Exploring Cepstral Coefficient Based Sleep Stage Scoring Method for Single-Channel EEG Signal Using Machine Learning Technique

The aim of the study was to inspect the acoustic properties and sleep characteristics of a preapneic snoring sound. The feasibility of forecasting upcoming respiratory events by snoring sound was also investigated. Participants with habitual snoring or a heavy breathing sound during sleep were recruited consecutively. Polysomnography was conducted, and snoring-related breathing sound was recorded simultaneously. Acoustic features and sleep features were extracted from 30-second samples, and a machine learning algorithm was used to establish 2 prediction models. A total of 74 eligible participants were included. Model 1, tested by 5-fold cross-validation, achieved an accuracy of 0.92 and an area under the curve of 0.94 for respiratory event prediction. Model 2, with acoustic features and sleep information tested by Leave-One-Out cross-validation, had an accuracy of 0.78 and an area under the curve of 0.80. Sleep position was found to be the most important among all sleep features contributing to the performance of the 2 models. Preapneic sound presented unique acoustic characteristics, and snoring-related breathing sound could be deployed as a real-time apneic event predictor. The models, combined with sleep information, serve as a promising tool for an early warning system to forecast apneic events. Wang B, Yi X, Gao J, etal. Real-time prediction of upcoming respiratory events via machine learning using snoring sound signal. J Clin Sleep Med. 2021;17(9):1777-1784.

Background: This study aims to explore the circadian rhythm of interictal epileptiform discharges (IEDs) and changes of spindles in patients with temporal lobe epilepsy (TLE). Methods: Subjects were divided into two groups: research group (patients diagnosed with TLE, n=50) and control group (n=30). The whole-night natural sleep of all subjects was monitored, analysis and statistics were performed on IED, and the number, amplitude and the average duration of spindles were compared between these two groups. Results: (1) In TLE patients, the number of IED was larger in non-rapid eye movement (NREM) stages 1+2 and NREM stages 3+4 than in the waking stage and rapid eye movement (REM) stage, and the differences were statistically significant (P<0.05). (2) TLE patients had bilateral asymmetric sleep spindles, and their amplitude was lower in the affected side than in the unaffected side. Furthermore, the number, amplitude and mean duration of sleep spindles in the affected side in NREM stage 2 was significantly reduced compared with that in the control group (P<0.05). Conclusions: (1) TLE patients have the highest frequency of IED in slow wave sleep, followed by NREM stages 1+2, waking and REM stages. Slow wave sleep easily induces IED. (2) The number, amplitude and mean duration of sleep spindles in the affected side in NREM stage 2 were significantly reduced, compared with that in the control group. This suggests that changes in spindles have a lateralization value.

The goal of the present study was to investigate arousal thresholds (ATs) in tonic and phasic episodes of rapid eye movement (REM) sleep, and to compare the frequency spectrum of these sub-states of REM to non-REM (NREM) stages of sleep. We found the two REM stages to differ with regard to behavioural responses to external acoustic stimuli. The AT in tonic REM was indifferent from that in sleep stage 2, and ATs in phasic REM were similar to those in slow-wave sleep (stage 4). NREM and REM stages of similar behavioural thresholds were distinctly different with regard to their frequency pattern. These data provide further evidence that REM sleep should not be regarded a uniform state. Regarding electroencephalogram frequency spectra, we found that the two REM stages were more similar to each other than to NREM stages with similar responsivity. Ocular activity such as ponto-geniculo-occipital-like waves and microsaccades are discussed as likely modulators of behavioural responsiveness and cortical processing of auditory information in the two REM sub-states.

