Polysomnographic Recordings Research Articles

Ictal Bradycardia and Asystole in Sleep-Related Hypermotor Epilepsy: A Study of 200 Patients.

Background: Ictal bradycardia (IB) and asystole (IA) represent a rare but potentially harmful feature of epileptic seizures. The aim of this study was to study IB/IA in patients with sleep-related hypermotor epilepsy (SHE). Methods: We retrospectively included cases with video-EEG-confirmed SHE who attended our Institute up to January 2021. We reviewed the ictal polysomnography recordings focusing on ECG and identified cases with IB (R-R interval ≥ 2 s or a ≥10% decrease of baseline heart rate) and IA (R-R interval ≥ 4 s). Results: We included 200 patients (123 males, 61.5%), with a mean age of 42 ± 16 years. Twenty patients (20%) had focal cortical dysplasia (FCD) on brain MRI. Eighteen (out of 104 tested, 17.3%) carried pathogenic variants (mTOR pathway, n = 10, nAchR subunits, n = 4, KCNT1, n = 4). We identified IB/IA in four cases (2%): three had IA (mean 10 s) and one had IB. Three patients had FCD (left fronto-insular region, left amygdala, right mid-temporal gyrus) and two had pathogenic variants in DEPDC5; both features were more prevalent in patients with IB/IA than those without (p = 0.003 and p = 0.037, respectively). Conclusions: We identified IB/IA in 2% of patients with SHE and showed that this subgroup more frequently had FCD on brain MRI and pathogenic variants in genes related to the mTOR pathway.

ENHANCED CHAMELEON SWARM OPTIMIZATION-BASED ENSEMBLE LEARNING APPROACH FOR SLEEP STAGE CLASSIFICATION FRAMEWORK

In today’s world, every individual faces the maladies of sleep malfunction, which is diagnosed by analyzing the PolySomnoGraphy (PSG) records. The primary remedy is systematically identifying the sleep stages. But practically, the sleep stage analysis depends on the visual examination of the 30[Formula: see text]s time duration of PSG record signals. Such expertise has developed an enormous model to rectify the issues. Albeit, it exhibits effective performance, it becomes cumbersome to handle the large-scale dimension of data. Thus, the model becomes fragile when it is implemented in some sleep clinics. Even if it contains a better compatible of PSG; it subsists with limitations such as obtaining less efficiency and mitigates the robustness of the system. To alleviate this problem, a novel scheme is proposed by an Ensemble Learning Approach (ELA) for sleep stage classification using ElectroEncephaloGram (EEG) signals. Initially, the required EEG signals for the proposed model are gathered from the standard data sources. Further, the garnered EEG signals are utilized in the sleep signal extraction phase, in which the band pass filter is employed for extracting the sleep signals. The extracted sleep signal is used under the signal decomposition phase, which is accomplished by 5-level Discrete Wavelet Transform (DWT) for decomposing the sleep signals. Subsequently, the decomposed signals are given into the feature extraction phase, where the spectral features and Principal Component Analysis (PCA) are used for extracting the EEG signal features. Further, the extracted features are fed as input into ELA using Deep Temporal Convolutional Networks (DTCNs), Long Short-Term Memory (LSTM), and Deep Neural Networks (DNNs) for classifying the sleep stages. Here, the hyper-parameter tuning is engaged for enhancing the classification performance using the Modified Position Updated Chameleon Search Algorithm (MPU-CSA). The experimental analysis is conducted by distinct validating metrics for revealing the efficacy of the developed sleep stage classification model over the conventional models.

