Proposed supplements and amendments to 'A Manual of Standardized Terminology, Techniques and Scoring System for Sleep Stages of Human Subjects', the Rechtschaffen & Kales (1968) standard

Machine learning classifier solving the problem of sleep stage imbalance between overnight sleep

Feature extraction follows the American Academy of Sleep Medicine (AASM) sleep score manually and applies it to machine learning with a focus on the generalization of sleep data to enable data-centric artificial intelligence. In real-world clinical testing, the manual scoring of sleep stages is time-consuming and requires significant expertise. Additionally, it is subject to interobserver subjective bias. Machine-learning techniques offer a way to overcome these limitations through automation. However, machine learning for sleep phase prediction can perform poorly for small classes. If the distribution of the training data was unbalanced, the model was trained with a bias toward the majority class. To address this, we experimented with loss function adjustment and resampling methods that assign more weight to the prediction errors of minority classes in sleep scoring to determine how to overcome the data imbalance problem. Machine learning can also be used to compare the accuracy of each channel in identifying electrodes, which should be monitored more closely in real-world clinical testing. Owing to the small amount of data available for machine learning in this study, we used various machine learning classifiers by increasing or decreasing the dataset using sampling techniques and weighting different classes of sleep stages. In our experiments, the best-performing model for classifying sleep stages had an accuracy of 91.9%, kappa of 0.899, and F1-score of 86.9%.

MHFNet: A Multimodal Hybrid-Embedding Fusion Network for Automatic Sleep Staging

Scoring sleep stages is essential for evaluating the status of sleep continuity and comprehending its structure. Despite previous attempts, automating sleep scoring remains challenging. First, most existing works did not fuse local and global temporal information. Second, the correlation for special waves in different signals is rarely used in sleep staging modeling. Third, the logic of scoring rules based on adjacent epochs is not considered in developing sleep staging models. This paper introduces a multimodal hybrid-embedding fusion network (MHFNet), which aims to tackle these challenges in automating sleep stage scoring. MHFNet comprises multi-stream Xception blocks to extract wave characteristics, a hybrid time-embedding module to combine local and global temporal information, a dual-path gate transformer to fuse and enhance attention features, and a refined output header to reconstruct sleep scoring. We perform experiments using three publicly available datasets (SleepEDF-ST, SleepEDF-SC, and SHHS). Experimental results indicate the superiority of MHFNet over baseline approaches in cross-validation. Moreover, at the individual level, MHFNet yielded an average $R^{2}$ score improvement of 9$\%$ in the testing dataset compared to state-of-the-art models, paving the way for its applications in real-world sleep medicine.

Sleep stage, sleep fragmentation and heart rate variability during the initial 3-h sleep period in patients with obstructive sleep apnea syndrome

To investigate differences in polysomnography (PSG) parameters and heart rate variability (HRV) during the initial 3-h sleep period in patients with mild, moderate, and severe obstructive sleep apnea syndrome (OSA). According to the apnea-hypopnea index, patients were divided into 3 groups: mild, moderate, and severe (n = 23, 59, and 94, respectively). PSG was performed, and HRV (frequency domain analysis), sleep stage (S1, S2, S3, REM, and waking), and sleep fragmentation index (SFI) were measured during the initial 3-h sleep periods. The total S1 time was significantly longer in the severe group than in the mild and moderate groups (p < 0.001). The severe group had significantly shorter total S2 and S3 times than the mild (p = 0.014, p < 0.001) and moderate (p = 0.034, p = 0.029) groups did. The SFI was significantly greater in the severe group than in the mild and moderate groups (p < 0.001, p = 0.008). The high-frequency component (HF) of the HRV showed no significant differences except that it was significantly smaller during S3 in the moderate group than in the mild group (p = 0.026). Compared with those with mild/moderate status, patients with severe OSA have shallower sleep and a higher SFI, suggesting poorer sleep quality. Although HF during S3 was significantly smaller in the moderate group, it did not significantly differ between the mild and severe groups, suggesting that the parasympathetic nervous system might compensate for humoral and hypoxemic abnormalities in patients with severe OSA.

Decoding Multifaceted Roles of Sleep-Related Genes as Molecular Bridges in Chronic Disease Pathogenesis

Sleep is a fundamental process essential for all organisms. Sleep deprivation can lead to significant detrimental effects, contributing to various physiological disorders and elevating the risk of several diseases. Investigating the relationship between sleep and human diseases offers valuable insights into the molecular mechanisms governing sleep regulation, potentially guiding the development of more effective treatments for sleep disorders and associated diseases. This study explored the roles of sleep-related genes in biological processes and their associations with chronic diseases, mainly including neurological, metabolic, cardiovascular diseases, and cancer. Additionally, an analysis on the sleep-related genes was also performed to understand the potential role in tumorigenesis. This review aims to enhance the understanding of the link between sleep-related genes and chronic diseases, contributing to the development of novel therapeutic approaches targeting sleep and circadian rhythm-related chronic diseases.

An Effective and Interpretable Sleep Stage Classification Approach Using Multi-Domain Electroencephalogram and Electrooculogram Features

Accurate sleep staging is critical for assessing sleep quality and diagnosing sleep disorders. Recent research efforts on automated sleep staging have focused on complex deep learning architectures that have achieved modest improvements in classification accuracy but have limited real-world applicability due to the complexity of model training and deployment and a lack of interpretability. This paper presents an effective and interpretable sleep staging scheme that follows a classical machine learning pipeline. Multi-domain features were extracted from preprocessed electroencephalogram (EEG) signals, and novel electrooculogram (EOG) features were created to characterize different sleep stages. A two-step feature selection strategy combining F-score pre-filtering and XGBoost feature ranking was designed to select the most discriminating feature subset, which was then fed into an XGBoost model for sleep stage classification. Through a rigorous double-cross-validation procedure, our approach achieved competitive classification performance on the public Sleep-EDF dataset (accuracy 87.0%, F1-score 86.6%, Kappa coefficient 0.81) compared with the state-of-the-art deep learning methods and provided interpretability through feature importance analysis. These promising results demonstrate the effectiveness of the proposed sleep staging model and show its potential in practical applications due to its low complexity, interpretability, and transparency.

Using cross-recurrence quantification analysis to compute similarity measures for time series of unequal length with applications to sleep stage analysis

Comparing time series of unequal length requires data processing procedures that may introduce biases. This article describes, validates, and applies Cross-Recurrence Quantification Analysis (CRQA) to detect and quantify correlation and coupling among time series of unequal length without prior data processing. We illustrate and validate this application using continuous and discrete data from a model system (study 1). Then we use the method to re-analyze the Sleep Heart Health Study (SHHS), a rare large dataset comprising detailed physiological sleep measurements acquired by in-home polysomnography. We investigate whether recurrence patterns of ultradian NREM/REM sleep cycles (USC) predict mortality (study 2). CRQA exhibits better performance compared with traditional approaches that require trimming, stretching or compression to bring two time series to the same length. Application to the SHHS indicates that recurrence patterns linked to stability of USCs are associated with all-cause mortality even after controlling for other sleep parameters, health, and sociodemographics. We suggest that CRQA is a useful tool for analyzing categorical time series, where the underlying structure of the data is unlikely to result in matching data points-such as ultradian sleep cycles.

