Simulated quick returns in a laboratory context and effects on sleep and pre-sleep arousal between shifts: a crossover controlled trial

This trial presents a laboratory model investigating the effect of quick returns (QRs, <11 h time off between shifts) on sleep and pre-sleep arousal. Using a crossover design, 63 participants worked a simulated QR condition (8 h time off between consecutive evening- and day shifts) and a day-day (DD) condition (16 h time off between consecutive day shifts). Participants slept at home and sleep was measured using a sleep diary and sleep radar. Compared to the DD condition, the QR condition reduced subjective and objective total sleep time by approximately one hour (both p < .001), reduced time in light- (p < .001), deep- (p = .004), rapid eye movement (REM, p < .001), percentage of REM sleep (p = .023), and subjective sleep quality (p < .001). Remaining sleep parameters and subjective pre-sleep arousal showed no differences between conditions. Results corroborate previous field studies, validating the QR model and indicating causal effects of short rest between shifts on common sleep parameters and sleep architecture.

Wavelet Entropy Analysis of Electroencephalogram Signals During Wake and Different Sleep Stages in Patients with Insomnia Disorder

Objective

To investigate the changes in the wavelet entropy during wake and different sleep stages in patients with insomnia disorder.

Methods

Sixteen patients with insomnia disorder and sixteen normal controls were enrolled. They underwent scale assessment and two consecutive nights of polysomnography (PSG). Wavelet entropy analysis of electroencephalogram (EEG) signals recorded from all participants in the two groups was performed. The changes in the integral wavelet entropy (En) and individual-scale wavelet entropy (En(a)) during wake and different sleep stages in the two groups were observed, and the differences between the two groups were compared.

Results

The insomnia disorder group exhibited lower En during the wake stage, and higher En during the N3 stage compared with the normal control group (all P < 0.001). In terms of En(a), patients with insomnia disorder exhibited lower En(a) in the β and α frequency bands during the wake stage compared with normal controls (β band, P < 0.01; α band, P < 0.001), whereas they showed higher En(a) in the β and α frequency bands during the N3 stage than normal controls (β band, P < 0.001; α band, P < 0.001).

Conclusion

Wavelet entropy can reflect the changes in the complexity of EEG signals during wake and different sleep stages in patients with insomnia disorder, which provides a new method and insights about understanding of pathophysiological mechanisms of insomnia disorder. Wavelet entropy provides an objective indicator for assessing sleep quality.

Alpha anteriorization and theta posteriorization during deep sleep

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.

Performance Evaluation of a New Sport Watch in Sleep Tracking: A Comparison against Overnight Polysomnography in Young Adults

Introduction: This study aimed to validate the ability of a prototype sport watch (Polar Electro Oy, FI) to recognize wake and sleep states in two trials with and without an interval training session (IT) 6 h prior to bedtime. Methods: Thirty-six participants completed this study. Participants performed a maximal aerobic test and three polysomnography (PSG) assessments. The first night served as a device familiarization night and to screen for sleep apnea. The second and third in-home PSG assessments were counterbalanced with/without IT. Accuracy and agreement in detecting sleep stages were calculated between PSG and the prototype. Results: Accuracy for the different sleep stages (REM, N1 and N2, N3, and awake) as a true positive for the nights without exercise was 84 ± 5%, 64 ± 6%, 81 ± 6%, and 91 ± 6%, respectively, and for the nights with exercise was 83 ± 7%, 63 ± 8%, 80 ± 7%, and 92 ± 6%, respectively. The agreement for the sleep night without exercise was 60.1 ± 8.1%, k = 0.39 ± 0.1, and with exercise was 59.2 ± 9.8%, k = 0.36 ± 0.1. No significant differences were observed between nights or between the sexes. Conclusion: The prototype showed better or similar accuracy and agreement to wrist-worn consumer products on the market for the detection of sleep stages with healthy adults. However, further investigations will need to be conducted with other populations.

High prevalence of severe sleep cycle disruption in de novo acromegaly and underdiagnosis by common clinical screening tools: A prospective, observational, cross-sectional study

CONTEXT

Although sleep disordered breathing (SDB) is well-recognised in acromegaly, most studies have reported heterogeneous, often heavily treated, groups and few have performed detailed sleep phenotyping at presentation.

OBJECTIVE

To study SDB using the gold standard of polysomnography, in the largest group of newly-diagnosed, treatment-naïve patients with acromegaly.

SETTING AND PATIENTS

40 patients [22 males, 18 females; mean age 54 years (range 23-78)], were studied to: (i) establish the prevalence and severity of SDB (ii) assess the reliability of commonly employed screening tools [Epworth Sleepiness Scale (ESS) and overnight oxygen desaturation index (DI)] to detect SDB (iii) determine the extent to which sleep architecture is disrupted.

RESULTS

Obstructive sleep apnoea (OSA), defined by the apnoea-hypopnoea index (AHI), was present in 79% of subjects (mild, n = 12; moderate, n = 5; severe, n = 14). However, in these individuals with OSA by AHI criteria, ESS (positive in 35% [n = 11]) and DI (positive in 71%: mild, n = 11; moderate, n = 6; severe, n = 5) markedly underestimated its prevalence/extent. Seventy-eight percent of patients exhibited increased arousal, with marked disruption of the sleep cycle, despite most (82%) having normal total time asleep. Fourteen patients spent longer in stage 1 sleep. Deeper sleep stages were severely attenuated in many subjects (reduced stage 2, n = 18; reduced slow wave sleep, n = 24; reduced rapid eye movement sleep, n = 32).

CONCLUSION

Our study provides strong support for clinical guidelines that recommend screening for sleep apnoea syndrome in patients with newly-diagnosed acromegaly. Importantly, however, it highlights shortcomings in commonly recommended screening tools (questionnaires, desaturation index) and demonstrates the added value of polysomnography to allow timely detection of obstructive sleep apnoea and associated sleep cycle disruption.

Sleep-phasic heart rate variability predicts stress severity: Building a machine learning-based stress prediction model

We propose a novel approach for predicting stress severity by measuring sleep phasic heart rate variability (HRV) using a smart device. This device can potentially be applied for stress self-screening in large populations. Using a Holter electrocardiogram (ECG) and a Huawei smart device, we conducted 24-h dual recordings of 159 medical workers working regular shifts. Based on photoplethysmography (PPG) and accelerometer signals acquired by the Huawei smart device, we sorted episodes of cyclic alternating pattern (CAP; unstable sleep), non-cyclic alternating pattern (NCAP; stable sleep), wakefulness, and rapid eye movement (REM) sleep based on cardiopulmonary coupling (CPC) algorithms. We further calculated the HRV indices during NCAP, CAP and REM sleep episodes using both the Holter ECG and smart-device PPG signals. We later developed a machine learning model to predict stress severity based only on the smart device data obtained from the participants along with a clinical evaluation of emotion and stress conditions. Sleep phasic HRV indices predict individual stress severity with better performance in CAP or REM sleep than in NCAP. Using the smart device data only, the optimal machine learning-based stress prediction model exhibited accuracy of 80.3 %, sensitivity 87.2 %, and 63.9 % for specificity. Sleep phasic heart rate variability can be accurately evaluated using a smart device and subsequently can be used for stress predication.

The neurophysiology of closed-loop auditory stimulation in sleep: A magnetoencephalography study

Closed-loop auditory stimulation (CLAS) is a brain modulation technique in which sounds are timed to enhance or disrupt endogenous neurophysiological events. CLAS of slow oscillation up-states in sleep is becoming a popular tool to study and enhance sleep's functions, as it increases slow oscillations, evokes sleep spindles and enhances memory consolidation of certain tasks. However, few studies have examined the specific neurophysiological mechanisms involved in CLAS, in part because of practical limitations to available tools. To evaluate evidence for possible models of how sound stimulation during brain up-states alters brain activity, we simultaneously recorded electro- and magnetoencephalography in human participants who received auditory stimulation across sleep stages. We conducted a series of analyses that test different models of pathways through which CLAS of slow oscillations may affect widespread neural activity that have been suggested in literature, using spatial information, timing and phase relationships in the source-localized magnetoencephalography data. The results suggest that auditory information reaches ventral frontal lobe areas via non-lemniscal pathways. From there, a slow oscillation is created and propagated. We demonstrate that while the state of excitability of tissue in auditory cortex and frontal ventral regions shows some synchrony with the electroencephalography (EEG)-recorded up-states that are commonly used for CLAS, it is the state of ventral frontal regions that is most critical for slow oscillation generation. Our findings advance models of how CLAS leads to enhancement of slow oscillations, sleep spindles and associated cognitive benefits and offer insight into how the effectiveness of brain stimulation techniques can be improved.

