Reproducible, data-driven characterization of sleep based on brain dynamics and transitions from whole-night fMRI.

Understanding the function of sleep requires studying the dynamics of brain activity across whole-night sleep and their transitions. However, current gold standard polysomnography (PSG) has limited spatial resolution to track brain activity. Additionally, previous fMRI studies were too short to capture full sleep stages and their cycling. To study whole-brain dynamics and transitions across whole-night sleep, we used an unsupervised learning approach, the Hidden Markov model (HMM), on two-night, 16 hr fMRI recordings of 12 non-sleep-deprived participants who reached all PSG-based sleep stages. This method identified 21 recurring brain states and their transition probabilities, beyond PSG-defined sleep stages. The HMM trained on one night accurately predicted the other, demonstrating unprecedented reproducibility. We also found functionally relevant subdivisions within rapid eye movement (REM) and within non-REM 2 stages. This study provides new insights into brain dynamics and transitions during sleep, aiding our understanding of sleep disorders that impact sleep transitions.

Temporal and Potential Predictive Relationships between Sleep Spindle Density and Spike-and-Wave Discharges.

Spike-and-wave discharges (SWDs) and sleep spindles are characteristic electroencephalographic (EEG) hallmarks of absence seizures and nonrapid eye movement sleep, respectively. They are commonly generated by the cortico-thalamo-cortical network including the thalamic reticular nucleus (TRN). It has been reported that SWD development is accompanied by a decrease in sleep spindle density in absence seizure patients and animal models. However, whether the decrease in sleep spindle density precedes, coincides with, or follows, the SWD development remains unknown. To clarify this, we exploited Pvalb-tetracycline transactivator (tTA)::tetO-ArchT (PV-ArchT) double-transgenic mouse, which can induce an absence seizure phenotype in a time-controllable manner by expressing ArchT in PV neurons of the TRN. In these mice, EEG recordings demonstrated that a decrease in sleep spindle density occurred 1 week before the onset of typical SWDs, with the expression of ArchT. To confirm such temporal relationship observed in these genetic model mice, we used a gamma-butyrolactone (GBL) pharmacological model of SWDs. Prior to GBL administration, we administered caffeine to wild-type mice for 3 consecutive days to induce a decrease in sleep spindle density. We then administered low-dose GBL, which cannot induce SWDs in normally conditioned mice but led to the occurrence of SWDs in caffeine-conditioned mice. These findings indicate a temporal relationship in which the decrease in sleep spindle density consistently precedes SWD development. Furthermore, the decrease in sleep spindle activity may have a role in facilitating the development of SWDs. Our findings suggest that sleep spindle reductions could serve as early indicators of seizure susceptibility.

Multi-Index Driver Drowsiness Detection Method Based on Driver's Facial Recognition Using Haar Features and Histograms of Oriented Gradients.

It is estimated that 10% to 20% of road accidents are related to fatigue, with accidents caused by drowsiness up to twice as deadly as those caused by other factors. In order to reduce these numbers, strategies such as advertising campaigns, the implementation of driving recorders in vehicles used for road transport of goods and passengers, or the use of drowsiness detection systems in cars have been implemented. Within the scope of the latter area, the technologies used are diverse. They can be based on the measurement of signals such as steering wheel movement, vehicle position on the road, or driver monitoring. Driver monitoring is a technology that has been exploited little so far and can be implemented in many different approaches. This work addresses the evaluation of a multidimensional drowsiness index based on the recording of facial expressions, gaze direction, and head position and studies the feasibility of its implementation in a low-cost electronic package. Specifically, the aim is to determine the driver's state by monitoring their facial expressions, such as the frequency of blinking, yawning, eye-opening, gaze direction, and head position. For this purpose, an algorithm capable of detecting drowsiness has been developed. Two approaches are compared: Facial recognition based on Haar features and facial recognition based on Histograms of Oriented Gradients (HOG). The implementation has been carried out on a Raspberry Pi, a low-cost device that allows the creation of a prototype that can detect drowsiness and interact with peripherals such as cameras or speakers. The results show that the proposed multi-index methodology performs better in detecting drowsiness than algorithms based on one-index detection.