Acute and chronic sleep restriction differentially modify maternal behavior and milk macronutrient composition in the postpartum rat

BackgroundsSleep restriction is considered a stressful condition itself, causing a wide variety of physiological alterations, from cognitive and hormonal to immunological status. In addition, it is established that stress in mother rats can modify milk ejection, milk composition, and maternal care of the pups. Also, sleep disturbances during the early stages of motherhood are a common feature of all studied species. In this context, while the impacts of sleep disruption in non-lactating animals were extensively investigated, its repercussions during the initial phases of motherhood have been poorly explored. Therefore, we wonder if maternal behavior, milk ejection and its macronutrient composition would be disrupted when mother rats are subjected to an additional acute or chronic sleep restriction to the already existing sleep disturbances. MethodsLactating rats were implanted with unilateral electrodes for polysomnographic recordings and for deep brain electrical stimulation into mesopontine waking-promoting area (for sleep deprivation). During the early postpartum period (postpartum day 5–9), mother rats were randomly assigned into one of three groups: chronic sleep restriction group (CSR; 6 h of sleep deprivation/day for five consecutive days), acute sleep restriction group (ASR; 6 h of sleep deprivation only for one day), or undisturbed group (control group). Active maternal behaviors (retrievals of the pups into the nest, mouthing, lickings [corporal and anogenital] and sniffing the pups) and passive maternal behaviors (kyphotic and supine nursing postures) were evaluated during a 30 min period without sleep restriction immediately after the sleep restriction or control period. The litter weight gain was assessed every day, and on the last experimental session mothers were milked for posterior macronutrients analysis (protein, carbohydrates and fat). ResultsWhen compared to control group, CSR decreased the amount of milk ejected in the middle days of the sleep restriction period, while ASR did not affect this parameter. Moreover, ASR reduced milk protein content compared to control and CSR groups. Finally, compared to the control group, CSR reduced active maternal behaviors towards the end of the treatment days. ConclusionsWe demonstrated that not only acute but also chronic sleep restriction impacts on the postpartum period, each one affecting different aspects of maternal behavior and lactation. Our results suggest the existence of a homeostatic recovery mechanism in breastfeeding during CSR, possibly ensuring the survival of the litter, while the decline in active maternal behaviors appears to be cumulative.

Noribogaine acute administration in rats promotes wakefulness and suppresses REM sleep.

Ibogaine is a potent atypical psychedelic that has gained considerable attention due to its antiaddictive and antidepressant properties in preclinical and clinical studies. Previous research from our group showed that ibogaine suppresses sleep and produces an altered wakefulness state, which resembles natural REM sleep. However, after systemic administration, ibogaine is rapidly metabolized to noribogaine, which also shows antiaddictive effects but with a distinct pharmacological profile, making this drug a promising therapeutic candidate. Therefore, we still ignore whether the sleep/wake alterations depend on ibogaine or its principal metabolite noribogaine. To answer this question, we conducted polysomnographic recordings in rats following the administration of pure noribogaine. Our results show that noribogaine promotes wakefulness while reducing slow-wave sleep and blocking REM sleep, similar to our previous results reported for ibogaine administration. Thus, we shed new evidence on the mechanisms by which iboga alkaloids work in the brain.

The effect of slow wave sleep deprivation on mood in adolescents with depressive symptoms: A pilot study

BackgroundThere is an urgent need for safe, rapid-acting treatment strategies for adolescent depression. In depressed adults, slow wave sleep deprivation (SWSD) improved next-day mood without disrupting sleep duration, but SWSD has not been tested in adolescents. In a pilot study, the aim was to assess the effect of SWSD on sleep physiology and mood outcomes (depression, rumination, anhedonia) among adolescents with depressive symptoms. MethodsSixteen adolescents (17.44 ± 1.46 yr, 12 female) completed three nights of polysomnographic sleep recording: Baseline, SWSD, and Recovery nights. Acoustic stimulation (tones of random pitch, duration, and volume) suppressed slow wave sleep (SWS) in real-time during SWSD. After each night, depression, rumination, and anhedonia severity were assessed. ResultsSWSD successfully suppressed SWS, increased N2, and had minimal impact on Rapid Eye Movement (REM), nocturnal awakenings, and total sleep time. While SWSD did not improve depression or anhedonia severity overall, lower baseline non-REM alpha activity and greater SWS rebound during recovery sleep correlated with SWSD-related reduction in clinician-rated depression severity. Next-day rumination severity decreased after SWSD, with sustained improvements following recovery sleep. However, rumination improvement was not associated with SWS suppression, but rather reduction in total sleep time and REM in exploratory correlation models. LimitationsSmall sample size and large proportion of females. ConclusionSWSD did not improve depression in adolescents overall but a subset with low non-REM alpha activity and intact homeostatic sleep regulation may benefit from this approach. Findings from this pilot study also suggest that partial sleep deprivation may be a beneficial therapeutic strategy for rumination in adolescents.