An acute bout of high-intensity exercise affects nocturnal sleep and sleep-dependent memory consolidation

Acute exercise has been shown to affect long-term memory and sleep. However, it is unclear whether exercise-induced changes in sleep architecture are associated with enhanced memory. Recently, it has been shown that exercise followed by a nap improved declarative memory. Whether these effects transfer to night sleep and other memory domains has not yet been studied. Here, we investigate the influence of exercise on nocturnal sleep architecture and associations with sleep-dependent procedural and declarative memory consolidation. Nineteen subjects (23.68 ± 3.97 years) were tested in a balanced cross-over design. In two evening sessions, participants either exercised (high-intensity interval training) or rested immediately after encoding two memory tasks: (1) a finger tapping task and (2) a paired-associate learning task. Subsequent nocturnal sleep was recorded by polysomnography. Retrieval was conducted the following morning. High-intensity interval training lead to an increased declarative memory retention (p = 0.047, d = 0.40) along with a decrease in REM sleep (p = 0.012, d = 0.75). Neither procedural memory nor NREM sleep were significantly affected. Exercise-induced changes in N2 showed a positive correlation with procedural memory retention which did not withstand multiple comparison correction. Exploratory analyses on sleep spindles and slow wave activity did not reveal significant effects. The present findings suggest an exercise-induced enhancement of declarative memory which aligns with changes in nocturnal sleep architecture. This gives additional support for the idea of a potential link between exercise-induced sleep modifications and memory formation which requires further investigation in larger scaled studies.

Standardized image-based polysomnography database and deep learning algorithm for sleep-stage classification

STUDY OBJECTIVES

Polysomnography (PSG) scoring is labor-intensive, subjective, and often ambiguous. Recently several deep learning (DL) models for automated sleep scoring have been developed, they are tied to a fixed amount of input channels and resolution. In this study, we constructed a standardized image-based PSG dataset in order to overcome the heterogeneity of raw signal data obtained from various PSG devices and various sleep laboratory environments.

METHODS

All individually exported European data format files containing raw signals were converted into images with an annotation file, which contained the demographics, diagnoses, and sleep statistics. An image-based DL model for automatic sleep staging was developed, compared with a signal-based model, and validated in an external dataset.

RESULTS

We constructed 10253 image-based PSG datasets using a standardized format. Among these, 7745 diagnostic PSG data were used to develop our DL model. The DL model using the image dataset showed similar performance to the signal-based dataset for the same subject. The overall DL accuracy was greater than 80%, even with severe obstructive sleep apnea. Moreover, for the first time, we showed explainable DL in the field of sleep medicine as visualized key inference regions using Eigen-class activation maps. Furthermore, when a DL model for sleep scoring performs external validation, we achieved a relatively good performance.

CONCLUSIONS

Our main contribution demonstrates the availability of a standardized image-based dataset, and highlights that changing the data sampling rate or number of sensors may not require retraining, although performance decreases slightly as the number of sensors decreases.

Maternal cardiorespiratory coupling: differences between pregnant and nonpregnant women are further amplified by sleep-stage stratification

Pregnancy complications are associated with abnormal maternal autonomic regulation. Subsequently, thoroughly understanding maternal autonomic regulation during healthy pregnancy may enable the earlier detection of complications, in turn allowing for the improved management thereof. Under healthy autonomic regulation, reciprocal interactions occur between the cardiac and respiratory systems, i.e., cardiorespiratory coupling (CRC). Here, we investigate, for the first time, the differences in CRC between healthy pregnant and nonpregnant women. We apply two algorithms, namely, synchrograms and bivariate phase-rectified signal averaging, to nighttime recordings of ECG and respiratory signals. We find that CRC is present in both groups. Significantly less (P < 0.01) cardiorespiratory synchronization occurs in pregnant women (11% vs. 15% in nonpregnant women). Moreover, there is a smaller response in the heart rate of pregnant women corresponding to respiratory inhalations and exhalations. In addition, we stratified these analyses by sleep stages. As each sleep stage is governed by different autonomic states, this stratification not only amplified some of the differences between groups but also brought out differences that remained hidden when analyzing the full-night recordings. Most notably, the known positive relationship between CRC and deep sleep is less prominent in pregnant women than in their nonpregnant counterparts. The decrease in CRC during healthy pregnancy may be attributable to decreased maternal parasympathetic activity, anatomical changes to the maternal respiratory system, and the increased physiological stress accompanying pregnancy. This work offers novel insight into the physiology of healthy pregnancy and forms part of the base knowledge needed to detect abnormalities in pregnancy.NEW & NOTEWORTHY We compare CRC, i.e., the reciprocal interaction between the cardiac and respiratory systems, between healthy pregnant and nonpregnant women for the first time. Although CRC is present in both groups, CRC is reduced during healthy pregnancy; there is less synchronization between maternal cardiac and respiratory activity and a smaller response in maternal heart rate to respiratory inhalations and exhalations. Stratifying this analysis by sleep stages reveals that differences are most prominent during deep sleep.

An effective hybrid feature selection using entropy weight method for automatic sleep staging

Objective. Sleep staging is the basis for sleep quality assessment and diagnosis of sleep-related disorders. In response to the inadequacy of traditional manual judgement of sleep stages, using machine learning techniques for automatic sleep staging has become a hot topic. To improve the performance of sleep staging, numerous studies have extracted a large number of sleep-related characteristics. However, there are redundant and irrelevant features in the high-dimensional features that reduce the classification accuracy. To address this issue, an effective hybrid feature selection method based on the entropy weight method is proposed in this paper for automatic sleep staging.Approach. Firstly, we preprocess the four modal polysomnography (PSG) signals, including electroencephalogram (EEG), electrooculogram (EOG), electrocardiogram (ECG) and electromyogram (EMG). Secondly, the time domain, frequency domain and nonlinear features are extracted from the preprocessed signals, with a total of 185 features. Then, in order to acquire characteristics of the multi-modal signals that are highly correlated with the sleep stages, the proposed hybrid feature selection method is applied to choose effective features. This method is divided into two stages. In stage I, the entropy weight method is employed to combine two filter methods to build a subset of features. This stage evaluates features based on information theory and distance metrics, which can quickly obtain a subset of features and retain the relevant features. In stage II, Sequential Forward Selection is used to evaluate the subset of features and eliminate redundant features. Further more, to achieve better performance of classification, an ensemble model based on support vector machine, K-nearest neighbor, random forest and multilayer perceptron is finally constructed for classifying sleep stages.Main results. The experiment using the Cyclic Alternating Pattern (CAP) sleep database is performed to assess the performance of the method proposed in this paper. The proposed hybrid feature selection method chooses only 30 features highly correlated to sleep stages. The accuracy, F1 score and Kappa coefficient of 6 class sleep staging reach 88.86%, 83.15% and 0.8531%, respectively.Significance. Experimental results show the effectiveness of the proposed method compared to the existing state-of-the-art studies. It greatly reduces the number of features required while achieving outstanding auto-sleep staging results.

Effect of depression on phase coherence between respiratory sinus arrhythmia and respiration during sleep in patients with obstructive sleep apnea

Introduction: A high prevalence of major depressive disorder (MDD) among Obstructive Sleep Apnea (OSA) patients has been observed in both community and clinical populations. Due to the overlapping symptoms between both disorders, depression is usually misdiagnosed when correlated with OSA. Phase coherence between respiratory sinus arrhythmia (RSA) and respiration (λ RSA-RESP) has been proposed as an alternative measure for assessing vagal activity. Therefore, this study aims to investigate if there is any difference in λ RSA-RESP in OSA patients with and without MDD. Methods: Electrocardiograms (ECG) and breathing signals using overnight polysomnography were collected from 40 OSA subjects with MDD (OSAD+), 40 OSA subjects without MDD (OSAD-), and 38 control subjects (Controls) without MDD and OSA. The interbeat intervals (RRI) and respiratory movement were extracted from 5-min segments of ECG signals with a single apneic event during non-rapid eye movement (NREM) [353 segments] and rapid eye movement (REM) sleep stages [298 segments]. RR intervals (RRI) and respiration were resampled at 10 Hz, and the band passed filtered (0.10-0.4 Hz) before the Hilbert transform was used to extract instantaneous phases of the RSA and respiration. Subsequently, the λ RSA-RESP between RSA and Respiration and Heart Rate Variability (HRV) features were computed. Results: Our results showed that λ RSA-RESP was significantly increased in the OSAD+ group compared to OSAD- group during NREM and REM sleep. This increase was accompanied by a decrease in the low frequency (LF) component of HRV. Discussion: We report that the phase synchronization index between RSA and respiratory movement could provide a useful measure for evaluating depression in OSA patients. Our findings suggest that depression has lowered sympathetic activity when accompanied by OSA, allowing for stronger synchronization between RSA and respiration.

REM Sleep Stage Identification with Raw Single-Channel EEG

This paper focused on creating an interpretable model for automatic rapid eye movement (REM) and non-REM sleep stage scoring for a single-channel electroencephalogram (EEG). Many methods attempt to extract meaningful information to provide to a learning algorithm. This method attempts to let the model extract the meaningful interpretable information by providing a smaller number of time-invariant signal filters for five frequency ranges using five CNN algorithms. A bi-directional GRU algorithm was applied to the output to incorporate time transition information. Training and tests were run on the well-known sleep-EDF-expanded database. The best results produced 97% accuracy, 93% precision, and 89% recall.