Chapter 2 - Normal Human Sleep: An Overview

Sleep stage classification plays a pivotal role in effective diagnosis and treatment of sleep related disorders. Traditionally, sleep scoring is done manually by trained sleep scorers. The analysis of electroencephalogram (EEG) signals recorded during sleep by clinicians is tedious, time-consuming and prone to human errors. Therefore, it is clinically important to score sleep stages using machine learning techniques to get accurate diagnosis. Several studies have been proposed for automated detection of sleep stages. However, these studies have employed only healthy normal subjects (good sleepers). The proposed study focuses on the automated sleep-stage scoring of subjects suffering from seven different kind of sleep disorders such as insomnia, bruxism, narcolepsy, nocturnal frontal lobe epilepsy (NFLE), periodic leg movement (PLM), rapid eye movement (REM) behavioural disorder and sleep-disordered breathing as well as normal subjects. The open source physionet’s cyclic alternating pattern (CAP) sleep database is used for this study. The EEG epochs are decomposed into sub-bands using a new class of optimized wavelet filters. Two EEG channels, namely F4-C4 and C4-A1, combined are used for this work as they can provide more insights into the changes in EEG signals during sleep. The norm features are computed from six sub-bands coefficients of optimal wavelet filter bank and fed to various supervised machine learning classifiers. We have obtained the highest classification performance using an ensemble of bagged tree (EBT) classifier with 10-fold cross validation. The CAP database comprising of 80 subjects is divided into ten different subsets and then ten different sleep-stage scoring tasks are performed. Since, the CAP database is unbalanced with different duration of sleep stages, the balanced dataset also has been created using over-sampling and under-sampling techniques. The highest average accuracy of 85.3% and Cohen’s Kappa coefficient of 0.786 and accuracy of 92.8% and Cohen’s Kappa coefficient of 0.915 are obtained for unbalanced and balanced databases, respectively. The proposed method can reliably classify the sleep stages using single or dual channel EEG epochs of 30 s duration instead of using multimodal polysomnography (PSG) which are generally used for sleep-stage scoring. Our developed automated system is ready to be tested with more sleep EEG data and can be employed in various sleep laboratories to evaluate the quality of sleep in various sleep disorder patients and normal subjects.

Preoptic/anterior hypothalamic neurons: thermosensitivity in wakefulness and non rapid eye movement sleep

What is the central question of this study? A transcranial magnetic stimulation (TMS)-induced twitch applied on isolated single breaths over the motor cortex somatotopic representation of the tongue briefly recruits submental muscles and improves airflow dynamics of flow-limited respiratory cycles without arousing sleep apnoea patients. However, the mechanical impact of the TMS-induced twitch applied during consecutive breathing cycles on airflow dynamics remains unknown. What is the main finding and what is its importance? Our results show that application of TMS with the stimulator output set at the sleep submental motor threshold intensity on consecutive respiratory cycles increases inspiratory flow and reduces the turbulent airflow component. These results indicate an improvement of airflow pattern after two single consecutive TMS-induced twitches without arousing sleep apnoea patients. Transcranial magnetic stimulation (TMS)-induced twitches applied on isolated breaths briefly recruit upper airway dilator muscles and improve airflow and inspiratory volume without arousing apnoeic patients from sleep, but the effects of applying such twitches consecutively on airflow dynamics is unknown. The objective of this study was to quantify the effects of five consecutive TMS-induced twitches applied on sleep-induced obstructive hypopnoeic breaths in 10 obstructive sleep apnoea patients. Submental muscle motor threshold (SUBMT) and motor-evoked potential were measured during wakefulness and sleep. The TMS-induced twitches were applied during stable non-rapid eye movement (NREM) sleep, at the beginning of inspiration of consecutive flow-limited respiratory cycles, with the stimulator output set at sleep SUBMT. Maximal inspiratory flow, inspiratory volume, inspiratory time, shifts of electroencephalogram frequency and pulse rate variability were assessed. During sleep, SUBMT increased (wakefulness, 25.3 ± 4.9%; NREM sleep, 27.0 ± 6.2%; P = 0.02). During each series of stimulations there was a rise in maximal inspiratory flow (from 306.7 ± 123.2 to 359.8 ± 154.1 ml s(-1); P = 0.0002) and in inspiratory volume (from 346.1 ± 128.1 to 414.9 ± 171.2 ml; P = 0.02) without differences in thoraco-abdominal efforts and inspiratory time. These responses were observed in the absence of arousals and ceased immediately after TMS interruption. Transcranial magnetic stimulation-induced cortical and/or autonomic arousal was observed in 30.2% of all series of stimulation. Consecutive twitch TMS of submental muscles may lead to arousals in a minority of patients but can be applied on consecutive respiratory cycles during sleep and can significantly improve maximal inspiratory flow and inspiratory volume of flow-limited cycles.