Disruption of sleep macro- and microstructure in Alzheimer's disease: overlaps between neuropsychology, neurophysiology, and neuroimaging

Alzheimer's disease (AD) is the leading cause of dementia, often associated with impaired sleep quality and disorganized sleep structure. This study aimed to characterize changes in sleep macrostructure and K-complex density in AD, in relation to neuropsychological performance and brain structural changes. We enrolled 30 AD and 30 healthy control participants, conducting neuropsychological exams, brain MRI, and one-night polysomnography. AD patients had significantly reduced total sleep time (TST), sleep efficiency, and relative durations of non-rapid eye movement (NREM) stages 2 (S2), 3 (S3), and rapid eye movement (REM) sleep (p < 0.01). K-complex (KC) density during the entire sleep period and S2 (p < 0.001) was significantly decreased in AD. We found strong correlations between global cognitive performance and relative S3 (p < 0.001; r = 0.86) and REM durations (p < 0.001; r = 0.87). TST and NREM stage 1 (S1) durations showed a moderate negative correlation with amygdaloid and hippocampal volumes (p < 0.02; r = 0.51-0.55), while S3 and REM sleep had a moderate positive correlation with cingulate cortex volume (p < 0.02; r = 0.45-0.61). KC density strongly correlated with global cognitive function (p < 0.001; r = 0.66) and the thickness of the anterior cingulate cortex (p < 0.05; r = 0.45-0.47). Our results indicate significant sleep organization changes in AD, paralleling cognitive decline. Decreased slow wave sleep and KCs are strongly associated with cingulate cortex atrophy. Since sleep changes are prominent in early AD, they may serve as prognostic markers or therapeutic targets.

The Effect of Continuous Positive Airway Pressure (CPAP) Therapy on Serum Caspase-3 Level in Patients with Obstructive Sleep Apnea (OSA)

INTRODUCTION

Intermittent hypoxemia has an important role in the physiopathogenesis of obstructive sleep apnea (OSA) complications. Increased apoptosis due to intermittent hypoxemia may be an important clinical entity in OSA. In this study, we aimed to evaluate caspase-3 enzyme level, which is an indirect marker of increased apoptosis in patients with OSA and to evaluate the effect of OSA treatment with continuous positive airway pressure on caspase-3 enzyme level.

MATERIALS AND METHODS

This study included 141 consecutive patients admitted to the sleep-disordered breathing laboratory within 6 months. Caspase-3 was measured in routine blood samples obtained on the morning of polysomnography (PSG) performed at night. The compliance of the patients to CPAP treatment was evaluated and caspase-3 levels were checked again after treatment.

RESULTS

A total of 141 patients, 39 females (27,7%) and 102 males (72,3%) were included in the study. The mean age of the patients was 49 ± 12 years (min-17, max-77). According to PSG results, OSA was detected in 95.7% (135/141) of the cases. Mild OSA was 35 (24.8%), moderate OSA 39 (27.7%) and severe OSA 61 (43.3%) cases. Median caspase-3 enzyme levels were similar in men and women in the study group. There was no statistically significant difference in hemogram parameters and caspase-3 enzyme levels between the groups divided according to the presence and severity of OSA. It was determined that caspase-3 enzyme level did not change significantly after 3 months of CPAP treatment in OSA compared to pretreatment. Caspase-3 was found to have a negative correlation with both the percentage of daily use of CPAP therapy and the percentage of CPAP device use for more than 1 h per night. It was found that the control caspase-3 level decreased statistically significantly as the percentage of daily use of CPAP therapy increased (r = -0.397, p = 0.030). It was found that the control caspase-3 level decreased statistically significantly as the percentage of CPAP therapy use for more than 1 h per night increased (r = -0.411, p = 0.024).

CONCLUSION

The results of this study did not reveal a relationship between the severity of OSA and caspase-3 levels. However, blood caspase-3 levels decreased as treatment compliance increased, suggesting that CPAP treatment may correct increased apoptosis in OSA. There is a need for more comprehensive studies on this issue.

EEGNet classification of sleep EEG for individual specialization based on data augmentation

Sleep is an essential part of human life, and the quality of one's sleep is also an important indicator of one's health. Analyzing the Electroencephalogram (EEG) signals of a person during sleep makes it possible to understand the sleep status and give relevant rest or medical advice. In this paper, a decent amount of artificial data generated with a data augmentation method based on Discrete Cosine Transform from a small amount of real experimental data of a specific individual is introduced. A classification model with an accuracy of 92.85% has been obtained. By mixing the data augmentation with the public database and training with the EEGNet, we obtained a classification model with significantly higher accuracy for the specific individual. The experiments have demonstrated that we can circumvent the subject-independent problem in sleep EEG in this way and use only a small amount of labeled data to customize a dedicated classification model with high accuracy.

Movement Termination of Slow-Wave Sleep-A Potential Biomarker?

The duration of slow-wave sleep (SWS) is related to the reported sleep quality and to the important variables of mental and physical health. The internal cues to end an episode of SWS are poorly understood. One such internal cue is the initiation of a body movement, which is detectable as electromyographic (EMG) activity in sleep-electroencephalography (EEG). In the present study, we characterized the termination of SWS episodes by movement to explore its potential as a biomarker. To this end, we characterized the relation between the occurrence of SWS termination by movement and individual characteristics (age, sex), SWS duration and spectral content, chronotype, depression, medication, overnight memory performance, and, as a potential neurological application, epilepsy. We analyzed 94 full-night EEG-EMG recordings (75/94 had confirmed epilepsy) in the video-EEG monitoring unit of the EpiCARE Centre Salzburg, Austria. Segments of SWS were counted and rated for their termination by movement or not through the visual inspection of continuous EEG and EMG recordings. Multiple linear regression was used to predict the number of SWS episodes that ended with movement by depression, chronotype, type of epilepsy (focal, generalized, no epilepsy, unclear), medication, gender, total duration of SWS, occurrence of seizures during the night, occurrence of tonic-clonic seizures during the night, and SWS frequency spectra. Furthermore, we assessed whether SWS movement termination was related to overnight memory retention. According to multiple linear regression, patients with overall longer SWS experienced more SWS episodes that ended with movement (t = 5.64; p = 0.001). No other variable was related to the proportion of SWS that ended with movement, including no epilepsy-related variable. A small sample (n = 4) of patients taking Sertraline experienced no SWS that ended with movement, which was significant compared to all other patients (t = 8.00; p < 0.001) and to n = 35 patients who did not take any medication (t = 4.22; p < 0.001). While this result was based on a small subsample and must be interpreted with caution, it warrants replication in a larger sample with and without seizures to further elucidate the role of the movement termination of SWS and its potential to serve as a biomarker for sleep continuity and for medication effects on sleep.

The effects of slow wave sleep characteristics on semantic, episodic, and procedural memory in people with epilepsy

Slow wave sleep (SWS) is highly relevant for verbal and non-verbal/spatial memory in healthy individuals, but also in people with epilepsy. However, contradictory findings exist regarding the effect of seizures on overnight memory retention, particularly relating to procedural and non-verbal memory, and thorough examination of episodic memory retention with ecologically valid tests is missing. This research explores the interaction of SWS duration with epilepsy-relevant factors, as well as the relation of spectral characteristics of SWS on overnight retention of procedural, verbal, and episodic memory. In an epilepsy monitoring unit, epilepsy patients (N = 40) underwent learning, immediate and 12 h delayed testing of memory retention for a fingertapping task (procedural memory), a word-pair task (verbal memory), and an innovative virtual reality task (episodic memory). We used multiple linear regression to examine the impact of SWS duration, spectral characteristics of SWS, seizure occurrence, medication, depression, seizure type, gender, and epilepsy duration on overnight memory retention. Results indicated that none of the candidate variables significantly predicted overnight changes for procedural memory performance. For verbal memory, the occurrence of tonic-clonic seizures negatively impacted memory retention and higher psychoactive medication load showed a tendency for lower verbal memory retention. Episodic memory was significantly impacted by epilepsy duration, displaying a potential nonlinear impact with a longer duration than 10 years negatively affecting memory performance. Higher drug load of anti-seizure medication was by tendency related to better overnight retention of episodic memory. Contrary to expectations longer SWS duration showed a trend towards decreased episodic memory performance. Analyses on associations between memory types and EEG band power during SWS revealed lower alpha-band power in the frontal right region as significant predictor for better episodic memory retention. In conclusion, this research reveals that memory modalities are not equally affected by important epilepsy factors such as duration of epilepsy and medication, as well as SWS spectral characteristics.