A Systematic Review of Publications on the Associations Between Sleep Architecture and Arterial Hypertension

Sleep research has garnered substantial interest among scientists owing to its correlation with various diseases, particularly elevated blood pressure observed in patients with obstructive sleep apnea. This systematic review aims to identify and analyze publications exploring the associations between sleep architecture and arterial hypertension. A comprehensive search of PubMed (MEDLINE), Scopus, and Embase databases yielded 111 reports, of which 7 manuscripts were included in the review. Four of the studies reported a significant reduction in the duration of the N3 phase of sleep in hypertensive patients, while 2 studies found a statistically significant reduction in the duration of the N2 and rapid eye movement (REM) stages of sleep. Three studies indicated increased sleep fragmentation in hypertensive patients. They showed a longer duration of the N1 stage of sleep, shorter duration of overall sleep time, and an increased apnea-hypopnea index in hypertensive patients. These findings underscore the association between the duration of non-REM/REM sleep stages and elevated BP, providing substantial evidence. Moreover, a notable increase in sleep fragmentation was observed among patients with hypertension. However, further research is warranted to expand and deepen our understanding of this intricate relationship. This systematic review serves as a valuable resource, guiding future investigations and contributing to advancements in the field of sleep and arterial hypertension.

Mixed-Input Deep Learning Approach to Sleep/Wake State Classification by Using EEG Signals

Sleep stage classification plays a pivotal role in predicting and diagnosing numerous health issues from human sleep data. Manual sleep staging requires human expertise, which is occasionally prone to error and variation. In recent times, availability of polysomnography data has aided progress in automatic sleep-stage classification. In this paper, a hybrid deep learning model is proposed for classifying sleep and wake states based on a single-channel electroencephalogram (EEG) signal. The model combines an artificial neural network (ANN) and a convolutional neural network (CNN) trained using mixed-input features. The ANN makes use of statistical features calculated from EEG epochs, and the CNN operates on Hilbert spectrum images generated during each epoch. The proposed method is assessed using single-channel Pz-Oz EEG signals from the Sleep-EDF database Expanded. The classification performance on four randomly selected individuals shows that the proposed model can achieve accuracy of around 96% in classifying between sleep and wake states from EEG recordings.

Automated sleep staging in people with intellectual disabilities using heart rate and respiration variability

BACKGROUND

People with intellectual disabilities (ID) have a higher risk of sleep disorders. Polysomnography (PSG) remains the diagnostic gold standard in sleep medicine. However, PSG in people with ID can be challenging, as sensors can be burdensome and have a negative influence on sleep. Alternative methods of assessing sleep have been proposed that could potentially transfer to less obtrusive monitoring devices. The goal of this study was to investigate whether analysis of heart rate variability and respiration variability is suitable for the automatic scoring of sleep stages in sleep-disordered people with ID.

METHODS

Manually scored sleep stages in PSGs of 73 people with ID (borderline to profound) were compared with the scoring of sleep stages by the CardioRespiratory Sleep Staging (CReSS) algorithm. CReSS uses cardiac and/or respiratory input to score the different sleep stages. Performance of the algorithm was analysed using input from electrocardiogram (ECG), respiratory effort and a combination of both. Agreement was determined by means of epoch-per-epoch Cohen's kappa coefficient. The influence of demographics, comorbidities and potential manual scoring difficulties (based on comments in the PSG report) was explored.

RESULTS

The use of CReSS with combination of both ECG and respiratory effort provided the best agreement in scoring sleep and wake when compared with manually scored PSG (PSG versus ECG = kappa 0.56, PSG versus respiratory effort = kappa 0.53 and PSG versus both = kappa 0.62). Presence of epilepsy or difficulties in manually scoring sleep stages negatively influenced agreement significantly, but nevertheless, performance remained acceptable. In people with ID without epilepsy, the average kappa approximated that of the general population with sleep disorders.

CONCLUSIONS

Using analysis of heart rate and respiration variability, sleep stages can be estimated in people with ID. This could in the future lead to less obtrusive measurements of sleep using, for example, wearables, more suitable to this population.

Prediction of Sleep Stages Via Deep Learning Using Smartphone Audio Recordings in Home Environments: Model Development and Validation

BACKGROUND

The growing public interest and awareness regarding the significance of sleep is driving the demand for sleep monitoring at home. In addition to various commercially available wearable and nearable devices, sound-based sleep staging via deep learning is emerging as a decent alternative for their convenience and potential accuracy. However, sound-based sleep staging has only been studied using in-laboratory sound data. In real-world sleep environments (homes), there is abundant background noise, in contrast to quiet, controlled environments such as laboratories. The use of sound-based sleep staging at homes has not been investigated while it is essential for practical use on a daily basis. Challenges are the lack of and the expected huge expense of acquiring a sufficient size of home data annotated with sleep stages to train a large-scale neural network.

OBJECTIVE

This study aims to develop and validate a deep learning method to perform sound-based sleep staging using audio recordings achieved from various uncontrolled home environments.

METHODS

To overcome the limitation of lacking home data with known sleep stages, we adopted advanced training techniques and combined home data with hospital data. The training of the model consisted of 3 components: (1) the original supervised learning using 812 pairs of hospital polysomnography (PSG) and audio recordings, and the 2 newly adopted components; (2) transfer learning from hospital to home sounds by adding 829 smartphone audio recordings at home; and (3) consistency training using augmented hospital sound data. Augmented data were created by adding 8255 home noise data to hospital audio recordings. Besides, an independent test set was built by collecting 45 pairs of overnight PSG and smartphone audio recording at homes to examine the performance of the trained model.

RESULTS

The accuracy of the model was 76.2% (63.4% for wake, 64.9% for rapid-eye movement [REM], and 83.6% for non-REM) for our test set. The macro F1-score and mean per-class sensitivity were 0.714 and 0.706, respectively. The performance was robust across demographic groups such as age, gender, BMI, or sleep apnea severity (accuracy 73.4%-79.4%). In the ablation study, we evaluated the contribution of each component. While the supervised learning alone achieved accuracy of 69.2% on home sound data, adding consistency training to the supervised learning helped increase the accuracy to a larger degree (+4.3%) than adding transfer learning (+0.1%). The best performance was shown when both transfer learning and consistency training were adopted (+7.0%).

CONCLUSIONS

This study shows that sound-based sleep staging is feasible for home use. By adopting 2 advanced techniques (transfer learning and consistency training) the deep learning model robustly predicts sleep stages using sounds recorded at various uncontrolled home environments, without using any special equipment but smartphones only.

Evaluation of the Accuracy of Contactless Consumer Sleep-Tracking Devices Application in Human Experiment: A Systematic Review and Meta-Analysis

Compared with the gold standard, polysomnography (PSG), and silver standard, actigraphy, contactless consumer sleep-tracking devices (CCSTDs) are more advantageous for implementing large-sample and long-period experiments in the field and out of the laboratory due to their low price, convenience, and unobtrusiveness. This review aimed to examine the effectiveness of CCSTDs application in human experiments. A systematic review and meta-analysis (PRISMA) of their performance in monitoring sleep parameters were conducted (PROSPERO: CRD42022342378). PubMed, EMBASE, Cochrane CENTRALE, and Web of Science were searched, and 26 articles were qualified for systematic review, of which 22 provided quantitative data for meta-analysis. The findings show that CCSTDs had a better accuracy in the experimental group of healthy participants who wore mattress-based devices with piezoelectric sensors. CCSTDs' performance in distinguishing waking from sleeping epochs is as good as that of actigraphy. Moreover, CCSTDs provide data on sleep stages that are not available when actigraphy is used. Therefore, CCSTDs could be an effective alternative tool to PSG and actigraphy in human experiments.

The memory sources of dreams: serial awakenings across sleep stages and time of night

Memories of waking-life events are incorporated into dreams, but their incorporation is not uniform across a night of sleep. This study aimed to elucidate ways in which such memory sources vary by sleep stage and time of night. Twenty healthy participants (11 F; 24.1 ± 5.7 years) spent a night in the laboratory and were awakened for dream collection approximately 12 times spread across early, middle, and late periods of sleep, while covering all stages of sleep (N1, N2, N3, REM). In the morning, participants identified and dated associated memories of waking-life events for each dream report, when possible. The incorporation of recent memory sources in dreams was more frequent in N1 and REM than in other sleep stages. The incorporation of distant memories from over a week ago, semantic memories not traceable to a single event, and anticipated future events remained stable throughout sleep. In contrast, the relative proportions of recent versus distant memory sources changed across the night, independently of sleep stage, with late-night dreams in all stages having relatively less recent and more remote memory sources than dreams earlier in the night. Qualitatively, dreams tended to repeat similar themes across the night and in different sleep stages. The present findings clarify the temporal course of memory incorporations in dreams, highlighting a specific connection between time of night and the temporal remoteness of memories. We discuss how dream content may, at least in part, reflect the mechanisms of sleep-dependent memory consolidation.

Association of Hypovitaminosis D with Sleep Parameters in Rotating Shift Worker Drivers

Objective  To evaluate the association between sleep parameters and hypovitaminosis D in rotating shift drivers. Material and Methods  We conducted a cross-sectional study on 82 male rotating shift workers (24-57 years old) with at least one cardiovascular risk factor (such as hyperglycemia, dyslipidemia, abdominal obesity, physical inactivity, hypertension, and smoking). Polysomnography was used to evaluate sleep parameters. Logistic regression was used to model the association between hypovitaminosis D and sleep parameters after adjustment for relevant covariates. Results  Hypovitaminosis D (< 20 ng/mL) was seen in 30.5% of the workers. Shift workers with hypovitaminosis D had lower sleep efficiency (odds ratio [OR]: 3.68; 95% confidence interval [CI]: 1.95-5.53), lower arterial oxygen saturation (OR: 5.35; 95% CI: 3.37-6.12), and increased microarousal index (OR: 3.85; 95% CI: 1.26-5.63) after adjusting. Conclusion  We suggest that hypovitaminosis D is associated with greater sleep disturbances in rotating shift workers.