Overnight Sleep Staging Using Chest-Worn Accelerometry.

Overnight sleep staging is an important part of the diagnosis of various sleep disorders. Polysomnography is the gold standard for sleep staging, but less-obtrusive sensing modalities are of emerging interest. Here, we developed and validated an algorithm to perform "proxy" sleep staging using cardiac and respiratory signals derived from a chest-worn accelerometer. We collected data in two sleep centers, using a chest-worn accelerometer in combination with full PSG. A total of 323 participants were analyzed, aged 13-83 years, with BMI 18-47 kg/m2. We derived cardiac and respiratory features from the accelerometer and then applied a previously developed method for automatic cardio-respiratory sleep staging. We compared the estimated sleep stages against those derived from PSG and determined performance. Epoch-by-epoch agreement with four-class scoring (Wake, REM, N1+N2, N3) reached a Cohen's kappa coefficient of agreement of 0.68 and an accuracy of 80.8%. For Wake vs. Sleep classification, an accuracy of 93.3% was obtained, with a sensitivity of 78.7% and a specificity of 96.6%. We showed that cardiorespiratory signals obtained from a chest-worn accelerometer can be used to estimate sleep stages among a population that is diverse in age, BMI, and prevalence of sleep disorders. This opens up the path towards various clinical applications in sleep medicine.

Age-related changes in sleep spindle characteristics in individuals over 75 years of age: a retrospective and comparative study.

BACKGROUND: Sleep and its architecture are affected and changing through the whole lifespan. We know main modifications of the macro-architecture with a shorter sleep, occurring earlier and being more fragmented. We have been studying sleep micro-architecture through its pathological modification in sleep, psychiatric or neurocognitive disorders whereas we are still unable to say if the sleep micro-architecture of an old and very old person is rather normal, under physiological changes, or a concern for a future disorder to appear. We wanted to evaluate age-related changes in sleep spindle characteristics in individuals over 75 years of age compared with younger individuals. METHODS: This was an exploratory study based on retrospective and comparative laboratory-based polysomnography data registered in the normal care routine for people over 75 years of age compared to people aged 65-74 years. We were studying their sleep spindle characteristics (localization, density, frequency, amplitude, and duration) in the N2 and N3 sleep stages. ANOVA and ANCOVA using age, sex and OSA were applied. RESULTS: We included 36 participants aged > 75 years and 57 participants aged between 65 and 74 years. An OSA diagnosis was most common in both groups. Older adults receive more medication to modify their sleep. Spindle localization becomes more central after 75 years of age. Changes in the other sleep spindle characteristics between the N2 and N3 sleep stages and between the slow and fast spindles were conformed to literature data, but age was a relevant modifier only for density and duration. CONCLUSION: We observed the same sleep spindle characteristics in both age groups except for localization. We built our study on a short sample, and participants were not free of all sleep disorders. We could establish normative values through further studies with larger samples of people without any sleep disorders to understand the modifications in normal aging and pathological conditions and to reveal the predictive biomarker function of sleep spindles.

An ensemble method for improving robustness against the electrode contact problems in automated sleep stage scoring.

In-home automated scoring systems are in high demand; however, the current systems are not widely adopted in clinical settings. Problems with electrode contact and restriction on measurable signals often result in unstable and inaccurate scoring for clinical use. To address these issues, we propose a method based on ensemble of small sleep stage scoring models with different input signal sets. By excluding models that employ problematic signals from the voting process, our method can mitigate the effects of electrode contact failure. Comparative experiments demonstrated that our method could reduce the impact of contact problems and improve scoring accuracy for epochs with problematic signals by 8.3 points, while also decreasing the deterioration in scoring accuracy from 7.9 to 0.3 points compared to typical methods. Additionally, we confirmed that assigning different input sets to small models did not diminish the advantages of the ensemble but instead increased its efficacy. The proposed model can improve overall scoring accuracy and minimize the effect of problematic signals simultaneously, making in-home sleep stage scoring systems more suitable for clinical practice.

Oscillatory-Quality of sleep spindles links brain state with sleep regulation and function.