The Chinese Clinical Sleep Database: An Innovative Database System Includes Large-Scale Clinical Data of Chinese Population.

In this study, we established the Chinese Clinical Sleep Database (CCSD), aiming to provide a safe, scalable, and user-friendly database that includes high-quality clinical data from Chinese population to facilitate sleep research. We collect individual's demographic data, scales, anthropometric measurements, clinical diagnosis, and polysomnography (PSG) recordings from the routine medical process of sleep medicine centers using standardized procedures. The distributed cluster storage technology are utilized to store these data. The structured data are stored in a high-performance MySQL database, while the unstructured data are stored in an object storage service. And we have developed an online data platform to share and manage our data. The data collection has been conducted in three hospitals. In the preliminary stage of data collection (from October 18, 2022 to September 4, 2023), our database included a total of 1183 patients. Among them, 56.8% were male and their ages ranged from 3 to 88 years. These patients were diagnosed with various types of sleep disorders. Since the CCSD's inception, it has demonstrated good stability, security, and scalability. As an public database, the CCSD also exhibits user-friendliness. The CCSD contains comprehensive clinical data, which can contribute to the advancement of the diagnosis and treatment strategies for sleep disorders, ultimately promoting sleep health.

Comparative analysis of sleep parameters and structures derived from wearable flexible electrode sleep patches and polysomnography in young adults.

Polysomnography (PSG) is the gold standard for clinical sleep monitoring, but its cost, discomfort, and limited suitability for continuous use present challenges. The flexible electrode sleep patch (FESP) emerges as an economically viable and patient-friendly solution, offering lightweight, simple operation, and self-applicable. Nevertheless, its utilization in young individuals remains uncertain. The objective of this study was to compare sleep data obtained by FESP and PSG in healthy young individuals and analyze agreement for sleep parameters and structure classification. Overnight monitoring with FESP and PSG recordings in 48 participants (mean age: 23 yr) was done. Correlation analysis, Bland-Altman plots, and Cohen's kappa coefficient assessed consistency. Sensitivity, specificity, and predictive values compared classification against PSG. FESP showed strong correlation and consistency with PSG for sleep monitoring. Bland-Altman plots indicated small errors and high consistency. Kappa values (0.70-0.84) suggested substantial agreement for sleep stage classification. Pearson correlation coefficient values for sleep stages (0.75-0.88) and sleep parameters (0.80-0.96) confirm that FESP has a strong application. Intraclass correlation coefficient yielded values between 0.65 and 0.97. In addition, FESP demonstrated an impressive accuracy range of 84.12-93.47% for sleep stage classification. The FESP also features a wearable self-test program with an error rate of no more than 8% for both deep sleep and wake. In young adults, FESP demonstrated reliable monitoring capabilities comparable to PSG. With its low cost and user-friendly design, FESP is a potential alternative for portable sleep assessment in clinical and research applications. Further studies involving larger populations are needed to validate its diagnostic potential.NEW & NOTEWORTHY By comparison with PSG, this study confirmed the reliability of an efficient, objective, low-cost, and noninvasive portable automatic sleep-monitoring device FESP, which provides effective information for long-term family sleep disorder diagnosis and sleep quality monitoring.

A bimodal feature fusion convolutional neural network for detecting obstructive sleep apnea/hypopnea from nasal airflow and oximetry signals