Central Apneic Event Prevalence in REM and NREM Sleep in OSA Patients: A Retrospective, Exploratory Study

Patients with sleep-disordered breathing show a combination of different respiratory events (central, obstructive, mixed), with one type being predominant. We observed a reduced prevalence of central apneic events (CAEs) during REM sleep compared to NREM sleep in patients with predominant obstructive sleep apnea (OSA). The aim of this retrospective, exploratory study was to describe this finding and to suggest pathophysiological explanations. The polysomnography (PSG) data of 141 OSA patients were assessed for the prevalence of CAEs during REM and NREM sleep. On the basis of the apnea-hypopnea index (AHI), patients were divided into three OSA severity groups (mild: AHI < 15/h; moderate: AHI = 15-30/h; severe: AHI > 30/h). We compared the frequency of CAEs adjusted for the relative length of REM and NREM sleep time, and a significantly increased frequency of CAEs in NREM was found only in severely affected OSA patients. Given that the emergence of CAEs is strongly associated with the chemosensitivity of the brainstem nuclei regulating breathing mechanics in humans, a sleep-stage-dependent chemosensitivity is proposed. REM-sleep-associated neuronal circuits in humans may act protectively against the emergence of CAEs, possibly by reducing chemosensitivity. On the contrary, a significant increase in the chemosensitivity of the brainstem nuclei during NREM sleep is suggested.

Scoring sleep with artificial intelligence enables quantification of sleep stage ambiguity: hypnodensity based on multiple expert scorers and auto-scoring

STUDY OBJECTIVES

To quantify the amount of sleep stage ambiguity across expert scorers and to validate a new auto-scoring platform against sleep staging performed by multiple scorers.

METHODS

We applied a new auto-scoring system to three datasets containing 95 PSGs scored by 6-12 scorers, to compare sleep stage probabilities (hypnodensity; i.e. the probability of each sleep stage being assigned to a given epoch) as the primary output, as well as a single sleep stage per epoch assigned by hierarchical majority rule.

RESULTS

The percentage of epochs with 100% agreement across scorers was 46 ± 9%, 38 ± 10% and 32 ± 9% for the datasets with 6, 9, and 12 scorers, respectively. The mean intra-class correlation coefficient between sleep stage probabilities from auto- and manual-scoring was 0.91, representing excellent reliability. Within each dataset, agreement between auto-scoring and consensus manual-scoring was significantly higher than agreement between manual-scoring and consensus manual-scoring (0.78 vs. 0.69; 0.74 vs. 0.67; and 0.75 vs. 0.67; all p < 0.01).

CONCLUSIONS

Analysis of scoring performed by multiple scorers reveals that sleep stage ambiguity is the rule rather than the exception. Probabilities of the sleep stages determined by artificial intelligence auto-scoring provide an excellent estimate of this ambiguity. Compared to consensus manual-scoring, sleep staging derived from auto-scoring is for each individual PSG noninferior to manual-scoring meaning that auto-scoring output is ready for interpretation without the need for manual adjustment.

Peripheral blood flow estimated by laser doppler flowmetry provides additional information about sleep state beyond that provided by pulse rate variability

Pulse rate variability (PRV), derived from Laser Doppler flowmetry (LDF) or photoplethysmography, has recently become widely used for sleep state assessment, although it cannot identify all the sleep stages. Peripheral blood flow (BF), also estimated by LDF, may be modulated by sleep stages; however, few studies have explored its potential for assessing sleep state. Thus, we aimed to investigate whether peripheral BF could provide information about sleep stages, and thus improve sleep state assessment. We performed electrocardiography and simultaneously recorded BF signals by LDF from the right-index finger and ear concha of 45 healthy participants (13 women; mean age, 22.5 ± 3.4 years) during one night of polysomnographic recording. Time- and frequency-domain parameters of peripheral BF, and time-domain, frequency-domain, and non-linear indices of PRV and heart rate variability (HRV) were calculated. Finger-BF parameters in the time and frequency domains provided information about different sleep stages, some of which (such as the difference between N1 and rapid eye movement sleep) were not revealed by finger-PRV. In addition, finger-PRV patterns and HRV patterns were similar for most parameters. Further, both finger- and ear-BF results showed 0.2-0.3 Hz oscillations that varied with sleep stages, with a significant increase in N3, suggesting a modulation of respiration within this frequency band. These results showed that peripheral BF could provide information for different sleep stages, some of which was complementary to the information provided by PRV. Furthermore, the combination of peripheral BF and PRV may be more advantageous than HRV alone in assessing sleep states and related autonomic nervous activity.

Measuring Sleep Stages and Screening for Obstructive Sleep Apnea with a Wearable Multi-Sensor System in Comparison to Polysomnography

Objective

To assess the performance of a wearable multi-sensor system (SensEcho) in comparison to polysomnography (PSG) in measuring sleep stages and searching for obstructive sleep apnea (OSA).

Methods

Participants underwent overnight simultaneous monitoring using SensEcho and PSG in a sleep laboratory. SensEcho analyzed the recordings spontaneously, and PSG was assessed as per standard guidelines. The degree of snoring was evaluated according to the guidelines for the diagnosis and treatment of OSA hypopnea syndrome (2011 revision). The Epworth Sleepiness Scale (ESS) was used to assess general daytime sleepiness.

Results

This study included 103 Han Chinese, 91 of whom (age 39.02 ± 13.84 years, body mass index 27.28 ± 5.12 kg/m2, 61.54% male) completed the assessments. The measures of total sleep time (P = 0.198); total wake time (P = 0.182); shallow sleep (P = 0.297), deep sleep (P = 0.422), rapid eye movement sleep (P = 0.570), and awake (P = 0.336) proportions were similar between SensEcho and PSG. Using an apnea-hypopnea index (AHI) cutoff of ≥ 5 events/h, the SensEcho had 82.69% sensitivity and 89.74% specificity. Almost the same results were obtained at an AHI threshold of ≥ 15 events/h. Although the specificity increased to 94.67%, it decreased to 43.75% at an AHI cutoff of ≥ 30 events/h.

Conclusion

This study demonstrated that SensEcho can be used to evaluate sleep status and screen for OSA. Nevertheless, improving the accuracy of its assessment of severe OSA and further testing its effectiveness in community and home environments is necessary.

Benzodiazepines and Sleep Architecture: A Systematic Review

BACKGROUND

Insomnia, defined as a difficulty in initiating or maintaining sleep, is a relevant medical issue. Benzodiazepines (BZDs) are commonly prescribed to treat insomnia. Two phases characterize human sleep structure: sleep with Non-Rapid Eye Movement (NREM) and sleep with Rapid Eye Movement (REM). Physiological sleep includes NREM and REM phases in a continuous cycle known as "Sleep Architecture."

OBJECTIVE

This systematic review summarizes the studies that have investigated effects of BZDs on Sleep Architecture.

METHODS

The articles selection included human clinical trials (in English, Portuguese, or Spanish) only, specifically focused on BZDs effects on sleep architecture. PubMed, BVS, and Google Scholar databases were searched.

RESULTS

Findings on BZDs effects on sleep architecture confirm an increase in stage 2 of NREM sleep and a decrease in time of stages 3 and 4 of NREM sleep with a reduction in time of REM sleep during the nocturnal sleep.

CONCLUSION

Variations in NREM and REM sleep may lead to deficits in concentration and working memory and weight gain. The increase in stage 2 of NREM sleep may lead to a subjective improvement of sleep quality with no awakenings. BZDz should be prescribed with zeal and professional judgment. These patients should be closely monitored for possible long-term side effects.

A model of autonomous interactions between hippocampus and neocortex driving sleep-dependent memory consolidation

How do we build up our knowledge of the world over time? Many theories of memory formation and consolidation have posited that the hippocampus stores new information, then "teaches" this information to the neocortex over time, especially during sleep. But it is unclear, mechanistically, how this actually works-How are these systems able to interact during periods with virtually no environmental input to accomplish useful learning and shifts in representation? We provide a framework for thinking about this question, with neural network model simulations serving as demonstrations. The model is composed of hippocampus and neocortical areas, which replay memories and interact with one another completely autonomously during simulated sleep. Oscillations are leveraged to support error-driven learning that leads to useful changes in memory representation and behavior. The model has a non-rapid eye movement (NREM) sleep stage, where dynamics between the hippocampus and neocortex are tightly coupled, with the hippocampus helping neocortex to reinstate high-fidelity versions of new attractors, and a REM sleep stage, where neocortex is able to more freely explore existing attractors. We find that alternating between NREM and REM sleep stages, which alternately focuses the model's replay on recent and remote information, facilitates graceful continual learning. We thus provide an account of how the hippocampus and neocortex can interact without any external input during sleep to drive useful new cortical learning and to protect old knowledge as new information is integrated.