Modulate the impact of the drowsiness on the resting state functional connectivity

This research explores different methodologies to modulate the effects of drowsiness on functional connectivity (FC) during resting-state functional magnetic resonance imaging (RS-fMRI). The study utilized a cohort of students (MRi-Share) and classified individuals into drowsy, alert, and mixed/undetermined states based on observed respiratory oscillations. We analyzed the FC group difference between drowsy and alert individuals after five different processing methods: the reference method, two based on physiological and a global signal regression of the BOLD time series signal, and two based on Gaussian standardizations of the FC distribution. According to the reference method, drowsy individuals exhibit higher cortico-cortical FC than alert individuals. First, we demonstrated that each method reduced the differences between drowsy and alert states. The second result is that the global signal regression was quantitively the most effective, minimizing significant FC differences to only 3.3% of the total FCs. However, one should consider the risks of overcorrection often associated with this methodology. Therefore, choosing a less aggressive form of regression, such as the physiological method or Gaussian-based approaches, might be a more cautious approach. Third and last, using the Gaussian-based methods, cortico-subcortical and intra-default mode network (DMN) FCs were significantly greater in alert than drowsy subjects. These findings bear resemblance to the anticipated patterns during the onset of sleep, where the cortex isolates itself to assist in transitioning into deeper slow wave sleep phases, simultaneously disconnecting the DMN.

Seizures and electrophysiological features in familial cortical myoclonic tremor with epilepsy 1

OBJECTIVES

To investigate and characterize epileptic seizures and electrophysiological features of familial cortical myoclonic tremor with epilepsy (FCMTE) type 1 patients in a large Chinese cohort.

METHODS

We systematically evaluated 125 FCMTEtype 1 patients carrying the pentanucleotide (TTTCA) repeat expansion in the SAMD12 gene in China.

RESULTS

Among the 28 probands, epileptic seizures (96.4%, 27/28) were the most common reason for an initial clinic visit. Ninety-seven (77.6%, 97/125) patients had experienced seizures. The seizures onset age was 36.5 ± 9.0 years, which was 6.9 years later than cortical tremors. The seizures were largely rare (<1/year, 58.8%) and occasional (1-6/year, 37.1%). Prolonged prodromes were reported in 57.7% (56/97). Thirty-one patients (24.8%, 31/125) reported photosensitivity history, and 79.5% (31/39) had a photoparoxysmal response. Interictal epileptiform discharges (IEDs) were recorded in 69.1% (56/81) of patients. Thirty-three patients showed generalized IEDs and 72.7% (24/33) were occipitally dominant, while 23 patients presented with focal IEDs with 65.2% (15/23) taking place over the occipital lobe. Overnight EEG of FCMTE patients displayed paradoxical sleep-wake fluctuation, with a higher average IED index of 0.82 ± 0.88/min during wakefulness and a lower IED index of 0.04 ± 0.06/min during non-rapid eye movement sleep stages I-II.

INTERPRETATION

FCMTE type 1 has a benign course of epilepsy and distinct clinical and electrophysiological features. In addition to a positive family history and cortical myoclonus tremor, the seizure prodromes, specific seizure triggers, photosensitivity, distribution of IEDs, and unique fluctuations during sleep-wake cycle are cues for proper genetic testing and an early diagnosis of FCMTE.

Exploring Convolutional Neural Network Architectures for EEG Feature Extraction

The main purpose of this paper is to provide information on how to create a convolutional neural network (CNN) for extracting features from EEG signals. Our task was to understand the primary aspects of creating and fine-tuning CNNs for various application scenarios. We considered the characteristics of EEG signals, coupled with an exploration of various signal processing and data preparation techniques. These techniques include noise reduction, filtering, encoding, decoding, and dimension reduction, among others. In addition, we conduct an in-depth analysis of well-known CNN architectures, categorizing them into four distinct groups: standard implementation, recurrent convolutional, decoder architecture, and combined architecture. This paper further offers a comprehensive evaluation of these architectures, covering accuracy metrics, hyperparameters, and an appendix that contains a table outlining the parameters of commonly used CNN architectures for feature extraction from EEG signals.

Orexin Receptor Antagonism: Normalizing Sleep Architecture in Old Age and Disease

Sleep is essential for human well-being, yet the quality and quantity of sleep reduce as age advances. Older persons (>65 years old) are more at risk of disorders accompanied and/or exacerbated by poor sleep. Furthermore, evidence supports a bidirectional relationship between disrupted sleep and Alzheimer's disease (AD) or related dementias. Orexin/hypocretin neuropeptides stabilize wakefulness, and several orexin receptor antagonists (ORAs) are approved for the treatment of insomnia in adults. Dysregulation of the orexin system occurs in aging and AD, positioning ORAs as advantageous for these populations. Indeed, several clinical studies indicate that ORAs are efficacious hypnotics in older persons and dementia patients and, as in adults, are generally well tolerated. ORAs are likely to be more effective when administered early in sleep/wake dysregulation to reestablish good sleep/wake-related behaviors and reduce the accumulation of dementia-associated proteinopathic substrates. Improving sleep in aging and dementia represents a tremendous opportunity to benefit patients, caregivers, and health systems.

Automatic sleep spindles identification and classification with multitapers and convolution

Sleep spindles are isolated transient surges of oscillatory neural activity present during sleep stages 2 and 3 in the nonrapid eye movement (NREM). They can indicate the mechanisms of memory consolidation and plasticity in the brain. Spindles can be identified across cortical areas and classified as either slow or fast. There are spindle transients across different frequencies and power, yet most of their functions remain a mystery. Using several electroencephalogram (EEG) databases, this study presents a new method, called the "spindles across multiple channels" (SAMC) method, for identifying and categorizing sleep spindles in EEGs during the NREM sleep. The SAMC method uses a multitapers and convolution (MT&C) approach to extract the spectral estimation of different frequencies present in sleep EEGs and graphically identify spindles across multiple channels. The characteristics of spindles, such as duration, power, and event areas, are also extracted by the SAMC method. Comparison with other state-of-the-art spindle identification methods demonstrated the superiority of the proposed method with an agreement rate, average positive predictive value, and sensitivity of over 90% for spindle classification across the three databases used in this paper. The computing cost was found to be, on average, 0.004 seconds per epoch. The proposed method can potentially improve the understanding of the behavior of spindles across the scalp and accurately identify and categories sleep spindles.

Role of the autonomic nervous system in young, middle-aged, and older individuals with essential hypertension and sleep-related changes in neurocardiac regulation

Essential hypertension involves complex cardiovascular regulation. The autonomic nervous system function fluctuates throughout the sleep-wake cycle and changes with advancing age. However, the precise role of the autonomic nervous system in the development of hypertension during aging remains unclear. In this study, we characterized autonomic function during the sleep-wake cycle in different age groups with essential hypertension. This study included 97 men (53 with and 44 without hypertension) aged 30-79 years. They were stratified by age into young (< 40 years), middle-aged (40-59 years), and older (60-79 years) groups. Polysomnography and blood pressure data were recorded for 2 min before and during an hour-long nap. Autonomic function was assessed by measuring heart rate variability and blood pressure variability. Data were analyzed using t tests, correlation analyses, and two-way analysis of variance. During nonrapid eye movement (nREM), a main effect of age was observed on cardiac parasympathetic measures and baroreflex sensitivity (BRS), with the highest and lowest levels noted in the younger and older groups, respectively. The coefficients of the correlations between these measures and age were lower in patients with hypertension than in normotensive controls. The BRS of young patients with hypertension was similar to that of their middle-aged and older counterparts. However, cardiac sympathetic activity was significantly higher (p = 0.023) and BRS was significantly lower (p = 0.022) in the hypertension group than in the control group. During wakefulness, the results were similar although some of the above findings were absent. Autonomic imbalance, particularly impaired baroreflex, plays a more significant role in younger patients with hypertension. The nREM stage may be suitable for gaining insights into the relevant mechanisms.