Here, we characterized the dynamics of sleep spindles, focusing on their damping, which we estimated using a metric called oscillatory-Quality (o-Quality), derived by fitting an autoregressive model to electrophysiological signals, recorded from the cortex in mice. The o-Quality of sleep spindles correlates weakly with their amplitude, shows marked laminar differences and regional topography across cortical regions, reflects the level of synchrony within and between cortical networks, is strongly modulated by sleep-wake history, reflects the degree of sensory disconnection, and correlates with the strength of coupling between spindles and slow waves. As most spindle events are highly localized and not detectable with conventional low-density recording approaches, o-Quality thus emerges as a valuable metric that allows us to infer the spread and dynamics of spindle activity across the brain and directly links their spatiotemporal dynamics with local and global regulation of brain states, sleep regulation, and function.

How to quantify sleepiness during an attempt to sleep?

Background. Sleepiness assessment tools were mostly developed for detection of an elevated sleepiness level in the condition of sleep deprivation and several medical conditions. However, sleepiness occurs in various other conditions including the transition from wakefulness to sleep during an everyday attempt to get sleep.Objective. We examined whether objective sleepiness indexes can be implicated in detection of fluctuations in sleepiness level during the polysomnographically-monitored attempt to sleep, i.e. in the absence of self-reports on perceived sleepiness level throughout such an attempt.Approach. The polysomnographic signals were recorded in the afternoon throughout 106 90 min napping attempts of 53 university students (28 females). To calculate two objective sleepiness indexes, the electroencephalographic (EEG) spectra were averaged on 30 s epochs of each record, assigned to one of 5 sleep-wake stages, and scored using either the frequency weighting curve for sleepiness substate of wake state or loadings of each frequency on the 2nd principal component of variation in the EEG spectrum (either sleepiness score or PC2 score, respectively).Main results. We showed that statistically significant fluctuations in these two objective sleepiness indexes during epochs assigned to wake stage can be described in terms of the changes in verbally anchored levels of subjective sleepiness assessed by scoring on the 9-step Karolinska Sleepiness Scale.Significance. The results afford new opportunities to elaborate importance of intermediate substates between wake and sleep states for sleep-wake dynamics in healthy individuals and patients with disturbed sleep.

Cerebral blood flow in sleep: A systematic review and meta-analysis.

Sleep plays an essential role in physiology, allowing the brain and body to restore itself. Despite its critical role, our understanding of the underlying processes in the sleeping human brain is still limited. Sleep comprises several distinct stages with varying depths and temporal compositions. Cerebral blood flow (CBF), which delivers essential nutrients and oxygen to the brain, varies across brain regions throughout these sleep stages, reflecting changes in neuronal function and regulation. This systematic review and meta-analysis assesses global and regional CBF across sleep stages. We included, appraised, and summarized all 38 published sleep studies on CBF in healthy humans that were not or only slightly (<24 h) sleep deprived. Our main findings are that CBF varies with sleep stage and depth, being generally lowest in NREM sleep and highest in REM sleep. These changes appear to stem from sleep stage-specific regional brain activities that serve particular functions, such as alterations in consciousness and emotional processing.

Attention-based CNN-BiLSTM for sleep state classification of spatiotemporal wide-field calcium imaging data.

BACKGROUND: Wide-field calcium imaging (WFCI) with genetically encoded calcium indicators allows for spatiotemporal recordings of neuronal activity in mice. When applied to the study of sleep, WFCI data are manually scored into the sleep states of wakefulness, non-REM (NREM) and REM by use of adjunct EEG and EMG recordings. However, this process is time-consuming, invasive and often suffers from low inter- and intra-rater reliability. Therefore, an automated sleep state classification method that operates on spatiotemporal WFCI data is desired. NEW METHOD: A hybrid network architecture consisting of a convolutional neural network (CNN) to extract spatial features of image frames and a bidirectional long short-term memory network (BiLSTM) with attention mechanism to identify temporal dependencies among different time points was proposed to classify WFCI data into states of wakefulness, NREM and REM sleep. RESULTS: Sleep states were classified with an accuracy of 84 % and Cohen's κ of 0.64. Gradient-weighted class activation maps revealed that the frontal region of the cortex carries more importance when classifying WFCI data into NREM sleep while posterior area contributes most to the identification of wakefulness. The attention scores indicated that the proposed network focuses on short- and long-range temporal dependency in a state-specific manner. COMPARISON WITH EXISTING METHOD: On a held out, repeated 3-hour WFCI recording, the CNN-BiLSTM achieved a κ of 0.67, comparable to a κ of 0.65 corresponding to the human EEG/EMG-based scoring. CONCLUSIONS: The CNN-BiLSTM effectively classifies sleep states from spatiotemporal WFCI data and will enable broader application of WFCI in sleep research.