An Automated Wavelet-Based Sleep Scoring Model Using EEG, EMG, and EOG Signals with More Than 8000 Subjects

Human life necessitates high-quality sleep. However, humans suffer from a lower quality of life because of sleep disorders. The identification of sleep stages is necessary to predict the quality of sleep. Manual sleep-stage scoring is frequently conducted through sleep experts’ visually evaluations of a patient’s neurophysiological data, gathered in sleep laboratories. Manually scoring sleep is a tough, time-intensive, tiresome, and highly subjective activity. Hence, the need of creating automatic sleep-stage classification has risen due to the limitations imposed by manual sleep-stage scoring methods. In this study, a novel machine learning model is developed using dual-channel unipolar electroencephalogram (EEG), chin electromyogram (EMG), and dual-channel electrooculgram (EOG) signals. Using an optimum orthogonal filter bank, sub-bands are obtained by decomposing 30 s epochs of signals. Tsallis entropies are then calculated from the coefficients of these sub-bands. Then, these features are fed an ensemble bagged tree (EBT) classifier for automated sleep classification. We developed our automated sleep classification model using the Sleep Heart Health Study (SHHS) database, which contains two parts, SHHS-1 and SHHS-2, containing more than 8455 subjects with more than 75,000 h of recordings. The proposed model separated three classes if sleep: rapid eye movement (REM), non-REM, and wake, with a classification accuracy of 90.70% and 91.80% using the SHHS-1 and SHHS-2 datasets, respectively. For the five-class problem, the model produces a classification accuracy of 84.3% and 86.3%, corresponding to the SHHS-1 and SHHS-2 databases, respectively, to classify wake, N1, N2, N3, and REM sleep stages. The model acquired Cohen’s kappa (κ) coefficients as 0.838 with SHHS-1 and 0.86 with SHHS-2 for the three-class classification problem. Similarly, the model achieved Cohen’s κ of 0.7746 for SHHS-1 and 0.8007 for SHHS-2 in five-class classification tasks. The model proposed in this study has achieved better performance than the best existing methods. Moreover, the model that has been proposed has been developed to classify sleep stages for both good sleepers as well as patients suffering from sleep disorders. Thus, the proposed wavelet Tsallis entropy-based model is robust and accurate and may help clinicians to comprehend and interpret sleep stages efficiently.

Validation Study on Automated Sleep Stage Scoring Using a Deep Learning Algorithm

Background and Objectives: Polysomnography is manually scored by sleep experts. However, manual scoring is a time-consuming and labor-intensive task. The goal of this study was to verify the accuracy of automated sleep-stage scoring based on a deep learning algorithm compared to manual sleep-stage scoring. Materials and Methods: A total of 602 polysomnography datasets from subjects (Male:Female = 397:205) aged 19 to 65 years (mean age, 43.8, standard deviation = 12.2) were included in the study. The performance of the proposed model was evaluated based on kappa value and bootstrapped point-estimate of median percent agreement with a 95% bootstrap confidence interval and R = 1000. The proposed model was trained using 482 datasets and validated using 48 datasets. For testing, 72 datasets were selected randomly. Results: The proposed model exhibited good concordance rates with manual scoring for stages W (94%), N1 (83.9%), N2 (89%), N3 (92%), and R (93%). The average kappa value was 0.84. For the bootstrap method, high overall agreement between the automated deep learning algorithm and manual scoring was observed in stages W (98%), N1 (94%), N2 (92%), N3 (99%), and R (98%) and total (96%). Conclusions: Automated sleep-stage scoring using the proposed model may be a reliable method for sleep-stage classification.

Quantitative Evaluation of EEG-Biomarkers for Prediction of Sleep Stages

Electroencephalography (EEG) is immediate and sensitive to neurological changes resulting from sleep stages and is considered a computing tool for understanding the association between neurological outcomes and sleep stages. EEG is expected to be an efficient approach for sleep stage prediction outside a highly equipped clinical setting compared with multimodal physiological signal-based polysomnography. This study aims to quantify the neurological EEG-biomarkers and predict five-class sleep stages using sleep EEG data. We investigated the three-channel EEG sleep recordings of 154 individuals (mean age of 53.8 ± 15.4 years) from the Haaglanden Medisch Centrum (HMC, The Hague, The Netherlands) open-access public dataset of PhysioNet. The power of fast-wave alpha, beta, and gamma rhythms decreases; and the power of slow-wave delta and theta oscillations gradually increases as sleep becomes deeper. Delta wave power ratios (DAR, DTR, and DTABR) may be considered biomarkers for their characteristics of attenuation in NREM sleep and subsequent increase in REM sleep. The overall accuracy of the C5.0, Neural Network, and CHAID machine-learning models are 91%, 89%, and 84%, respectively, for multi-class classification of the sleep stages. The EEG-based sleep stage prediction approach is expected to be utilized in a wearable sleep monitoring system.

End-to-End Sleep Staging Using Nocturnal Sounds from Microphone Chips for Mobile Devices

PURPOSE

Nocturnal sounds contain numerous information and are easily obtainable by a non-contact manner. Sleep staging using nocturnal sounds recorded from common mobile devices may allow daily at-home sleep tracking. The objective of this study is to introduce an end-to-end (sound-to-sleep stages) deep learning model for sound-based sleep staging designed to work with audio from microphone chips, which are essential in mobile devices such as modern smartphones.

PATIENTS AND METHODS

Two different audio datasets were used: audio data routinely recorded by a solitary microphone chip during polysomnography (PSG dataset, N=1154) and audio data recorded by a smartphone (smartphone dataset, N=327). The audio was converted into Mel spectrogram to detect latent temporal frequency patterns of breathing and body movement from ambient noise. The proposed neural network model learns to first extract features from each 30-second epoch and then analyze inter-epoch relationships of extracted features to finally classify the epochs into sleep stages.

RESULTS

Our model achieved 70% epoch-by-epoch agreement for 4-class (wake, light, deep, REM) sleep stage classification and robust performance across various signal-to-noise conditions. The model performance was not considerably affected by sleep apnea or periodic limb movement. External validation with smartphone dataset also showed 68% epoch-by-epoch agreement.

CONCLUSION

The proposed end-to-end deep learning model shows potential of low-quality sounds recorded from microphone chips to be utilized for sleep staging. Future study using nocturnal sounds recorded from mobile devices at home environment may further confirm the use of mobile device recording as an at-home sleep tracker.

Evaluation of Sleep Architecture using 24-hour Polysomnography in Patients Recovering from Critical Illness in an Intensive Care Unit and High Dependency Unit: a Longitudinal, Prospective, and Observational Study

Background and objective

The sleep architecture of critically ill patients being treated in Intensive Care Units (ICU) and High Dependency Units (HDU) is frequently unsettled and inadequate both qualitatively and quantitatively. The study aimed to investigate and elucidate factors influencing sleep architecture and quality in ICU and HDU in a limited resource setting with financial constraints, lacking human resources and technology for routine monitoring of noise, light and sleep promotion strategies in ICU.

Methods

The study was longitudinal, prospective, hospital-based, analytic, and observational. Insomnia Severity Index (ISI) and the Epworth Sleepiness Scale (ESS) pre hospitalisation scores were recorded. Patients underwent 24-hour polysomnography (PSG) with the simultaneous monitoring of noise and light in their environments. Patients stabilised in ICU were transferred to HDU, where the 24-hour PSG with the simultaneous monitoring of noise and light in their environments was repeated. Following PSG, the Richards-Campbell Sleep Questionnaire (RCSQ) was employed to rate patients’ sleep in both the ICU and HDU.

Results

Of 46 screened patients, 26 patients were treated in the ICU and then transferred to the HDU. The mean (SD) of the study population’s mean (SD) age was 35.96 (11.6) years with a predominantly male population (53.2% (n=14)). The mean (SD) of the ISI and ESS scores were 6.88 (2.58) and 4.92 (1.99), respectively. The comparative analysis of PSG data recording from the ICU and HDU showed a statistically significant reduction in N1, N2 and an increase in N3 stages of sleep (p<0.05). Mean (SD) of RCSQ in the ICU and the HDU were 54.65 (7.70) and 60.19 (10.85) (p-value = 0.04) respectively. The disease severity (APACHE II) has a weak correlation with the arousal index but failed to reach statistical significance (coeff= 0.347, p= 0.083).

Conclusion

Sleep in ICU is disturbed and persisting during the recovery period in critically ill. However, during recovery, sleep architecture shows signs of restoration.

Estimating sleep stages using cardiorespiratory signals: validation of a novel algorithm across a wide range of sleep-disordered breathing severity

STUDY OBJECTIVES

We have developed the CardioRespiratory Sleep Staging (CReSS) algorithm for estimating sleep stages using heart rate variability and respiration, allowing for estimation of sleep staging during home sleep apnea tests. Our objective was to undertake an epoch-by-epoch validation of algorithm performance against the gold standard of manual polysomnography sleep staging.

METHODS

Using 296 polysomnographs, we created a limited montage of airflow and heart rate and deployed CReSS to identify each 30-second epoch as wake, light sleep (N1 + N2), deep sleep (N3), or rapid eye movement (REM) sleep. We calculated Cohen's kappa and the percentage of accurately identified epochs. We repeated our analyses after stratification by sleep-disordered breathing (SDB) severity, and after adding thoracic respiratory effort as a backup signal for periods of invalid airflow.

RESULTS

CReSS discriminated wake/light sleep/deep sleep/REM sleep with 78% accuracy; the kappa value was 0.643 (95% confidence interval, 0.641-0.645). Discrimination of wake/sleep demonstrated a kappa value of 0.711 and accuracy of 89%, non-REM sleep/REM sleep demonstrated a kappa of 0.790 and accuracy of 94%, and light sleep/deep sleep demonstrated a kappa of 0.469 and accuracy of 87%. Kappa values did not vary by more than 0.07 across subgroups of no SDB, mild SDB, moderate SDB, and severe SDB. Accuracy increased to 80%, with a kappa value of 0.680 (95% confidence interval, 0.678-0.682), when CReSS additionally utilized the thoracic respiratory effort signal.

