF, 82.7% in SEDFX, 86.4% in SHHS and 78.8% in CAP are obtained under subject-independent cross validation., Conclusions: The network extracts the long-term and short-term temporal context information of sleep stages from the sequence features, which utilizes the temporal dependencies among the EEG epochs effectively and improves the accuracy of sleep stages. The sleep staging method based on forward temporal context information is suitable for real-time family sleep monitoring system., Competing Interests: Declaration of Competing Interest Authors declare that there is no conflict of interest in this paper., (Copyright © 2022. Published by Elsevier B.V.)

Sleep is characterized by an intricate variation of brain activity over time. Measuring these temporal sleep dynamics is relevant for elucidating healthy and pathological sleep mechanisms. The rapidly increasing possibilities for obtaining and processing sleep registrations have led to an abundance of data, which can be challenging to analyze and interpret. This review provides a structured overview of approaches to represent temporal sleep dynamics, categorized based on the way the source data is compressed. For each category of representations, we describe advantages and disadvantages. Standard human-defined 30-s sleep stages have the advantages of standardization and interpretability. Alternative human-defined representations are less standardized but offer a higher temporal resolution (in case of microstructural events such as sleep spindles), or reflect non-categorical information (for example spectral power analysis). Machine-learned representations offer additional possibilities: automated sleep stages are useful for handling large quantities of data, while alternative sleep stages obtained from clustering data-driven features could aid finding new patterns and new possible clinical interpretations. While newly developed sleep representations may offer relevant insights, they can be difficult to interpret in for example a clinical context. Therefore, there should always be a balance between developing these sophisticated sleep analysis techniques and maintaining clinical explainability., Competing Interests: Conflicts of interest This work has been performed in the IMPULS framework of the Eindhoven MedTech Innovation Center (e/MTIC, incorporating Eindhoven University of Technology, Philips Research, Sleep Medicine Center Kempenhaeghe). The funders had no role in the study design, decision to publish, or preparation of the manuscript. Philips Research provided support in the form of a salary for authors LWAH, TRML and PF, but did not have any additional role in the study design, data collection and analysis, decision to publish, or preparation of the manuscript. This activity is in part funded by the PPS program research and innovation of the Dutch ministry of Economic affairs and Climate., (Copyright © 2022 The Author(s). Published by Elsevier Ltd.. All rights reserved.)

In everyday life, we have to make decisions under varying degrees of risk. Even though previous research has shown that the manipulation of sleep affects risky decision-making, it remains unknown whether individual, temporally stable neural sleep characteristics relate to individual differences in risk preferences. Here, we collected sleep data under normal conditions in fifty-four healthy adults using a portable high-density EEG at participants' home. Whole-brain corrected for multiple testing, we found that lower slow-wave activity (SWA, an indicator of sleep depth) in a cluster of electrodes over the right prefrontal cortex (PFC) is associated with higher individual risk propensity. Importantly, the association between local sleep depth and risk preferences remained significant when controlling for total sleep time and for time spent in deep sleep, i.e., sleep stages N2 and N3. Moreover, the association between risk preferences and SWA over the right PFC was very similar in all sleep cycles. Because the right PFC plays a central role in cognitive control functions, we speculate that local sleep depth in this area, as reflected by SWA, might serve as a dispositional indicator of self-regulatory ability, which in turn reflects risk preferences., Competing Interests: Declaration of Competing Interest The authors have no conflict of interest to disclose., (Copyright © 2022. Published by Elsevier Inc.)

In humans, sleep spindles are 10- to 16-Hz oscillations lasting approximately 0.5-2 s. Spindles, along with cortical slow oscillations, may facilitate memory consolidation by enabling synaptic plasticity. Early recordings of spindles at the scalp found anterior channels had overall slower frequency than central-posterior channels. This robust, topographical finding led to dichotomizing spindles as "slow" versus "fast," modeled as two distinct spindle generators in frontal versus posterior cortex. Using a large dataset of intracranial stereoelectroencephalographic (sEEG) recordings from 20 patients (13 female, 7 male) and 365 bipolar recordings, we show that the difference in spindle frequency between frontal and parietal channels is comparable to the variability in spindle frequency within the course of individual spindles, across different spindles recorded by a given site, and across sites within a given region. Thus, fast and slow spindles only capture average differences that obscure a much larger underlying overlap in frequency. Furthermore, differences in mean frequency are only one of several ways that spindles differ. For example, compared with parietal, frontal spindles are smaller, tend to occur after parietal when both are engaged, and show a larger decrease in frequency within-spindles. However, frontal and parietal spindles are similar in being longer, less variable, and more widespread than occipital, temporal, and Rolandic spindles. These characteristics are accentuated in spindles which are highly phase-locked to posterior hippocampal spindles. We propose that rather than a strict parietal-fast/frontal-slow dichotomy, spindles differ continuously and quasi-independently in multiple dimensions, with variability due about equally to within-spindle, within-region, and between-region factors. SIGNIFICANCE STATEMENT Sleep spindles are 10- to 16-Hz neural oscillations generated by cortico-thalamic circuits that promote memory consolidation. Spindles are often dichotomized into slow-anterior and fast-posterior categories for cognitive and clinical studies. Here, we show that the anterior-posterior difference in spindle frequency is comparable to that observed between different cycles of individual spindles, between spindles from a given site, or from different sites within a region. Further, we show that spindles vary on other dimensions such as duration, amplitude, spread, primacy and consistency, and that these multiple dimensions vary continuously and largely independently across cortical regions. These findings suggest that multiple continuous variables rather than a strict frequency dichotomy may be more useful biomarkers for memory consolidation or psychiatric disorders., (Copyright © 2022 the authors.)

Modern sleep monitoring development is shifting towards the use of unobtrusive sensors combined with algorithms for automatic sleep scoring. Many different combinations of wet and dry electrodes, ear-centered, forehead-mounted or headband-inspired designs have been proposed, alongside an ever growing variety of machine learning algorithms for automatic sleep scoring., Objective: Among candidate positions, those in the facial area and around the ears have the benefit of being relatively hairless, and in our view deserve extra attention. In this paper, we seek to determine the limits to sleep monitoring quality within this spatial constraint., Methods: We compare 13 different, realistic sensor setups derived from the same data set and analysed with the same pipeline., Results: All setups which include both a lateral and an EOG derivation show similar, state-of-the-art performance, with average Cohen's kappa values of at least 0.80., Conclusion: If large electrode distances are used, positioning is not critical for achieving large sleep-related signal-to-noise-ratio, and hence accurate sleep scoring., Significance: We argue that with the current competitive performance of automated staging approaches, there is a need for establishing an improved benchmark beyond current single human rater scoring.