Few-shot EEG sleep staging based on transductive prototype optimization network

Electroencephalography (EEG) is a commonly used technology for monitoring brain activities and diagnosing sleep disorders. Clinically, doctors need to manually stage sleep based on EEG signals, which is a time-consuming and laborious task. In this study, we propose a few-shot EEG sleep staging termed transductive prototype optimization network (TPON) method, which aims to improve the performance of EEG sleep staging. Compared with traditional deep learning methods, TPON uses a meta-learning algorithm, which generalizes the classifier to new classes that are not visible in the training set, and only have a few examples for each new class. We learn the prototypes of existing objects through meta-training, and capture the sleep features of new objects through the "learn to learn" method of meta-learning. The prototype distribution of the class is optimized and captured by using support set and unlabeled high confidence samples to increase the authenticity of the prototype. Compared with traditional prototype networks, TPON can effectively solve too few samples in few-shot learning and improve the matching degree of prototypes in prototype network. The experimental results on the public SleepEDF-2013 dataset show that the proposed algorithm outperform than most advanced algorithms in the overall performance. In addition, we experimentally demonstrate the feasibility of cross-channel recognition, which indicates that there are many similar sleep EEG features between different channels. In future research, we can further explore the common features among different channels and investigate the combination of universal features in sleep EEG. Overall, our method achieves high accuracy in sleep stage classification, demonstrating the effectiveness of this approach and its potential applications in other medical fields.

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.

REM-OSA as a Tool to Understand Both the Architecture of Sleep and Pathogenesis of Sleep Apnea-Literature Review

Sleep is a complex physiological state, which can be divided into the non-rapid eye movement (NREM) phase and the REM phase. Both have some unique features and functions. This difference is best visible in electroencephalography recordings, respiratory system activity, arousals, autonomic nervous system activity, or metabolism. Obstructive sleep apnea (OSA) is a common condition characterized by recurrent episodes of pauses in breathing during sleep caused by blockage of the upper airways. This common condition has multifactorial ethiopathogenesis (e.g., anatomical predisposition, sex, obesity, and age). Within this heterogenous syndrome, some distinctive phenotypes sharing similar clinical features can be recognized, one of them being REM sleep predominant OSA (REM-OSA). The aim of this review was to describe the pathomechanism of REM-OSA phenotype, its specific clinical presentation, and its consequences. Available data suggest that in this group of patients, the severity of specific cardiovascular and metabolic complications is increased. Due to the impact of apneas and hypopneas predominance during REM sleep, patients are more prone to develop hypertension or glucose metabolism impairment. Additionally, due to the specific function of REM sleep, which is predominantly fragmented in the REM-OSA, this group presents with decreased neurocognitive performance, reflected in memory deterioration, and mood changes including depression. REM-OSA clinical diagnosis and treatment can alleviate these outcomes, surpassing the traditional treatment and focusing on a more personalized approach, such as using longer therapy of continuous positive airway pressure or oral appliance use.

Assessment of factors influencing glymphatic activity and implications for clinical medicine

The glymphatic system is a highly specialized fluid transport system in the central nervous system. It enables the exchange of the intercellular fluid of the brain, regulation of the movement of this fluid, clearance of unnecessary metabolic products, and, potentially, brain immunity. In this review, based on the latest scientific reports, we present the mechanism of action and function of the glymphatic system and look at the role of factors influencing its activity. Sleep habits, eating patterns, coexisting stress or hypertension, and physical activity can significantly affect glymphatic activity. Modifying them can help to change lives for the better. In the next section of the review, we discuss the connection between the glymphatic system and neurological disorders. Its association with many disease entities suggests that it plays a major role in the physiology of the whole brain, linking many pathophysiological pathways of individual diseases.

CAPSCNet: A novel scattering network for automated identification of phasic cyclic alternating patterns of human sleep using multivariate EEG signals

The Cyclic Alternating Pattern (CAP) can be considered a physiological marker of sleep instability. The CAP can examine various sleep-related disorders. Certain short events (A and B phases) manifest related to a specific physiological process or pathology during non-rapid eye movement (NREM) sleep. These phases unexpectedly modify EEG oscillations; hence, manual detection is challenging. Therefore, it is highly desirable to have an automated system for detecting the A-phases (AP). Deep convolution neural networks (CNN) have shown high performance in various healthcare applications. A variant of the deep neural network called the Wavelet Scattering Network (WSN) has been used to overcome the specific limitations of CNN, such as the need for a large amount of data to train the model. WSN is an optimized network that can learn features that help discriminate patterns hidden inside signals. Also, WSNs are invariant to local perturbations, making the network significantly more reliable and effective. It can also help improve performance on tasks where data is minimal. In this study, we proposed a novel WSN-based CAPSCNet to automatically detect AP using EEG signals. Seven dataset variants of cyclic alternating pattern (CAP) sleep cohort is employed for this study. Two electroencephalograms (EEG) derivations, namely: C4-A1 and F4-C4, are used to develop the CAPSCNet. The model is examined using healthy subjects and patients tormented by six different sleep disorders, namely: sleep-disordered breathing (SDB), insomnia, nocturnal frontal lobe epilepsy (NFLE), narcolepsy, periodic leg movement disorder (PLM) and rapid eye movement behavior disorder (RBD) subjects. Several different machine-learning algorithms were used to classify the features obtained from the WSN. The proposed CAPSCNet has achieved the highest average classification accuracy of 83.4% using a trilayered neural network classifier for the healthy data variant. The proposed CAPSCNet is efficient and computationally faster.

Insomnia with objective, but not subjective, short sleep duration is associated with increased risk of incident hypertension: the Sleep Heart Health Study

STUDY OBJECTIVES

Insomnia with objective short sleep duration has been associated with higher risk of cardiometabolic morbidity. In this study, we examined the association between insomnia with objective short sleep duration, also based on subjective sleep duration, with incident hypertension in the Sleep Heart Health Study.

METHODS

We analyzed data from 1,413 participants free of hypertension or sleep apnea at baseline from the Sleep Heart Health Study, with a median follow-up duration of 5.1 years. Insomnia symptoms were defined based on difficulty falling asleep, difficulty returning to sleep, early morning awakening, or sleeping pill use more than half the days in a month. Objective short sleep duration was defined as polysomnography-measured total sleep time < 6 hours. Incident hypertension was defined based on blood pressure measures and/or use of antihypertensive medications at follow-up.

RESULTS

Individuals with insomnia who slept objectively < 6 hours had significantly higher odds of incident hypertension compared to normal sleepers who slept ≥ 6 hours (odds ratio = 2.00, 95% confidence interval = 1.09-3.65) or < 6 hours (odds ratio = 2.00, 95% confidence interval = 1.06-3.79) or individuals with insomnia who slept ≥ 6 hours (odds ratio = 2.79, 95% confidence interval = 1.24-6.30). Individuals with insomnia who slept ≥ 6 hours or normal sleepers who slept < 6 hours were not associated with increased risk of incident hypertension compared to normal sleepers who slept ≥ 6 hours. Finally, individuals with insomnia who self-reported sleeping < 6 hours were not associated with significantly increased odds of incident hypertension.

CONCLUSIONS

These data further support that the insomnia with objective short sleep duration phenotype based on objective, but not subjective measures, is associated with increased risk of developing hypertension in adults.

CITATION

Dai Y, Chen B, Chen L, et al. Insomnia with objective, but not subjective, short sleep duration is associated with increased risk of incident hypertension: the Sleep Heart Health Study. J Clin Sleep Med. 2023;19(8):1421-1428.

Spotlight on Sleep Stage Classification Based on EEG

The recommendations for identifying sleep stages based on the interpretation of electrophysiological signals (electroencephalography [EEG], electro-oculography [EOG], and electromyography [EMG]), derived from the Rechtschaffen and Kales manual, were published in 2007 at the initiative of the American Academy of Sleep Medicine, and regularly updated over years. They offer an important tool to assess objective markers in different types of sleep/wake subjective complaints. With the aims and advantages of simplicity, reproducibility and standardization of practices in research and, most of all, in sleep medicine, they have overall changed little in the way they describe sleep. However, our knowledge on sleep/wake physiology and sleep disorders has evolved since then. High-density electroencephalography and intracranial electroencephalography studies have highlighted local regulation of sleep mechanisms, with spatio-temporal heterogeneity in vigilance states. Progress in the understanding of sleep disorders has allowed the identification of electrophysiological biomarkers better correlated with clinical symptoms and outcomes than standard sleep parameters. Finally, the huge development of sleep medicine, with a demand for explorations far exceeding the supply, has led to the development of alternative studies, which can be carried out at home, based on a smaller number of electrophysiological signals and on their automatic analysis. In this perspective article, we aim to examine how our description of sleep has been constructed, has evolved, and may still be reshaped in the light of advances in knowledge of sleep physiology and the development of technical recording and analysis tools. After presenting the strengths and limitations of the classification of sleep stages, we propose to challenge the "EEG-EOG-EMG" paradigm by discussing the physiological signals required for sleep stages identification, provide an overview of new tools and automatic analysis methods and propose avenues for the development of new approaches to describe and understand sleep/wake states.