CONCLUSIONS

We observed substantial agreement between CReSS and the gold-standard comparator of manual sleep staging of polysomnographic signals, which was consistent across the full range of SDB severity. Future research should focus on the extent to which CReSS reduces the discrepancy between the apnea-hypopnea index and the respiratory event index, and the ability of CReSS to identify REM sleep-related obstructive sleep apnea.

Targeted memory reactivation has a sleep stage-specific delayed effect on dream content

Although new learning is known to reappear in later dream scenarios, the timing of such reappearances remains unclear. Sometimes, references to new learning occur relatively quickly, 1 day post-learning (day-residue effect); at other times there may be a substantive delay, 5-7 days, before such references appear (dream-lag effect). We studied temporal delays in dream reactivation following the learning of a virtual reality (VR) flying task using 10-day home sleep/dream logs, and how these might be influenced by targeted memory reactivation (TMR). Participants were exposed twice to a VR task in the sleep laboratory; once before and once after a 2-hr opportunity to nap (n = 65) or to read (n = 32). Auditory cues associated with the VR task were replayed in either wake, rapid eye movement (REM) sleep, slow-wave sleep (SWS) or were not replayed. Although we previously showed that TMR cueing did not have an immediate effect on dream content, in the present study we extend these results by showing that TMR in sleep has instead a delayed effect on task-dream reactivations: participants dreamed more about the task 1-2 days later when TMR was applied in REM sleep and 5-6 days later when it was applied in SWS sleep, compared to participants with no cueing. Findings may help explain the temporal relationships between dream and memory reactivations and clarify the occurrence of day-residue and dream-lag phenomena.

Vector Phase Analysis Approach for Sleep Stage Classification: A Functional Near-Infrared Spectroscopy-Based Passive Brain-Computer Interface

A passive brain-computer interface (BCI) based upon functional near-infrared spectroscopy (fNIRS) brain signals is used for earlier detection of human drowsiness during driving tasks. This BCI modality acquired hemodynamic signals of 13 healthy subjects from the right dorsolateral prefrontal cortex (DPFC) of the brain. Drowsiness activity is recorded using a continuous-wave fNIRS system and eight channels over the right DPFC. During the experiment, sleep-deprived subjects drove a vehicle in a driving simulator while their cerebral oxygen regulation (CORE) state was continuously measured. Vector phase analysis (VPA) was used as a classifier to detect drowsiness state along with sleep stage-based threshold criteria. Extensive training and testing with various feature sets and classifiers are done to justify the adaptation of threshold criteria for any subject without requiring recalibration. Three statistical features (mean oxyhemoglobin, signal peak, and the sum of peaks) along with six VPA features (trajectory slopes of VPA indices) were used. The average accuracies for the five classifiers are 90.9% for discriminant analysis, 92.5% for support vector machines, 92.3% for nearest neighbors, 92.4% for both decision trees, and ensembles over all subjects' data. Trajectory slopes of CORE vector magnitude and angle: m(|R|) and m(∠R) are the best-performing features, along with ensemble classifier with the highest accuracy of 95.3% and minimum computation time of 40 ms. The statistical significance of the results is validated with a p-value of less than 0.05. The proposed passive BCI scheme demonstrates a promising technique for online drowsiness detection using VPA along with sleep stage classification.

Sleep staging from electrocardiography and respiration with deep learning

STUDY OBJECTIVES

Sleep is reflected not only in the electroencephalogram but also in heart rhythms and breathing patterns. We hypothesized that it is possible to accurately stage sleep based on the electrocardiogram (ECG) and respiratory signals.

METHODS

Using a dataset including 8682 polysomnograms, we develop deep neural networks to stage sleep from ECG and respiratory signals. Five deep neural networks consisting of convolutional networks and long- and short-term memory networks are trained to stage sleep using heart and breathing, including the timing of R peaks from ECG, abdominal and chest respiratory effort, and the combinations of these signals.

RESULTS

ECG in combination with the abdominal respiratory effort achieved the best performance for staging all five sleep stages with a Cohen's kappa of 0.585 (95% confidence interval ±0.017); and 0.760 (±0.019) for discriminating awake vs. rapid eye movement vs. nonrapid eye movement sleep. Performance is better for younger ages, whereas it is robust for body mass index, apnea severity, and commonly used outpatient medications.

CONCLUSIONS

Our results validate that ECG and respiratory effort provide substantial information about sleep stages in a large heterogeneous population. This opens new possibilities in sleep research and applications where electroencephalography is not readily available or may be infeasible.

The Dreem Headband compared to polysomnography for electroencephalographic signal acquisition and sleep staging

Study Objectives

The development of ambulatory technologies capable of monitoring brain activity during sleep longitudinally is critical for advancing sleep science. The aim of this study was to assess the signal acquisition and the performance of the automatic sleep staging algorithms of a reduced-montage dry-electroencephalographic (EEG) device (Dreem headband, DH) compared to the gold-standard polysomnography (PSG) scored by five sleep experts.

Methods

A total of 25 subjects who completed an overnight sleep study at a sleep center while wearing both a PSG and the DH simultaneously have been included in the analysis. We assessed (1) similarity of measured EEG brain waves between the DH and the PSG; (2) the heart rate, breathing frequency, and respiration rate variability (RRV) agreement between the DH and the PSG; and (3) the performance of the DH’s automatic sleep staging according to American Academy of Sleep Medicine guidelines versus PSG sleep experts manual scoring.

Results

The mean percentage error between the EEG signals acquired by the DH and those from the PSG for the monitoring of α was 15 ± 3.5%, 16 ± 4.3% for β, 16 ± 6.1% for λ, and 10 ± 1.4% for θ frequencies during sleep. The mean absolute error for heart rate, breathing frequency, and RRV was 1.2 ± 0.5 bpm, 0.3 ± 0.2 cpm, and 3.2 ± 0.6%, respectively. Automatic sleep staging reached an overall accuracy of 83.5 ± 6.4% (F1 score: 83.8 ± 6.3) for the DH to be compared with an average of 86.4 ± 8.0% (F1 score: 86.3 ± 7.4) for the 5 sleep experts.

Conclusions

These results demonstrate the capacity of the DH to both monitor sleep-related physiological signals and process them accurately into sleep stages. This device paves the way for, large-scale, longitudinal sleep studies.

Clinical Trial Registration

NCT03725943.

Estimating Sleep Stages Using a Head Acceleration Sensor

Sleep disruption from causes, such as changes in lifestyle, stress from aging, family issues, or life pressures are a growing phenomenon that can lead to serious health problems. As such, sleep disorders need to be identified and addressed early on. In recent years, studies have investigated sleep patterns through body movement information collected by wristwatch-type devices or cameras. However, these methods capture only the individual’s awake and sleep states and lack sufficient information to identify specific sleep stages. The aim of this study was to use a 3-axis accelerometer attached to an individual’s head to capture information that can identify three specific sleep stages: rapid eye movement (REM) sleep, light sleep, and deep sleep. These stages are measured by heart rate features captured by a ballistocardiogram and body movement. The sleep experiment was conducted for two nights among eight healthy adult men. According to the leave-one-out cross-validation results, the F-scores were: awake 76.6%, REM sleep 52.7%, light sleep 78.2%, and deep sleep 67.8%. The accuracy was 74.6% for the four estimates. This proposed measurement system was able to estimate the sleep stages with high accuracy simply by using the acceleration in the individual’s head.

Confidence-Based Framework Using Deep Learning for Automated Sleep Stage Scoring

STUDY OBJECTIVES

Automated sleep stage scoring is not yet vigorously used in practice because of the black-box nature and the risk of wrong predictions. The objective of this study was to introduce a confidence-based framework to detect the possibly wrong predictions that would inform clinicians about which epochs would require a manual review and investigate the potential to improve accuracy for automated sleep stage scoring.

METHODS

We used 702 polysomnography studies from a local clinical dataset (SNUBH dataset) and 2804 from an open dataset (SHHS dataset) for experiments. We adapted the state-of-the-art TinySleepNet architecture to train the classifier and modified the ConfidNet architecture to train an auxiliary confidence model. For the confidence model, we developed a novel method, Dropout Correct Rate (DCR), and the performance of it was compared with other existing methods.

RESULTS

Confidence estimates (0.754) reflected accuracy (0.758) well in general. The best performance for differentiating correct and wrong predictions was shown when using the DCR method (AUROC: 0.812) compared to the existing approaches which largely failed to detect wrong predictions. By reviewing only 20% of epochs that received the lowest confidence values, the overall accuracy of sleep stage scoring was improved from 76% to 87%. For patients with reduced accuracy (ie, individuals with obesity or severe sleep apnea), the possible improvement range after applying confidence estimation was even greater.

CONCLUSION

To the best of our knowledge, this is the first study applying confidence estimation on automated sleep stage scoring. Reliable confidence estimates by the DCR method help screen out most of the wrong predictions, which would increase the reliability and interpretability of automated sleep stage scoring.