The most prevalent sleep-disordered breathing condition is Obstructive Sleep Apnea (OSA), which has been linked to various health consequences, including cardiovascular disease (CVD) and even sudden death. Therefore, early detection of OSA can effectively help patients prevent the diseases induced by it. However, many existing methods have low accuracy in detecting hypopnea events or even ignore them altogether. According to the guidelines provided by the American Academy of Sleep Medicine (AASM), two modal signals, namely nasal pressure airflow and pulse oxygen saturation (SpO2), offer significant advantages in detecting OSA, particularly hypopnea events. Inspired by this notion, we propose a bimodal feature fusion CNN model that primarily comprises of a dual-branch CNN module and a feature fusion module for the classification of 10-second-long segments of nasal pressure airflow and SpO2. Additionally, an Efficient Channel Attention mechanism (ECA) is incorporated into the second module to adaptively weight feature map of each channel for improving classification accuracy. Furthermore, we design an OSA Severity Assessment Framework (OSAF) to aid physicians in effectively diagnosing OSA severity. The performance of both the bimodal feature fusion CNN model and OSAF is demonstrated to be excellent through per-segment and per-patient experimental results, based on the evaluation of our method using two real-world datasets consisting of polysomnography (PSG) recordings from 450 subjects.

Improving the detection of sleep slow oscillations in electroencephalographic data.

We aimed to build a tool which facilitates manual labeling of sleep slow oscillations (SOs) and evaluate the performance of traditional sleep SO detection algorithms on such a manually labeled data set. We sought to develop improved methods for SO detection. SOs in polysomnographic recordings acquired during nap time from ten older adults were manually labeled using a custom built graphical user interface tool. Three automatic SO detection algorithms previously used in the literature were evaluated on this data set. Additional machine learning and deep learning algorithms were trained on the manually labeled data set. Our custom built tool significantly decreased the time needed for manual labeling, allowing us to manually inspect 96,277 potential SO events. The three automatic SO detection algorithms showed relatively low accuracy (max. 61.08%), but results were qualitatively similar, with SO density and amplitude increasing with sleep depth. The machine learning and deep learning algorithms showed higher accuracy (best: 99.20%) while maintaining a low prediction time. Accurate detection of SO events is important for investigating their role in memory consolidation. In this context, our tool and proposed methods can provide significant help in identifying these events.

Characterization of EEG biomarker of narcolepsy type I and idiopathic hypersomnia in polysomnographic recordings

Characterization of EEG biomarker of narcolepsy type I and idiopathic hypersomnia in polysomnographic recordings

A novel analytic framework to identify the neural signatures of sleep state misperception from polysomnographic recordings

A novel analytic framework to identify the neural signatures of sleep state misperception from polysomnographic recordings

SleepMI: An AI-based screening algorithm for myocardial infarction using nocturnal electrocardiography

Myocardial infarction (MI) is a common cardiovascular disease, the early diagnosis of which is essential for effective treatment and reduced mortality. Therefore, novel methods are required for automatic screening or early diagnosis of MI, and many studies have proposed diverse conventional methods for its detection. In this study, we aimed to develop a sleep-myocardial infarction (sleepMI) algorithm for automatic screening of MI based on nocturnal electrocardiography (ECG) findings from diagnostic polysomnography (PSG) data using artificial intelligence (AI) models. The proposed sleepMI algorithm was designed using representation and ensemble learning methods and optimized via dropout and batch normalization. In the sleepMI algorithm, a deep convolutional neural network and light gradient boost machine (LightGBM) models were mixed to obtain robust and stable performance for screening MI from nocturnal ECG findings. The nocturnal ECG signal was extracted from 2,691 participants (2,331 healthy individuals and 360 patients with MI) from the PSG data of the second follow-up stage of the Sleep Heart Health Study. The nocturnal ECG signal was extracted 3 h after sleep onset and segmented at 30-s intervals for each participant. All ECG datasets were divided into training, validation, and test sets consisting of 574,729, 143,683, and 718,412 segments, respectively. The proposed sleepMI model exhibited very high performance with precision, recall, and F1-score of 99.38%, 99.38%, and 99.38%, respectively. The total mean accuracy for automatic screening of MI using a nocturnal single-lead ECG was 99.387%. MI events can be detected using conventional 12-lead ECG signals and polysomnographic ECG recordings using our model.

Short-Term Stability and Night-to-Night Variability of Sleep Parameters in Nightmares Comorbid with Chronic Insomnia Disorder Across Multiple Nights of Polysomnography.