Computerized detection of cyclic alternating patterns of sleep: A new paradigm, future scope and challenges

BACKGROUND AND OBJECTIVES

Sleep quality is associated with wellness, and its assessment can help diagnose several disorders and diseases. Sleep analysis is commonly performed based on self-rating indices, sleep duration, environmental factors, physiologically and polysomnographic-derived parameters, and the occurrence of disorders. However, the correlation that has been observed between the subjective assessment and objective measurements of sleep quality is small. Recently, a few automated systems have been suugested to measure sleep quality to address this challenge. Sleep quality can be assessed by evaluating macrostructure-based sleep analysis via the examination of sleep cycles, namely Rapid Eye Movement (REM) and Non Rapid Eye Movement (NREM) with N1, N2, and N3 stages. However, macrostructure sleep analysis does not consider transitory phenomena like K-complexes and transient fluctuations, which are indispensable in diagnosing various sleep disorders. The CAP, part of the microstructure of sleep, may offer a more precise and relevant examination of sleep and can be considered one of the candidates to measure sleep quality and identify sleep disorders such as insomnia and apnea. CAP is characterized by very subtle changes in the brain's electroencephalogram (EEG) signals that occur during the NREM stage of sleep. The variations among these patterns in healthy subjects and subjects with sleep disorders can be used to identify sleep disorders. Studying CAP is highly arduous for human experts; thus, developing automated systems for assessing CAP is gaining momentum. Developing new techniques for automated CAP detection installed in clinical setups is essential. This paper aims to analyze the algorithms and methods presented in the literature for the automatic assessment of CAP and the development of CAP-based sleep markers that may enhance sleep quality assessment, helping diagnose sleep disorders.

METHODS

This literature survey examined the automated assessment of CAP and related parameters. We have reviewed 34 research articles, including fourteen ML, nine DL, and ten based on some other techniques.

RESULTS

The review includes various algorithms, databases, features, classifiers, and classification performances and their comparisons, advantages, and limitations of automated systems for CAP assessment.

CONCLUSION

A detailed description of state-of-the-art research findings on automated CAP assessment and associated challenges has been presented. Also, the research gaps have been identified based on our review. Further, future research directions are suggested for sleep quality assessment using CAP.

Effects of continuous positive airway pressure on very short-term blood pressure variability associated with sleep-disordered breathing by pulse transit time-based blood pressure measurements

BACKGROUND

Blood pressure (BP) variability (BPV) is a predictor of cardiovascular outcomes independently of BP absolute values. We previously reported that pulse transit time (PTT) enables monitoring beat-to-beat BP, identifying a strong relationship between the extent of very short-term BPV and the severity of sleep-disordered breathing (SDB). Here, we investigated the effects of continuous positive airway pressure (CPAP) on very short-term BPV.

METHODS

We studied 66 patients (mean age 62 years old, 73% male) with newly diagnosed SDB who underwent full polysomnography on two consecutive days for diagnosis (baseline) and CPAP, together with PTT-driven BP continuous recording. PTT index was defined as the average number of acute transient rises in BP (≥12 mmHg) within 30 s/h.

RESULTS

CPAP treatment effectively improved SDB parameters, and attenuated PTT-based BP absolute values during the night-time. Very short-term BPV that includes PTT index and standard deviation (SD) of systolic PTT-BP was significantly reduced by CPAP therapy. The changes in PTT index from baseline to CPAP were positively correlated with the changes in apnea-hypopnea index, obstructive apnea index (OAI), oxygen desaturation index, minimal SpO 2 , and mean SpO 2 . Multivariate regression analysis revealed that changes in OAI and minimal SpO 2 , as well as heart failure, were the independent factors in determining the reduction of PTT index following CPAP.

CONCLUSION

PTT-driven BP monitoring discovered the favorable effects of CPAP on very short-term BPV associated with SDB events. Targeting very short-term BPV may be a novel approach to identifying individuals who experience greater benefits from CPAP.

Potential of Polyphenols for Improving Sleep: A Preliminary Results from Review of Human Clinical Trials and Mechanistic Insights

Global epidemiologic evidence supports an interrelationship between sleep disorders and fruits and vegetable ingestion. Polyphenols, a broad group of plant substances, are associated with several biologic processes, including oxidative stress and signaling pathways that regulate the expression of genes promoting an anti-inflammatory environment. Understanding whether and how polyphenol intake is related to sleep may provide avenues to improve sleep and contribute to delaying or preventing the development of chronic disease. This review aims to assess the public health implications of the association between polyphenol intake and sleep and to inform future research. The effects of polyphenol intake, including chlorogenic acid, resveratrol, rosmarinic acid, and catechins, on sleep quality and quantity are discussed to identify polyphenol molecules that may improve sleep. Although some animal studies have investigated the mechanisms underlying the effects of polyphenols on sleep, the paucity of trials, especially randomized controlled trials, does not allow for conducting a meta-analysis to reach clear conclusions about the relationships among these studies to support the sleep-improving effects of polyphenols.

Objective multidisciplinary measurements of sleep disturbance and autonomic dysfunction as risk factors for chronic subjective tinnitus

PURPOSE

This observational study assessed sleep disturbance and autonomic dysfunction as risk factors for chronic subjective tinnitus through polysomnography (PSG) and autonomic function tests.

METHODS

Adult patients with chronic subjective tinnitus who visited the department of otolaryngology in our hospitals (n = 40), along with controls without tinnitus (n = 80), were recruited. Individuals with an average hearing threshold level (HL) exceeding 25 dB HL and a known diagnosis of insomnia were excluded. Objective assessments comprised pure-tone audiometry, PSG, and autonomic function tests (e.g., the cold pressor test).

RESULTS

Patients with prolonged sleep latency, lower sleep efficiency, and sympathetic hyperactivity had significantly higher risks of developing tinnitus. No interaction effect between poor sleep quality and sympathetic hyperactivity on tinnitus was detected.

CONCLUSION

This is the first study to administer PSG and autonomic function tests to patients with chronic subjective tinnitus. Poor sleep quality and autonomic dysfunction were implicated as risk factors for tinnitus. PSG and the autonomic function tests helped identify tinnitus-related comorbidities and inform tinnitus treatment. Sleep disturbance and autonomic dysfunction did not exert an interaction effect on tinnitus. Further studies with a larger sample size and the inclusion of patients with more severe tinnitus are warranted.

Sleep disordered breathing and its relation to stroke and pulmonary hypertension in children with sickle cell disease: a single-center cross-sectional study

Sleep disordered breathing (SDB) is a common underdiagnosed sequela of sickle cell disease (SCD) that has been linked to the frequency of vaso-occlusive crises. To determine the frequency of SDB in children with SCD and its association to SCD-related complications, thirty children and adolescents with SCD at their steady state underwent clinical, laboratory, and radiological assessment using transcranial duplex (TCD) and echo assessment of tricuspid regurge velocity (TRV). All participants had an overnight polysomnography after completing the modified STOP-Bang questionnaire. The mean age of the studied cohort was 10.2 years, with male: female ratio 1.7:1. Six children (20%) had high-risk for obstructive sleep apnea (OSA), while nine (30%) were at intermediate risk. Sleep apnea defined as apnea (AHI) > 1 event/hour was found among 18/30 (60%) subjects (14 males and 4 females). Children with AHI > 5 (moderate to severe OSA) had significantly higher TRV (p = 0.007) and left MCA flow velocity (p = 0.049) when compared to those with AHI < 5. Children with AHI > 5 were at higher risk of OSA according to the modified STOP-Bang questionnaire (p = 0.02). AHI positively correlated with TRV (r = 0.53, p = 0.003), right MCA flow velocity (r = 0.45, p = 0.013), and left MCA flow velocity (r = 0.55, p = 0.002), and negatively correlated to BMI-SDS (r =  - 0.48, p = 0.008). The high frequency of OSA in the studied cohort with SCD and its association with increasing risk of PH and TCD changes highlights the importance of early detection and management of OSA in children with SCD.