A Review of Cerebral Hemodynamics During Sleep Using Near-Infrared Spectroscopy

Investigating cerebral hemodynamic changes during regular sleep cycles and sleep disorders is fundamental to understanding the nature of physiological and pathological mechanisms in the regulation of cerebral oxygenation during sleep. Although sleep neuroimaging methods have been studied and have been well-reviewed, they have limitations in terms of technique and experimental design. Neurologists are convinced that Near-infrared spectroscopy (NIRS) provides essential information and can be used to assist the assessment of cerebral hemodynamics, and numerous studies regarding sleep have been carried out based on NIRS. Thus, a brief historical overview of the sleep studies using NIRS will be helpful for the biomedical students, academicians, and engineers to better understand NIRS from various perspectives. In this study, the existing literature on sleep studies is reviewed, and an overview of the NIRS applications is synthesized and provided. The paper first reviews the application scenarios, as well as the patterns of fluctuation of NIRS, which includes the investigation in regular sleep and sleep-disordered breathing. Various factors such as different sleep stages, populations, and degrees of severity were considered. Furthermore, the experimental design and signal processing, as well as the regulation mechanisms involved in regular and pathological sleep, are investigated and discussed. The strengths and weaknesses of the existing NIRS applications are addressed and presented, which can direct further NIRS analysis and utilization.

A Paradoxical Kind of Sleep in Drosophila melanogaster

The dynamic nature of sleep in many animals suggests distinct stages that serve different functions. Genetic sleep induction methods in animal models provide a powerful way to disambiguate these stages and functions, although behavioral methods alone are insufficient to accurately identify what kind of sleep is being engaged. In Drosophila, activation of the dorsal fan-shaped body (dFB) promotes sleep, but it remains unclear what kind of sleep this is, how the rest of the fly brain is behaving, or if any specific sleep functions are being achieved. Here, we developed a method to record calcium activity from thousands of neurons across a volume of the fly brain during spontaneous sleep and compared this to dFB-induced sleep. We found that spontaneous sleep typically transitions from an active "wake-like" stage to a less active stage. In contrast, optogenetic activation of the dFB promotes sustained wake-like levels of neural activity even though flies become unresponsive to mechanical stimuli. When we probed flies with salient visual stimuli, we found that the activity of visually responsive neurons in the central brain was blocked by transient dFB activation, confirming an acute disconnect from the external environment. Prolonged optogenetic dFB activation nevertheless achieved a key sleep function by correcting visual attention defects brought on by sleep deprivation. These results suggest that dFB activation promotes a distinct form of sleep in Drosophila, where brain activity appears similar to wakefulness, but responsiveness to external sensory stimuli is profoundly suppressed.

Correspondence between physiological and behavioural responses to vibratory stimuli during the sleep onset period: A quantitative electroencephalography analysis

Behavioural responses to auditory stimuli cease in late N1 or early N2 sleep. Yet, responsiveness to minimal intensity tactile stimuli and the correspondence with sleep microstructure during the sleep onset period is unknown. The aim of the present study was to investigate sleep microstructure using quantitative electroencephalography analysis when participants behaviourally responded to minimal intensity vibratory stimuli compared to when participants did not respond to stimuli during the sleep onset period. Eighteen participants wore a device that emitted vibratory stimuli to which individuals responded by tapping their index finger. A fast Fourier transform using multitaper-based estimation was applied to electroencephalography signals in 5-s epochs. Participants exhibited increases in higher frequencies 5 s before and immediately after the stimulus presentation when they responded to the stimulus compared to when they did not respond during all sleep stages. They also had greater delta power after stimulus onset when they did not respond to stimuli presented in N1 and N2 sleep compared to when they did respond. Participants responded to a significantly greater proportion of stimuli in wake than in N1 sleep (p < .001, d = 2.38), which was also significantly greater than the proportion of responses in N2 sleep (p < .001, d = 1.12). Participants showed wake-like sleep microstructure when they responded to vibratory stimuli and sleep-like microstructure when they did not respond during all sleep stages. The present study adds to the body of evidence characterising N1 sleep as a transitional period between sleep and wake containing rapid fluctuations between these two states.

Development of Automated Sleep Stage Classification System Using Multivariate Projection-Based Fixed Boundary Empirical Wavelet Transform and Entropy Features Extracted from Multichannel EEG Signals

The categorization of sleep stages helps to diagnose different sleep-related ailments. In this paper, an entropy-based information–theoretic approach is introduced for the automated categorization of sleep stages using multi-channel electroencephalogram (EEG) signals. This approach comprises of three stages. First, the decomposition of multi-channel EEG signals into sub-band signals or modes is performed using a novel multivariate projection-based fixed boundary empirical wavelet transform (MPFBEWT) filter bank. Second, entropy features such as bubble and dispersion entropies are computed from the modes of multi-channel EEG signals. Third, a hybrid learning classifier based on class-specific residuals using sparse representation and distances from nearest neighbors is used to categorize sleep stages automatically using entropy-based features computed from MPFBEWT domain modes of multi-channel EEG signals. The proposed approach is evaluated using the multi-channel EEG signals obtained from the cyclic alternating pattern (CAP) sleep database. Our results reveal that the proposed sleep staging approach has obtained accuracies of 91.77%, 88.14%, 80.13%, and 73.88% for the automated categorization of wake vs. sleep, wake vs. rapid eye movement (REM) vs. Non-REM, wake vs. light sleep vs. deep sleep vs. REM sleep, and wake vs. S1-sleep vs. S2-sleep vs. S3-sleep vs. REM sleep schemes, respectively. The developed method has obtained the highest overall accuracy compared to the state-of-art approaches and is ready to be tested with more subjects before clinical application.

A sleep intervention study comparing effects of sleep restriction and fragmentation on sleep and vigilance and the need for recovery

PURPOSE

Sleep deprivation is present not only in sleep disorders but also in numerous high demanding jobs and negatively affects cognition, performance and health. We developed a study design to distinguish the effects and need for recovery of two short-term disturbances - intermittent sleep fragmentation and partial sleep restriction.

METHODS

The randomized within-subjects design contained two weeks each with a baseline night, an intervention night of either sleep deprivation (5 h) or sleep fragmentation (light on every hour) and two undisturbed recovery nights. Twenty healthy male participants (mean age: 39.9 ± 7.4 years, mean BMI: 25.5 ± 2.2 kg/m²) underwent polysomnography, a psychomotor vigilance task (PVT), and subjective questions on well-being and sleep efficiency.

RESULTS

Percentage-wise, the restriction night had significant less wake times, less light sleep (stage 1), less REM sleep, but more deep sleep (stage 3) than the fragmentation night. The restriction week displayed a significant recovery effect regarding these sleep stages. The sleep fragmentation week presented a significant recovery effect regarding sleep onset times. PVT performance showed only a slight recovery effect after sleep restriction. Subjective sleep quality was reduced after both interventions with a significant recovery effect during restriction week only.

CONCLUSIONS

Short-term sleep restriction presented as a stronger sleep disturbance than short-term intermittent sleep fragmentation, including a stronger need for recovery. Already a one night sleep deprivation had an effect beyond two recovery days. The PVT was not sensitive enough to reveal significant changes. Next, autonomic parameters as possible biomarkers will be investigated.

A novel sleep stage scoring system: Combining expert-based features with the generalized linear model

In this study, we aim to automate the sleep stage scoring process of overnight polysomnography (PSG) data while adhering to expert-based rules. We developed a sleep stage scoring algorithm utilizing the generalized linear modelling (GLM) framework and extracted features from electroencephalogram (EEG), electromyography (EMG) and electrooculogram (EOG) signals based on predefined rules of the American Academy of Sleep Medicine (AASM) Manual for Scoring Sleep. Specifically, features were computed in 30-s epochs in the time and frequency domains of the signals and were then used to model the probability of an epoch being in each of five sleep stages: N3, N2, N1, REM or Wake. Finally, each epoch was assigned to a sleep stage based on model predictions. The algorithm was trained and tested on PSG data from 38 healthy individuals with no reported sleep disturbances. The overall scoring accuracy reached on the test set was 81.50 ± 1.14% (Cohen's kappa, κ = 0.73 ± 0.02 ). The test set results were highly comparable to the training set, indicating robustness of the algorithm. Furthermore, our algorithm was compared to three well-known commercialized sleep-staging tools and achieved higher accuracies than all of them. Our results suggest that automatic classification is highly consistent with visual scoring. We conclude that our algorithm can reproduce the judgement of a scoring expert and is also highly interpretable. This tool can assist visual scorers to speed up their process (from hours to minutes) and provides a method for a more robust, quantitative, reproducible and cost-effective PSG evaluation, supporting assessment of sleep and sleep disorders.