The purpose of this study was to examine the degree of short-term stability of polysomnographic (PSG) measured sleep parameters and the overall differences between individuals with comorbid nightmares and insomnia compared to those with chronic insomnia disorder alone or good sleeping controls across four nights in the sleep lab. A total of 142 good sleeping controls, 126 chronic insomnia alone and 24 comorbid insomnia/nightmare participants underwent 4 consecutive nights of 8-hour PSG recordings. Outcomes included sleep continuity, architecture, and REM-related parameters across nights 1 through 4. Intraclass correlation coefficients with mixed-effect variances and repeated-measure analysis of covariance were used, respectively, to determine short-term stability as well as between-subjects and time-by-group interaction effects. Wake after sleep onset and stage 1 showed "poor stability" in the comorbid insomnia/nightmare group compared to "moderate stability" in the good sleeping controls and chronic insomnia alone group. Significant between-group effects (all ps<0.05) showed that the comorbid insomnia/nightmare group took longer to fall asleep and had a greater first-night-effect in stage 1 compared to good sleeping controls and chronic insomnia alone group; in addition, the comorbid insomnia/nightmare and insomnia alone groups slept shorter, yet had fewer awakenings and REM periods, compared to the good sleeping controls. Nightmares are associated with abnormal sleep above and beyond REM disruption, as sleep continuity was the primary aspect in which poor stability and group differences emerged. The greater inability to fall asleep and instability of sleep fragmentation in those with comorbid insomnia/nightmares compared to chronic insomnia alone may be attributed to the impact of pre-sleep anticipatory anxiety and nightmare-related distress itself.

Gender differences in the relationship between sleep and age in a Brazilian cohort: the Baependi Heart Study.

Gender and age are well-established determinants of health and sleep health that influence overall health, which also often varies by gender and age. Sleep architecture is an important component of sleep health. The goal of this analysis was to examine whether associations between age and sleep stages differ by gender in the absence of moderate-severe obstructive sleep apnea (OSA) in a rural setting in Brazil. This study conducted polysomnography recordings in the Baependi Heart Study, a cohort of Brazilian adults. Our sample included 584 women and 309 men whose apnea-hypopnea index was ≤15 events/h. We used splines to distinguish non-linear associations between age, total sleep time, wake after sleep onset (WASO), N2, N3, and rapid-eye-movement sleep. The mean (standard deviation; range) age was 47 (14; 18-89) years. All sleep outcomes were associated with age. Compared to men, women had more N3 sleep and less WASO after adjusting for age. Model-based comparisons between genders at specific ages showed statistically higher mean WASO for men at ages 60 (+13.6 min) and 70 years (+19.5 min) and less N3 for men at ages 50 (-13.2 min), 60 (-19.0 min), and 70 years (-19.5 min) but no differences at 20, 30, 40 or 80 years. The other sleep measures did not differ by gender at any age. Thus, even in the absence of moderate-severe OSA, sleep architecture was associated with age across adulthood, and there were gender differences in WASO and N3 at older ages in this rural community.

Effects of acute bouts of evening resistance or endurance exercises on sleep EEG and salivary cortisol.

Introduction: Deleterious effects of exercise close to bedtime could be due to increased physiological arousal that can be detected during sleep using sleep spectral analysis. Resistance and endurance exercises have different effects on cortisol release that may lead them to impact sleep spectral signatures differently. The present study aimed to investigate the effects of two types of evening exercise on sleep architecture, sleep spectral parameters and salivary cortisol. Methods: Young healthy participants came to our laboratory to undergo 3 counterbalanced pre-sleep conditions that started 1h before bedtime (a resistance and an endurance exercise conditions of 30min duration, identical in terms of workload; and a control condition) followed by polysomnographic recordings. Results were compared between the three conditions for 16 participants. Results: Sleep efficiency was lower after both endurance and resistance exercise than after the control condition. Total sleep time was lower after endurance exercise compared to the control condition. Sleep spectral analyses showed that both endurance and resistance exercises led to greater alpha power during N1 sleep stage and greater theta power during N2 sleep stage compared to the control condition. The endurance exercise led to greater beta power during N2 sleep stage, greater alpha power during REM sleep, and higher cortisol levels compared to the control condition (trend), and compared to the resistance exercise condition (significant). The resistance exercise led to lower beta power during N2 sleep stage than the control condition and lower cortisol levels than the endurance exercise condition. Discussion: This study underlines significant modifications of sleep quality and quantity after both moderate evening endurance and resistance exercises. Still, these effects cannot be considered as deleterious. In contrast to the resistance exercise, endurance exercise led to an increase in sleep EEG activity associated with hyperarousal during sleep and higher cortisol levels, suggesting an hyperarousal effect of endurance exercise performed in the evening. These results align with previous warning about the arousal effects of evening exercise but do not support the notion of deleterious effects on sleep. While these results provide support for the physiological effects of evening exercises on sleep, replication with larger sample size is needed.