Effects of using a snooze alarm on sleep inertia after morning awakening

BACKGROUND

Many people use the snooze function of digital alarm clocks for morning awakening, but the effects of a snooze alarm on waking are unclear. We examined the effects of a snooze alarm on sleep inertia, which is a transitional state characterized by reduced arousal and impaired cognitive and behavioral performance immediately upon awakening.

METHODS

In study 1, healthy Japanese university students responded to a sleep survey during a psychology class (study 1), and we collected 293 valid responses. In study 2, we compared a separate sample of university students (n = 10) for the effects of using or not using a snooze alarm on sleep inertia immediately after awakening from normal nocturnal sleep in a sleep laboratory.

RESULTS

Of 293 valid respondents in study 1, 251 often used a tool to wake up in the morning (85.7%). Moreover, 70.5% reported often using the snooze function of their mobile phones, mainly to reduce anxiety about oversleeping. Study 2 indicated no differences in the sleep quality or quantity before awakening with or without the snooze alarm, except in the last 20 min. However, during the last 20 min of sleep with snooze alarm, the snooze alarm prolonged waking and stage N1 sleep. Stage N1 sleep is non-rapid eye movement sleep that is primarily defined as a drowsy state. Furthermore, Global Vigor values were enhanced after awakening compared to pre-sleep in the no-snooze condition.

CONCLUSIONS

Using a snooze alarm prolongs sleep inertia compared to a single alarm, possibly because snooze alarms induce repeated forced awakenings.

Effects of age and sex on vasomotor activity and baroreflex sensitivity during the sleep-wake cycle

Cardiovascular function is related to age, sex, and state of consciousness. We hypothesized that cardiovagal baroreflex sensitivity (BRS) demonstrates different patterns in both sexes before and after 50 years of age and that these patterns are associated with patterned changes during the sleep-wake cycle. We recruited 67 healthy participants (aged 20-79 years; 41 women) and divided them into four age groups: 20-29, 30-49, 50-69, and 70-79 years. All the participants underwent polysomnography and blood pressure measurements. For each participant, we used the average of the arterial pressure variability, heart rate variability (HRV), and BRS parameters during the sleep-wake stages. BRS and HRV parameters were significantly negatively correlated with age. The BRS indexes were significantly lower in the participants aged ≥ 50 years than in those aged < 50 years, and these age-related declines were more apparent during non-rapid eye movement sleep than during wakefulness. Only BRS demonstrated a significantly negative correlation with age in participants ≥ 50 years old. Women exhibited a stronger association than men between BRS and age and an earlier decline in BRS. Changes in BRS varied with age, sex, and consciousness state, each demonstrating a specific pattern. The age of 50 years appeared to be a crucial turning point for sexual dimorphism in BRS. Baroreflex modulation of the cardiovascular system during sleep sensitively delineated the age- and sex-dependent BRS patterns, highlighting the clinical importance of our results. Our findings may aid in screening for neurocardiac abnormalities in apparently healthy individuals.

Fast Sleep Stage Classification Using Cascaded Support Vector Machines with Single-Channel EEG Signals

Long-term sleep stage monitoring is very important for the diagnosis and treatment of insomnia. With the development of wearable electroencephalogram (EEG) devices, we developed a fast and accurate sleep stage classification method in this study with single-channel EEG signals for practical applications. The original sleep recordings were collected from the Sleep-EDF database. The wavelet threshold denoising (WTD) method and wavelet packet transformation (WPT) method were applied as signal preprocessing to extract six kinds of characteristic waves. With a comprehensive feature system including time, frequency, and nonlinear dynamics, we obtained the sleep stage classification results with different Support Vector Machine (SVM) models. We proposed a novel classification method based on cascaded SVM models with various features extracted from denoised EEG signals. To enhance the accuracy and generalization performance of this method, nonlinear dynamics features were taken into consideration. With nonlinear dynamics features included, the average classification accuracy was up to 88.11% using this method. In addition, with cascaded SVM models, the classification accuracy of the non-rapid eye movement sleep stage 1 (N1) was enhanced from 41.5% to 55.65% compared with the single SVM model, and the overall classification time for each epoch was less than 1.7 s. Moreover, we demonstrated that it was possible to apply this method for long-term sleep stage monitor applications.

MRASleepNet: a multi-resolution attention network for sleep stage classification using single-channel EEG

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/.

Sleep, circadian biology and skeletal muscle interactions: Implications for metabolic health

There currently exists a modern epidemic of sleep loss, triggered by the changing demands of our 21st century lifestyle that embrace 'round-the-clock' remote working hours, access to energy-dense food, prolonged periods of inactivity, and on-line social activities. Disturbances to sleep patterns impart widespread and adverse effects on numerous cells, tissues, and organs. Insufficient sleep causes circadian misalignment in humans, including perturbed peripheral clocks, leading to disrupted skeletal muscle and liver metabolism, and whole-body energy homeostasis. Fragmented or insufficient sleep also perturbs the hormonal milieu, shifting it towards a catabolic state, resulting in reduced rates of skeletal muscle protein synthesis. The interaction between disrupted sleep and skeletal muscle metabolic health is complex, with the mechanisms underpinning sleep-related disturbances on this tissue often multifaceted. Strategies to promote sufficient sleep duration combined with the appropriate timing of meals and physical activity to maintain circadian rhythmicity are important to mitigate the adverse effects of inadequate sleep on whole-body and skeletal muscle metabolic health. This review summarises the complex relationship between sleep, circadian biology, and skeletal muscle, and discusses the effectiveness of several strategies to mitigate the negative effects of disturbed sleep or circadian rhythms on skeletal muscle health.

A review of automated sleep disorder detection

Automated sleep disorder detection is challenging because physiological symptoms can vary widely. These variations make it difficult to create effective sleep disorder detection models which support hu-man experts during diagnosis and treatment monitoring. From 2010 to 2021, authors of 95 scientific papers have taken up the challenge of automating sleep disorder detection. This paper provides an expert review of this work. We investigated whether digital technology and Artificial Intelligence (AI) can provide automated diagnosis support for sleep disorders. We followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines during the content discovery phase. We compared the performance of proposed sleep disorder detection methods, involving differ-ent datasets or signals. During the review, we found eight sleep disorders, of which sleep apnea and insomnia were the most studied. These disorders can be diagnosed using several kinds of biomedical signals, such as Electrocardiogram (ECG), Polysomnography (PSG), Electroencephalogram (EEG), Electromyogram (EMG), and snore sound. Subsequently, we established areas of commonality and distinctiveness. Common to all reviewed papers was that AI models were trained and tested with labelled physiological signals. Looking deeper, we discovered that 24 distinct algorithms were used for the detection task. The nature of these algorithms evolved, before 2017 only traditional Machine Learning (ML) was used. From 2018 onward, both ML and Deep Learning (DL) methods were used for sleep disorder detection. The strong emergence of DL algorithms has considerable implications for future detection systems because these algorithms demand significantly more data for training and testing when compared with ML. Based on our review results, we suggest that both type and amount of labelled data is crucial for the design of future sleep disorder detection systems because this will steer the choice of AI algorithm which establishes the desired decision support. As a guiding principle, more labelled data will help to represent the variations in symptoms. DL algorithms can extract information from these larger data quantities more effectively, therefore; we predict that the role of these algorithms will continue to expand.