Common sleep data pipeline for combined data sets.

Over the past few years, sleep research has shown impressive performance of deep neural networks in the area of automatic sleep-staging. Recent studies have demonstrated the necessity of combining multiple data sets to obtain sufficiently generalizing results. However, working with large amounts of sleep data can be challenging, both from a hardware perspective and because of the different preprocessing steps necessary for distinct data sources. Here we review the possible obstacles and present an open-source pipeline for automatic data loading. Our solution includes both a standardized data store as well as a 'data serving' portion which can be used to train neural networks on the standardized data, allowing for different configuration options for different studies and machine learning designs. The pipeline, including implementation, is made public to ensure better and more reproducible sleep research.

Toward Interpretable Sleep Stage Classification Using Cross-Modal Transformers.

Accurate sleep stage classification is significant for sleep health assessment. In recent years, several machine-learning based sleep staging algorithms have been developed, and in particular, deep-learning based algorithms have achieved performance on par with human annotation. Despite improved performance, a limitation of most deep-learning based algorithms is their black-box behavior, which have limited their use in clinical settings. Here, we propose a cross-modal transformer, which is a transformer-based method for sleep stage classification. The proposed cross-modal transformer consists of a cross-modal transformer encoder architecture along with a multi-scale one-dimensional convolutional neural network for automatic representation learning. The performance of our method is on-par with the state-of-the-art methods and eliminates the black-box behavior of deep-learning models by utilizing the interpretability aspect of the attention modules. Furthermore, our method provides considerable reductions in the number of parameters and training time compared to the state-of-the-art methods. Our code is available at https://github.com/Jathurshan0330/Cross-Modal-Transformer. A demo of our work can be found at https://bit.ly/Cross_modal_transformer_demo.

Wireless ear EEG to monitor drowsiness.

Neural wearables can enable life-saving drowsiness and health monitoring for pilots and drivers. While existing in-cabin sensors may provide alerts, wearables can enable monitoring across more environments. Current neural wearables are promising but most require wet-electrodes and bulky electronics. This work showcases in-ear, dry-electrode earpieces used to monitor drowsiness with compact hardware. The employed system integrates additive-manufacturing for dry, user-generic earpieces, existing wireless electronics, and offline classification algorithms. Thirty-five hours of electrophysiological data were recorded across nine subjects performing drowsiness-inducing tasks. Three classifier models were trained with user-specific, leave-one-trial-out, and leave-one-user-out splits. The support-vector-machine classifier achieved an accuracy of 93.2% while evaluating users it has seen before and 93.3% when evaluating a never-before-seen user. These results demonstrate wireless, dry, user-generic earpieces used to classify drowsiness with comparable accuracies to existing state-of-the-art, wet electrode in-ear and scalp systems. Further, this work illustrates the feasibility of population-trained classification in future electrophysiological applications.

Differentiation Across Bipolar Disorder and Major Depressive Disorder by Whole-Night Polysomnographic Findings.