All Obstructive Sleep Apnea Events Are Not Created Equal: The Relationship between Event-related Hypoxemia and Physiologic Response.

Rationale: Obstructive sleep apnea (OSA) severity is typically assessed by the apnea-hypopnea index (AHI), a frequency-based metric that allocates equal weight to all respiratory events. However, more severe events may have a greater physiologic impact. Objectives: The purpose of this study was to determine whether the degree of event-related hypoxemia would be associated with the postevent physiologic response. Methods: Patients with OSA (AHI, ⩾5/h) from the multicenter Canadian Sleep and Circadian Network cohort were studied. Using mixed-effect linear regression, we examined associations between event-related hypoxic burden (HBev) assessed by the area under the event-related oxygen saturation recording with heart rate changes (ΔHRev), vasoconstriction (vasoconstriction burden [VCBev] assessed with photoplethysmography), and electroencephalographic responses (power ratio before and after events). Results: Polysomnographic recordings from 658 patients (median [interquartile range] age, 55.00 [45.00, 64.00] yr; AHI, 27.15 [14.90, 64.05] events/h; 42% female) were included in the analyses. HBev was associated with an increase in all physiologic responses after controlling for age, sex, body mass index, sleep stage, total sleep time, and study centers; for example, 1 standard deviation increase in HBev was associated with 0.21 [95% confidence interval, 0.2, 0.22], 0.08 [0.08, 0.09], and 0.22 [0.21, 0.23] standard deviation increases in ΔHRev, VCBev, and β-power ratio, respectively. Conclusions: Increased event-related hypoxic burden was associated with greater responses across a broad range of physiologic signals. Future metrics that incorporate information about the variability of these physiologic responses may have promise in providing a more nuanced assessment of OSA severity.

Subjective sleep onset latency is influenced by sleep structure and body heat loss in human subjects.

The present study examined the relationship between subjective sleep onset latency (SOL), sleep structure, changes in skin and body temperature, and subjective evaluation of sleep in healthy young adults to elucidate the pathophysiological mechanisms of insomnia. A total of 28 participants (age 21.54 [0.50] years) with no sleep problems participated in a 1-h polysomnographic recording that obtained objective sleep parameters during the daytime while skin and body temperatures were recorded. The distal-proximal skin temperature gradient (DPG) was calculated. Subjective parameters, such as subjective SOL, sleep time, and restorative sleepiness, were evaluated before and after sleep. Most participants estimated their sleep latency as being longer than their actual SOL (13.7 versus 7.6 min). Objective SOL was significantly correlated with each sleep stage parameter whereas subjective SOL was negatively correlated with Stage N2 sleep duration (Rho = -0.454, p = 0.020), slow-wave activity and delta power (Rho = -0.500, p = 0.011 and Rho = -0.432, p = 0.031, respectively), and ΔDPG (the degree of reduction of heat loss before and after lights-off). Stepwise regression analysis showed that ΔDPG was the strongest predictive factor in explaining the length of subjective SOL. The degree of heat dissipation before and after lights-off contributed most to the sensation of falling asleep in healthy young adults. This finding may be helpful for elucidating the physiological mechanisms of insomnia and its treatment.