Local networks from different parts of the human cerebral cortex generate and share the same population dynamic

A major goal of neuroscience is to reveal mechanisms supporting collaborative actions of neurons in local and larger-scale networks. However, no clear overall principle of operation has emerged despite decades-long experimental efforts. Here, we used an unbiased method to extract and identify the dynamics of local postsynaptic network states contained in the cortical field potential. Field potentials were recorded by depth electrodes targeting a wide selection of cortical regions during spontaneous activities, and sensory, motor, and cognitive experimental tasks. Despite different architectures and different activities, all local cortical networks generated the same type of dynamic confined to one region only of state space. Surprisingly, within this region, state trajectories expanded and contracted continuously during all brain activities and generated a single expansion followed by a contraction in a single trial. This behavior deviates from known attractors and attractor networks. The state-space contractions of particular subsets of brain regions cross-correlated during perceptive, motor, and cognitive tasks. Our results imply that the cortex does not need to change its dynamic to shift between different activities, making task-switching inherent in the dynamic of collective cortical operations. Our results provide a mathematically described general explanation of local and larger scale cortical dynamic.

Night shifts in interns: Effects of daytime napping on autonomic activity and cognitive function

Objective

Night shifts have adverse cognitive outcomes that might be attenuated by daytime napping. The neurovisceral integration model suggests that resting vagally mediated heart rate variability (vmHRV) is linked with cognitive function. This study investigated the relationship between resting vmHRV and cognitive function after different nap durations in interns after shift work.

Methods

A total of 105 interns were randomly allocated to one of three groups (non-nap, n = 35; 15-min nap, n = 35; 45-min nap, n = 35) to perform cognitive tests and resting vmHRV at 12:00, 15:00 and 18:00. Information processing (digit symbol substitution test; DSST), motor speed (finger tapping test; FTT), response selection (choice reaction time; CRT), and attention shifts (shifting attention test; SAT) were assessed. Resting vmHRV was assessed at baseline and during each cognitive task across groups.

Results

Compared with the non-nap control, the 15-min and 45-min naps improved all outcome measures (including subjective sleepiness and cognitive performance) at 15:00, with some benefits maintained at 18:00. The 15-min nap produced significantly greater benefits on the FTT at 15:00 after napping than did the 45-min nap. Resting vmHRV was significantly correlated with DSST and SAT performance. In addition, FTT performance was the only significant predictor of DSST performance across different nap durations.

Conclusion

Our results demonstrate links between daytime napping (in particular, a 15-min nap) and improved cognitive control in relation to autonomic activity after shift work in interns. These results indicated that autonomic activity when awake plays a crucial role in DSST and SAT performance and facilitated the understanding of differences in neurocognitive mechanisms underlying information processing after different nap durations.

Unveiling the Associations between EEG Indices and Cognitive Deficits in Schizophrenia-Spectrum Disorders: A Systematic Review

Cognitive dysfunctions represent a core feature of schizophrenia-spectrum disorders due to their presence throughout different illness stages and their impact on functioning. Abnormalities in electrophysiology (EEG) measures are highly related to these impairments, but the use of EEG indices in clinical practice is still limited. A systematic review of articles using Pubmed, Scopus and PsychINFO was undertaken in November 2021 to provide an overview of the relationships between EEG indices and cognitive impairment in schizophrenia-spectrum disorders. Out of 2433 screened records, 135 studies were included in a qualitative review. Although the results were heterogeneous, some significant correlations were identified. In particular, abnormalities in alpha, theta and gamma activity, as well as in MMN and P300, were associated with impairments in cognitive domains such as attention, working memory, visual and verbal learning and executive functioning during at-risk mental states, early and chronic stages of schizophrenia-spectrum disorders. The review suggests that machine learning approaches together with a careful selection of validated EEG and cognitive indices and characterization of clinical phenotypes might contribute to increase the use of EEG-based measures in clinical settings.

Research advances in the study of sleep disorders, circadian rhythm disturbances and Alzheimer’s disease

Although there are still no satisfactory answers to the question of why we need to sleep, a better understanding of its function will help to improve societal attitudes toward sleep. Sleep disorders are very common in neurodegenerative diseases and are a key factor in the quality of life of patients and their families. Alzheimer’s disease (AD) is an insidious and irreversible neurodegenerative disease. Along with progressive cognitive impairment, sleep disorders and disturbances in circadian rhythms play a key role in the progression of AD. Sleep and circadian rhythm disturbances are more common in patients with AD than in the general population and can appear early in the course of the disease. Therefore, this review discusses the bidirectional relationships among circadian rhythm disturbances, sleep disorders, and AD. In addition, pharmacological and non-pharmacological treatment options for patients with AD and sleep disorders are outlined.

Bright Light During Wakefulness Improves Sleep Quality in Healthy Men: A Forced Desynchrony Study Under Dim and Bright Light (III)

Under real-life conditions, increased light exposure during wakefulness seems associated with improved sleep quality, quantified as reduced time awake during bed time, increased time spent in non-rapid eye movement (NREM) sleep, or increased power of the electroencephalogram delta band (0.5-4 Hz). The causality of these important relationships and their dependency on circadian phase and/or time awake has not been studied in depth. To disentangle possible circadian and homeostatic interactions, we employed a forced desynchrony protocol under dim light (6 lux) and under bright light (1300 lux) during wakefulness. Our protocol consisted of a fast cycling sleep-wake schedule (13 h wakefulness—5 h sleep; 4 cycles), followed by 3 h recovery sleep in a within-subject cross-over design. Individuals (8 men) were equipped with 10 polysomnography electrodes. Subjective sleep quality was measured immediately after wakening with a questionnaire. Results indicated that circadian variation in delta power was only detected under dim light. Circadian variation in time in rapid eye movement (REM) sleep and wakefulness were uninfluenced by light. Prior light exposure increased accumulation of delta power and time in NREM sleep, while it decreased wakefulness, especially during the circadian wake phase (biological day). Subjective sleep quality scores showed that participants rated their sleep quality better after bright light exposure while sleeping when the circadian system promoted wakefulness. These results suggest that high environmental light intensity either increases sleep pressure buildup during wakefulness or prevents the occurrence of micro-sleep, leading to improved quality of subsequent sleep.

Human fertility and sleep disturbances: A narrative review

INTRODUCTION

Many factors may be hidden behind the global fertility decline observed in Western countries. Alongside the progressively increased age of infertile couples, environmental and behavioural factors, including non-optimal lifestyle habits, should be considered. Among these, sleep disorders have been suggested to be linked to human fertility.

METHODS

This is a narrative review, describing first sleep physiology, its disturbances, and the tools able to quantify sleep dysfunction. Then, we consider all available studies aimed at investigating the connection between sleep disorders and human fertility, providing a comprehensive view on this topic.

RESULTS

Forty-two studies investigating the relationship between sleep habits and human reproduction were included. All the published evidence was grouped according to the aspect of human fertility considered, i.e. i) female reproductive functions, ii) male reproductive functions, iii) natural conception and iv) assisted reproduction. For each of the sub-groups considered, the connection between sleep dysregulation and human fertility was classified according to specific sleep characteristics, such as sleep duration, quality, and habits. In addition, possible physio-pathological mechanisms proposed to support the link between sleep and fertility were summarized.

CONCLUSION

This review summarizes the most relevant findings about the intricate and still largely unknown network of molecular pathways involved in the regulation of circadian homeostasis, to which sleep contributes, essential for reproductive physiology. Thus, many mechanisms seem correlate sleep disorders to reproductive health, such as adrenal activation, circadian dysregulation, and genetic influences. This review highlights the need to properly designed trials on the topic.

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.