Interaction Between Slow Wave Sleep and Obstructive Sleep Apnea in Prevalent Hypertension

Due to frequent abnormal breathing events and their effects on sleep architecture, patients with obstructive sleep apnea (OSA) exhibit decreased amounts of slow wave sleep (SWS). Reduced SWS has been linked to hypertension in community-based studies. We sought to investigate whether SWS percentage modifies the association between OSA and prevalent hypertension. We studied 7107 patients with OSA and 1118 primary snorers who underwent in-laboratory polysomnography. Patients were classified into quartiles of percent SWS. Hypertension was defined based either on clinic blood pressure measures or on physician diagnosis. Multivariable logistic regression model showed a significant interaction effect of OSA and SWS on prevalent hypertension (P=0.002). Decreased SWS was associated with higher odds for hypertension in OSA but not in primary snoring, with patients with OSA exhibiting <0.1% SWS (OR, 1.44 [95% CI, 1.21-1.70]; P=0.001) and those with 0.1% to 4.8% SWS (OR, 1.20 [95% CI, 1.03-1.40]; P=0.02) being more likely to have hypertension compared with those with >11.1% SWS. In analysis stratified by OSA severity, significant associations between percent SWS and blood pressure emerged only in moderate and severe OSA. Effect modifications by sex (P=0.040) and age (P=0.007) were also only evident in OSA, indicating that decreased SWS was associated with hypertension only in men and in patients <60 years old. Decreased SWS is associated with a dose-dependent increase in odds of prevalent hypertension in patients with OSA. The effects of SWS are likely to be modulated by OSA severity. SWS may be implicated in the heightened risk of cardiovascular diseases exhibited by patients with OSA.

Obstructive sleep apnea in obese minipigs

Objective:

Obesity has reached epidemic proportions and is a strong risk factor for obstructive sleep apnea (OSA). However, the underlying mechanisms are poorly understood and current treatment strategies for OSA and obesity have critical limitations. Thus, establishment of an obesity-related large animal model with spontaneous OSA is imperative.

Materials and methods:

Natural and sedated sleep were monitored and characterized in 4 obese (body mass index - BMI>48) and 3 non-obese (BMI<40) minipigs. These minipigs were instrumented with the BioRadio system under sedation for the wireless recording of respiratory airflow, snoring, abdominal and chest respiratory movements, electroencephalogram, electrooclulogram, electromyogram, and oxygen saturation. After instrumentation, the minipigs were placed in a dark room with a remote night-vision camera for monitoring all behaviors. Wakefulness and different sleep stages were classified, and episodes of apneas and/or hypopneas were identified during natural and/or sedated sleep.

Results:

No hypopnea episodes were observed in two of the non-obese minipigs, but one non-obese minipig had 5 hypopnea events. Heavy snoring and 27-58 apnea and/or hypopnea episodes were identified in all 4 obese minipigs. Most of these episodes occurred in the rapid eye movement stage during natural sleep and/or sedated sleep in Yucatan minipigs.

Conclusions:

Obese minipigs can experience naturally occurring OSA, thus are an ideal large animal model for obese-related OSA studies.

Effective Continuous Positive Airway Pressure Changes Related to Sleep Stage and Body Position in Obstructive Sleep Apnea during Upward and Downward Titration: An Experimental Study

Background and Purpose

The aim of this study was to determine how the sleep stage and body position influence the effective pressure (Peff) in standard upward titration and experimental downward titration.

Methods

This study applied successful manual titration of continuous positive airway pressure over 3 hours [including at least 15 min in supine rapid eye movement (REM) sleep] followed by consecutive downward titration for at least 1 hour to 22 patients with moderate-to-severe obstructive sleep apnea. We analyzed baseline polysomnography variables and compared the effective pressures (Peff1_upward and Peff2_downward) between non-REM and REM sleep and between supine and lateral positions using the paired t-test or Wilcoxon signed-rank test.

Results

During upward titration, Peff1 increased during REM sleep compared to non-REM sleep [9.5±2.9 vs. 8.9±2.7 cm H₂O (mean±SD), ΔPeff1_{REM–non-REM}=0.6±1.1 cm H₂O; p=0.024]. During downward titration, Peff2 was higher in a supine than a lateral position (7.3±1.7 vs. 4.8±1.5 cm H₂O, ΔPeff2_{supine-lateral}=2.5±1.3 cm H₂O; p=0.068). When comparing both upward and downward titration conditions, we found that Peff2 was significantly lower than Peff1 in all sleep stages, especially during REM sleep (Peff1_REM vs. Peff2_REM=9.5±2.9 vs. 7.4±3.3 cm H₂O) with an overall difference of 2.1±1.7 cm H₂O (p<0.001). Peff in supine sleep decreased from 9.4±3.0 cm H₂O (Peff1_supine) to 7.6±3.3 cm H₂O (Peff2_supine), with an overall difference of 1.8±1.6 cm H₂O (p<0.001).

Conclusions

This study has revealed that the collapsibility of the upper airway is influenced by sleep stage and body position. After achieving an initial Peff1, a lower pressure was acceptable to maintain airway patency during the rest of the sleep. The observed pressure decrease may support the use of an automated titration device that integrates real-time positional and sleep-stage factors, and the use of a lower pressure may improve fixed-pressure-related intolerance.

Accuracy of Wristband Fitbit Models in Assessing Sleep: Systematic Review and Meta-Analysis

BACKGROUND

Wearable sleep monitors are of high interest to consumers and researchers because of their ability to provide estimation of sleep patterns in free-living conditions in a cost-efficient way.

OBJECTIVE

We conducted a systematic review of publications reporting on the performance of wristband Fitbit models in assessing sleep parameters and stages.

METHODS

In adherence with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement, we comprehensively searched the Cumulative Index to Nursing and Allied Health Literature (CINAHL), Cochrane, Embase, MEDLINE, PubMed, PsycINFO, and Web of Science databases using the keyword Fitbit to identify relevant publications meeting predefined inclusion and exclusion criteria.

RESULTS

The search yielded 3085 candidate articles. After eliminating duplicates and in compliance with inclusion and exclusion criteria, 22 articles qualified for systematic review, with 8 providing quantitative data for meta-analysis. In reference to polysomnography (PSG), nonsleep-staging Fitbit models tended to overestimate total sleep time (TST; range from approximately 7 to 67 mins; effect size=-0.51, P<.001; heterogenicity: I2=8.8%, P=.36) and sleep efficiency (SE; range from approximately 2% to 15%; effect size=-0.74, P<.001; heterogenicity: I2=24.0%, P=.25), and underestimate wake after sleep onset (WASO; range from approximately 6 to 44 mins; effect size=0.60, P<.001; heterogenicity: I2=0%, P=.92) and there was no significant difference in sleep onset latency (SOL; P=.37; heterogenicity: I2=0%, P=.92). In reference to PSG, nonsleep-staging Fitbit models correctly identified sleep epochs with accuracy values between 0.81 and 0.91, sensitivity values between 0.87 and 0.99, and specificity values between 0.10 and 0.52. Recent-generation Fitbit models that collectively utilize heart rate variability and body movement to assess sleep stages performed better than early-generation nonsleep-staging ones that utilize only body movement. Sleep-staging Fitbit models, in comparison to PSG, showed no significant difference in measured values of WASO (P=.25; heterogenicity: I2=0%, P=.92), TST (P=.29; heterogenicity: I2=0%, P=.98), and SE (P=.19) but they underestimated SOL (P=.03; heterogenicity: I2=0%, P=.66). Sleep-staging Fitbit models showed higher sensitivity (0.95-0.96) and specificity (0.58-0.69) values in detecting sleep epochs than nonsleep-staging models and those reported in the literature for regular wrist actigraphy.

CONCLUSIONS

Sleep-staging Fitbit models showed promising performance, especially in differentiating wake from sleep. However, although these models are a convenient and economical means for consumers to obtain gross estimates of sleep parameters and time spent in sleep stages, they are of limited specificity and are not a substitute for PSG.

Performance assessment of new-generation Fitbit technology in deriving sleep parameters and stages

We compared performance in deriving sleep variables by both Fitbit Charge 2™, which couples body movement (accelerometry) and heart rate variability (HRV) in combination with its proprietary interpretative algorithm (IA), and standard actigraphy (Motionlogger® Micro Watch Actigraph: MMWA), which relies solely on accelerometry in combination with its best performing 'Sadeh' IA, to electroencephalography (EEG: Zmachine® Insight+ and its proprietary IA) used as reference. We conducted home sleep studies on 35 healthy adults, 33 of whom provided complete datasets of the three simultaneously assessed technologies. Relative to the Zmachine EEG method, Fitbit showed an overall Kappa agreement of 54% in distinguishing wake/sleep epochs and sensitivity of 95% and specificity of 57% in detecting sleep epochs. Fitbit, relative to EEG, underestimated sleep onset latency (SOL) by ~11 min and overestimated sleep efficiency (SE) by ~4%. There was no statistically significant difference between Fitbit and EEG methods in measuring wake after sleep onset (WASO) and total sleep time (TST). Fitbit showed substantial agreement with EEG in detecting rapid eye movement and deep sleep, but only moderate agreement in detecting light sleep. The MMWA method showed 51% overall Kappa agreement with the EEG one in detecting wake/sleep epochs, with sensitivity of 94% and specificity of 53% in detecting sleep epochs. MMWA, relative to EEG, underestimated SOL by ~10 min. There was no significant difference between Fitbit and MMWA methods in amount of bias in estimating SOL, WASO, TST, and SE; however, the minimum detectable change (MDC) per sleep variable with Fitbit was better (smaller) than with MMWA, respectively, by ~10 min, ~16 min, ~22 min, and ~8%. Overall, performance of Fitbit accelerometry and HRV technology in conjunction with its proprietary IA to detect sleep vs. wake episodes is slightly better than wrist actigraphy that relies solely on accelerometry and best performing Sadeh IA. Moreover, the smaller MDC of Fitbit technology in deriving sleep parameters in comparison to wrist actigraphy makes it a suitable option for assessing changes in sleep quality over time, longitudinally, and/or in response to interventions.