Sleep and the Social Profiles of Individuals With Rett Syndrome

BackgroundThis study investigates the distinctive social behaviors observed in individuals with Rett syndrome (RTT), characterized by the loss of spoken language, impaired eye gaze communication, gait abnormalities, and sleep issues. The research aims to identify social profiles in RTT and explore their correlation with sleep, sleep-disordered breathing (SDB), and daytime sleepiness. MethodsStandard overnight sleep macrostructure and respiratory parameters were assessed. Extracting 25 social-related items and one for daytime sleepiness from the Rett Syndrome Behavioral Questionnaire, factor analysis was applied to establish latent social profiles. These profiles were then correlated with sleep parameters. The nonparametric Mann-Whitney U test compared social profiles based on the presence of SDB (defined by an apnea-hypopnea index greater than one per hour) and daytime sleepiness. ResultsThe study involved 12 female subjects with confirmed RTT diagnoses and MECP2 mutations, aged 8.54 ± 5.30 years. The Rett Syndrome Behavioral Questionnaire revealed a total average score of 25.83 ± 12.34, indicating varying degrees of social impairments. Comprising 25 social-related items, factor analysis yielded four social profiles: “interactive motricity,” “mood change,” “anxiety/agitation,” and “gazing.” Longer sleep onset latency correlated with increased socio-behavioral impairments, particularly in interactive motricity reduction. Conversely, higher rapid eye movement sleep was associated with fewer interactive socio-motor behaviors. No significant differences in social profiles were found concerning the presence of SDB or daytime sleepiness. ConclusionsThe findings suggest four distinct social profiles in RTT individuals, hinting at shared disrupted circuits between sensorimotor functioning and sleep-related neuronal pathways. Despite the absence of differences in SDB or daytime sleepiness, the study highlights the relationship between sleep parameters, such as sleep onset latency and rapid eye movement sleep, and socio-behavioral outcomes in RTT with MECP2 mutations.

Simplifying Multimodal With Single EOG Modality for Automatic Sleep Staging.

Polysomnography (PSG) recordings have been widely used for sleep staging in clinics, containing multiple modality signals (i.e., EEG and EOG). Recently, many studies have combined EEG and EOG modalities for sleep staging, since they are the most and the second most powerful modality for sleep staging among PSG recordings, respectively. However, EEG is complex to collect and sensitive to environment noise or other body activities, imbedding its use in clinical practice. Comparatively, EOG is much more easily to be obtained. In order to make full use of the powerful ability of EEG and the easy collection of EOG, we propose a novel framework to simplify multimodal sleep staging with a single EOG modality. It still performs well with only EOG modality in the absence of the EEG. Specifically, we first model the correlation between EEG and EOG, and then based on the correlation we generate multimodal features with time and frequency guided generators by adopting the idea of generative adversarial learning. We collected a real-world sleep dataset containing 67 recordings and used other four public datasets for evaluation. Compared with other existing sleep staging methods, our framework performs the best when solely using the EOG modality. Moreover, under our framework, EOG provides a comparable performance to EEG.

CareSleepNet: A Hybrid Deep Learning Network for Automatic Sleep Staging.

Sleep staging is essential for sleep assessment and plays an important role in disease diagnosis, which refers to the classification of sleep epochs into different sleep stages. Polysomnography (PSG), consisting of many different physiological signals, e.g. electroencephalogram (EEG) and electrooculogram (EOG), is a gold standard for sleep staging. Although existing studies have achieved high performance on automatic sleep staging from PSG, there are still some limitations: 1) they focus on local features but ignore global features within each sleep epoch, and 2) they ignore cross-modality context relationship between EEG and EOG. In this paper, we propose CareSleepNet, a novel hybrid deep learning network for automatic sleep staging from PSG recordings. Specifically, we first design a multi-scale Convolutional-Transformer Epoch Encoder to encode both local salient wave features and global features within each sleep epoch. Then, we devise a Cross-Modality Context Encoder based on co-attention mechanism to model cross-modality context relationship between different modalities. Next, we use a Transformer-based Sequence Encoder to capture the sequential relationship among sleep epochs. Finally, the learned feature representations are fed into an epoch-level classifier to determine the sleep stages. We collected a private sleep dataset, SSND, and use two public datasets, Sleep-EDF-153 and ISRUC to evaluate the performance of CareSleepNet. The experiment results show that our CareSleepNet achieves the state-of-the-art performance on the three datasets. Moreover, we conduct ablation studies and attention visualizations to prove the effectiveness of each module and to analyze the influence of each modality.