Interictal Heart Rate Variability as a Biomarker for Comorbid Depressive Disorders among People with Epilepsy

Depressive disorders are common among people with epilepsy (PwE). We here aimed to report an unbiased automatic classification of epilepsy comorbid depressive disorder cases via training a linear support vector machine (SVM) model using the interictal heart rate variability (HRV) data. One hundred and eighty-six subjects participated in this study. Among all participants, we recorded demographic information, epilepsy states and neuropsychiatric features. For each subject, we performed simultaneous electrocardiography and electroencephalography recordings both in wakefulness and non-rapid eye movement (NREM) sleep stage. Using these data, we systematically explored the full parameter space in order to determine the most effective combinations of data to classify the depression status in PwE. PwE with depressive disorders exhibited significant alterations in HRV parameters, including decreased time domain and nonlinear domain values both in wakefulness and NREM sleep stage compared with without depressive disorders and non-epilepsy controls. Interestingly, PwE without depressive disorder showed the same level of HRV values as the non-epilepsy control subjects. The SVM classification model of PwE depression status achieved a higher classification accuracy with the combination of HRV parameters in wakefulness and NREM sleep stage. Furthermore, the receiver operating characteristic (ROC) curve of the SVM classification model showed a satisfying area under the ROC curve (AUC: 0.758). Intriguingly, we found that the HRV measurements during NREM sleep are particularly important for correct classification, suggesting a mechanistic link between the dysregulation of heart rate during sleep and the development of depressive disorders in PwE. Our classification model may provide an objective measurement to assess the depressive status in PwE.

Mouth opening/breathing is common in sleep apnea and linked to more nocturnal water loss

OBJECTIVES

Mouth opening/breathing during sleep is common in patients with obstructive sleep apnea (OSA), which is probably associated with more water loss and higher risk for nocturnal ischemic heart attack. This study aimed to evaluate nocturnal changes in hematocrit/hemoglobin levels and estimated plasma volume loss in OSA patients and its relation to their OSA severity and mouth open/breathing.

METHODS

Sixty OSA patients and fifteen healthy controls were enrolled and underwent overnight polysomnography. Mouth status was evaluated via an infrared camera and nasal/mouth airflow. Hematocrit and hemoglobin levels in peripheral venous blood were measured before and after sleep to estimate the change of plasma volume.

RESULTS

Compared to controls, OSA patients had a greater nocturnal increase in hematocrit (1.35% vs. 1.0%, p=0.013), hemoglobin (0.50% vs. 0.30%, p=0.002) and more estimated water loss (5.5% vs 3.7% of plasma volume, p<0.013). The extent of increase was correlated to apnea-hypopnea index_the marker of OSA severity (Spearman's ρ=0.332, p=0.004; ρ=0.367, p=0.001 for hematocrit, hemoglobin, respectively), which remained significant after serial multivariate adjustment. OSA patients had more sleep time with mouth open (96.7% vs 26.7% of total sleep time, p<0.001) and time with complete mouth breathing (14.1% vs 2.7%, p<0.001). The extent of mouth breathing was correlated to apnea-hypopnea index (ρ=0.487, p<0.001), nocturnal increase in hematocrit/hemoglobin levels (ρ=0.236, p=0.042; ρ=0.304, p=0.008, respectively) and estimated plasma volume loss (ρ=0.262, p=0.023).

CONCLUSIONS

OSA patients had a greater increase in hematocrit/hemoglobin levels after sleep, which is probably linked to more water loss and more sleep time with mouth open/breathing.

Hydroalcoholic Extract of Ashwagandha Improves Sleep by Modulating GABA/Histamine Receptors and EEG Slow-Wave Pattern in In Vitro - In Vivo Experimental Models

Withania somnifera (ashwagandha) has been used traditionally as a remedy for insomnia and to enhance cognitive function. The effects of ashwagandha extract (AE, 35% withanolide glycosides, Shoden^Ⓡ) on the expression levels of γ-aminobutyric acid (GABA)_Aρ1 and histamine H3 receptors in Rattus norvegicus glioblastoma (C6) cell lines were studied using semiquantitative reverse transcriptase-polymerase chain reactions. The effects of AE on sleep onset and duration were studied in Swiss albino mice using the pentobarbital-induced sleep model. Furthermore, the effects on nonrapid eye movement (NREM) and rapid eye movement sleep patterns were studied in Wistar rats with electroencephalogram (EEG) to support the improvement in sleep quality. There was an increase in gene expression levels of GABA_Aρ1 receptor (1.38 and 1.94 folds) and histamine H3 (1.14 and 1.29 folds) receptors induced by AE at doses of 15 and 30 μg/mL compared to control. AE at doses of 10, 25, and 50 mg/kg body weight showed a significant decrease in time to sleep onset and increased total sleep duration in the pentobarbital-induced sleep model. At 50 mg/kg body weight dosage level, a 34% decrease (P<0.0001) in sleep onset time and 47% increase (P<0.0001) in sleep duration was observed. The EEG study showed significant improvement in alpha, beta, theta, delta, and gamma bands at doses of 10, 25, and 50 mg/kg body weight with delta waves showing increases of 30%, 46% (P<0.05), and 34%, respectively. The induction of sleep, GABA-mimetic action, NREM sleep, and the effects on slow-wave cycles support the calming property of AE in improving the quality of sleep.

The impact of treatment of periodic limb movements in sleep on blood pressure in patients with and without sleep apnea

Improving sleep quality in patients with obstructive sleep apnea (OSA) by positive airway pressure therapy is associated with a decrease of blood pressure (BP). It remains elusive, whether treatment of sleep disturbances due to restless legs syndrome with symptomatic periodic limb movements in sleep (PLMS) affects BP as well. The present study provides first data on this issue. Retrospective study on patients undergoing polysomnography in a German University Hospital. Inclusion criteria were first diagnosis of restless legs syndrome with PLMS (PLM index ≥ 15/h and PLM arousal index ≥ 5/h) with subsequent initiation of levodopa/benserazide or dopamine agonists. Exclusion criterion was an initiation or change of preexisting positive airway pressure therapy between baseline and follow-up. BP and Epworth sleepiness scale were assessed at two consecutive polysomnographies. After screening of 953 PLMS data sets, 114 patients (mean age 62.1 ± 12.1 years) were included. 100 patients (87.7%) were started on levodopa/benserazide, 14 patients (12.2%) on dopamine agonists. Treatment was associated with significant reductions of PLM index (81.2 ± 65.0 vs. 39.8 ± 51.2, p < 0.001) and ESS (6 [interquartile range, IQR, 3–10.5] vs. 5 [IQR 3–10], p = 0.013). Systolic BP decreased from 132.9 ± 17.1 to 128.0 ± 15.8 mmHg (p = 0.006), whereas there was no significant change of diastolic BP (76.7 ± 10.9 vs. 75.1 ± 9.2 mmHg, p = 0.15) and heart rate (71.5 ± 11.9 vs. 71.3 ± 12.7, p = 0.84). The number of antihypertensive drugs remained unchanged with a median of 2 (IQR 1–3, p = 0.27). Dopaminergic treatment of PLMS is associated with an improvement of sleep quality and a decrease of systolic BP comparable to treatment OSA.

Evaluation of a Single-Channel EEG-Based Sleep Staging Algorithm

Sleep staging is the basis of sleep assessment and plays a crucial role in the early diagnosis and intervention of sleep disorders. Manual sleep staging by a specialist is time-consuming and is influenced by subjective factors. Moreover, some automatic sleep staging algorithms are complex and inaccurate. The paper proposes a single-channel EEG-based sleep staging method that provides reliable technical support for diagnosing sleep problems. In this study, 59 features were extracted from three aspects: time domain, frequency domain, and nonlinear indexes based on single-channel EEG data. Support vector machine, neural network, decision tree, and random forest classifier were used to classify sleep stages automatically. The results reveal that the random forest classifier has the best sleep staging performance among the four algorithms. The recognition rate of the Wake phase was the highest, at 92.13%, and that of the N1 phase was the lowest, at 73.46%, with an average accuracy of 83.61%. The embedded method was adopted for feature filtering. The results of sleep staging of the 11-dimensional features after filtering show that the random forest model achieved 83.51% staging accuracy under the condition of reduced feature dimensions, and the coincidence rate with the use of all features for sleep staging was 94.85%. Our study confirms the robustness of the random forest model in sleep staging, which also represents a high classification accuracy with appropriate classifier algorithms, even using single-channel EEG data. This study provides a new direction for the portability of clinical EEG monitoring.