Abstract.Background: There is growing evidence that understanding the role of sleep disturbance in bipolar disorder (BD) and major depressive disorder (MDD) is helpful when studying the high heterogeneity of patients across psychiatric disorders.Objective: The present study was designed to investigate the transdiagnostic role of sleep disturbance measured by polysomnography (PSG) in differentiating from MDD with BD.Methods: A total of 256 patients with MDD and 107 first-episode and never medicated patients with BD using the Diagnostic and Statistical Manual of Mental Disorders, Fourth Edition, criteria were recruited. All patients completed 1 night of PSG recording, and the changes in objective sleep structure parameters were determined by PSG analysis.Results: We showed that patients with MDD had statistically longer rapid eye movement (REM) latency, a higher percentage of stage N2 sleep, and lower percentages of stage N3 sleep and REM sleep than those with BD after controlling for confounding factors (all P < .05). Moreover, using the logistic regression analysis, we identified that REM latency was associated with BD diagnosis among the PSG sleep features. The cutoff value for PSG characteristics to differentiate BD from MDD was 261 in REM latency (sensitivity: 41.4% and specificity: 84.1%).Conclusions: Our findings suggest that PSG-measured sleep abnormalities, such as reduced REM latency, may be a diagnostic differentiating factor between MDD and BD, indicating their roles in identifying homogeneous transdiagnostic subtypes across psychiatric disorders.

The effect of central sleep apnea on sleep architecture in children with obstructive sleep apnea.

OBJECTIVE: This study aimed to investigate how central sleep apnea (CSA) impacts sleep patterns in children with obstructive sleep apnea (OSA). METHODS: Children undergoing polysomnography (PSG) were enrolled and sorted into two groups: those with OSA alone (Group A) and those with both OSA and CSA (CAI <1 nd: children with 10 % CSA or more and less than 50 %, Group B). Statistical analysis was conducted to compare sleep structure and clinical features between Group A and Group B. RESULTS: Group B exhibited significantly higher respiratory events, apnea hypoventilation index, apnea index and oxygen desaturation index (ODI) compared to Group A (p < 0.05). Group B also showed higher total sleep time and arousal index than Group A (P < 0.05). The proportion of time spent in stage N3 was lower in Group B than in Group A (P < 0.05). Moreover, mean heart rate and minimum heart rate were higher in Group B compared to Group A (P < 0.05).Minimum oxygenation levels (including non-rapid eye movement (NREM) stages) were lowe in Group B than in Group A (P < 0.05). Additionally, the prevalence of positional obstructive sleep apnea (P-OSA) was greater in Group B than in Group A (P < 0.05). CONCLUSION: In comparison to those with OSA alone, children with OSA and concurrent CSA exhibited distinct sleep patterns, including reduced N3uration, higher arousal index, longer respiratory events, higher ODI, and lower oxygen saturation, higher heart rate.

GRU-powered sleep stage classification with permutation-based EEG channel selection.

We present a new approach to classifying the sleep stage that incorporates a computationally inexpensive method based on permutations for channel selection and takes advantage of deep learning power, specifically the gated recurrent unit (GRU) model, along with other deep learning methods. By systematically permuting the electroencephalographic (EEG) channels, different combinations of EEG channels are evaluated to identify the most informative subset for the classification of the 5-class sleep stage. For analysis, we used an EEG dataset that was collected at the International Institute for Integrative Sleep Medicine (WPI-IIIS) at the University of Tsukuba in Japan. The results of these explorations provide many new insights such as the (1) drastic decrease in performance when channels are fewer than 3, (2) 3-random channels selected by permutation provide the same or better prediction than the 3 channels recommended by the American Academy of Sleep Medicine (AASM), (3) N1 class suffers the most in prediction accuracy as the channels drop from 128 to 3 random or 3 AASM, and (4) no single channel provides acceptable levels of accuracy in the prediction of 5 classes. The results obtained show the GRU's ability to retain essential temporal information from EEG data, which allows capturing the underlying patterns associated with each sleep stage effectively. Using permutation-based channel selection, we enhance or at least maintain as high model efficiency as when using high-density EEG, incorporating only the most informative EEG channels.

MLS-Net: An Automatic Sleep Stage Classifier Utilizing Multimodal Physiological Signals in Mice.

Over the past decades, feature-based statistical machine learning and deep neural networks have been extensively utilized for automatic sleep stage classification (ASSC). Feature-based approaches offer clear insights into sleep characteristics and require low computational power but often fail to capture the spatial-temporal context of the data. In contrast, deep neural networks can process raw sleep signals directly and deliver superior performance. However, their overfitting, inconsistent accuracy, and computational cost were the primary drawbacks that limited their end-user acceptance. To address these challenges, we developed a novel neural network model, MLS-Net, which integrates the strengths of neural networks and feature extraction for automated sleep staging in mice. MLS-Net leverages temporal and spectral features from multimodal signals, such as EEG, EMG, and eye movements (EMs), as inputs and incorporates a bidirectional Long Short-Term Memory (bi-LSTM) to effectively capture the spatial-temporal nonlinear characteristics inherent in sleep signals. Our studies demonstrate that MLS-Net achieves an overall classification accuracy of 90.4% and REM state precision of 91.1%, sensitivity of 84.7%, and an F1-Score of 87.5% in mice, outperforming other neural network and feature-based algorithms in our multimodal dataset.

Automated explainable wavelet-based sleep scoring system for a population suspected with insomnia, apnea and periodic leg movement.

Sleep is an integral and vital component of human life, contributing significantly to overall health and well-being, but a considerable number of people worldwide experience sleep disorders. Sleep disorder diagnosis heavily depends on accurately classifying sleep stages. Traditionally, this classification has been performed manually by trained sleep technologists that visually inspect polysomnography records. However, in order to mitigate the labor-intensive nature of this process, automated approaches have been developed. These automated methods aim to streamline and facilitate sleep stage classification. This study aims to classify sleep stages in a dataset comprising subjects with insomnia, PLM, and sleep apnea. The dataset consists of PSG recordings from the multi-ethnic study of atherosclerosis (MESA) cohort of the national sleep research resource (NSRR), including 2056 subjects. Among these subjects, 130 have insomnia, 39 suffer from PLM, 156 have sleep apnea, and the remaining 1731 are classified as good sleepers. This study proposes an automated computerized technique to classify sleep stages, developing a machine-learning model with explainable artificial intelligence (XAI) capabilities using wavelet-based Hjorth parameters. An optimal biorthogonal wavelet filter bank (BOWFB) has been employed to extract subbands (SBs) from 30 seconds of electroencephalogram (EEG) epochs. Three EEG channels, namely: Fz_Cz, Cz_Oz, and C4_M1, are employed to yield an optimum outcome. The Hjorth parameters extracted from SBs were then fed to different machine learning algorithms. To gain an understanding of the model, in this study, we used SHAP (Shapley Additive explanations) method. For subjects suffering from the aforementioned diseases, the model utilized features derived from all channels and employed an ensembled bagged trees (EnBT) classifier. The highest accuracy of 86.8%, 87.3%, 85.0%, 84.5%, and 83.8% is obtained for the insomniac, PLM, apniac, good sleepers and complete datasets, respectively. Using these techniques and datasets, the study aims to enhance sleep stage classification accuracy and improve understanding of sleep disorders such as insomnia, PLM, and sleep apnea.

Efficient Sleep Stage Identification Using Piecewise Linear EEG Signal Reduction: A Novel Algorithm for Sleep Disorder Diagnosis.

Sleep is a vital physiological process for human health, and accurately detecting various sleep states is crucial for diagnosing sleep disorders. This study presents a novel algorithm for identifying sleep stages using EEG signals, which is more efficient and accurate than the state-of-the-art methods. The key innovation lies in employing a piecewise linear data reduction technique called the Halfwave method in the time domain. This method simplifies EEG signals into a piecewise linear form with reduced complexity while preserving sleep stage characteristics. Then, a features vector with six statistical features is built using parameters obtained from the reduced piecewise linear function. We used the MIT-BIH Polysomnographic Database to test our proposed method, which includes more than 80 h of long data from different biomedical signals with six main sleep classes. We used different classifiers and found that the K-Nearest Neighbor classifier performs better in our proposed method. According to experimental findings, the average sensitivity, specificity, and accuracy of the proposed algorithm on the Polysomnographic Database considering eight records is estimated as 94.82%, 96.65%, and 95.73%, respectively. Furthermore, the algorithm shows promise in its computational efficiency, making it suitable for real-time applications such as sleep monitoring devices. Its robust performance across various sleep classes suggests its potential for widespread clinical adoption, making significant advances in the knowledge, detection, and management of sleep problems.