Rationale: Sleep-disordered breathing (SDB) occurring primarily during rapid eye movement (REM) sleep is a common clinical problem. The natural history of REM-related SDB and the associated cardiovascular sequelae of disease progression remain to be determined.Objectives: The objective of the current study was to describe the natural history of REM-related SDB, ascertain predictors of progression, and determine whether the evolution of REM-related SDB into non-REM (NREM) sleep is associated with incident cardiovascular events.Methods: Participants from the Sleep Heart Health Study with a baseline NREM apnea-hypopnea index (NREM-AHI) of <5 events/h and data from a follow-up sleep study along with information on incident cardiovascular disease were included in the study. Bivariate logistic regression was used to jointly model the predictors of disease progression based on the presence or absence of SDB during NREM and REM sleep using a cut-point of 5 events/h. Explanatory variables such as age, race, body mass index (BMI), change in BMI, and baseline REM-AHI were considered. Proportional hazards regression was then used to establish whether the development of SDB during NREM sleep was associated with incident cardiovascular disease.Results: The majority of the 1,908 participants included in the study did not develop SDB during NREM sleep. The likelihood of progression of SDB into NREM sleep did increase with higher baseline REM-AHI. BMI and an increase in BMI predicted progression of SDB in both NREM and REM sleep in men but not in women. There was a strong interdependence between developing a NREM-AHI of ≥5 events/h and worsening REM-AHI at follow-up with odds ratios of 6.01 and 4.47, in women and men, respectively. Moreover, the relative risk for incident cardiovascular events among those who developed a NREM-AHI of ≥5 events/h at the follow-up visit was elevated only in women with REM-related SDB at baseline.Conclusions: SDB during REM sleep is a relatively stable condition and does not progress in the majority of individuals. Progression of SDB into NREM sleep is associated with sex, weight, and age. SDB during REM and NREM sleep tends to develop concurrently. Finally, the development of SDB during NREM sleep is associated with incident cardiovascular events, but only in women with REM-related SDB at baseline.

Cardiovascular Disease and Sleep Disordered Breathing: Are Children Vulnerable?

Background: Sleep stage scoring, which is an essential step in the quantitative analysis of sleep monitoring, relies on human experts and is therefore subjective and time-consuming; thus, an easy and accurate method is needed for the automatic scoring of sleep stages. Methods: In this study, we constructed a deep convolutional recurrent (DCR) model for the automatic scoring of sleep stages based on a raw single-lead electrocardiogram (ECG). The DCR model uses deep convolutional and recurrent neural networks to apply the complex and cyclic rhythms of human sleep. It consists of three convolutional and two recurrent layers and is optimized by dropout and batch normalization. The constructed DCR model was evaluated using multiclass classification, including five-class sleep stages (wake, N1, N2, N3, and rapid eye movement (REM)) and three-class sleep stages (wake, non-REM (NREM), and REM), using a raw single-lead ECG signal. The single-lead ECG signal was collected from 112 subjects in two groups: control (52 subjects) and sleep apnea (60 subjects). The single-lead ECG signal was preprocessed, segmented at a duration of 30 s, and divided into a training set of 89 subjects and test set of 23 subjects. Results: We achieved an overall accuracy of 74.2% for five classes and 86.4% for three classes. Conclusions: These results show the DCR model’s superior performance over those in the previous studies, highlighting that the model can be an alternative tool for sleep monitoring and sleep screening.

Birds exhibit two types of sleep that are in many respects similar to mammalian rapid eye movement (REM) and non-REM (NREM) sleep. As in mammals, several aspects of avian sleep can occur in a local manner within the brain. Electrophysiological evidence of NREM sleep occurring more deeply in one hemisphere, or only in one hemisphere – the latter being a phenomenon most pronounced in dolphins – was actually first described in birds. Such asymmetric or unihemispheric NREM sleep occurs with one eye open, enabling birds to visually monitor their environment for predators. Frigatebirds primarily engage in this form of sleep in flight, perhaps to avoid collisions with other birds. In addition to interhemispheric differences in NREM sleep intensity, the intensity of NREM sleep is homeostatically regulated in a local, use-depended manner within each hemisphere. Furthermore, the intensity and temporo-spatial distribution of NREM sleep-related slow waves varies across layers of the avian hyperpallium – a primary visual area – with the slow waves occurring first in, and propagating through and outward from, thalamic input layers. Slow waves also have the greatest amplitude in these layers. Although most research has focused on NREM sleep, there are also local aspects to avian REM sleep. REM sleep-related reductions in skeletal muscle tone appear largely restricted to muscles involved in maintaining head posture. Other local aspects of sleep manifest as a mixture of features of NREM and REM sleep occurring simultaneously in different parts of the neuroaxis. Like monotreme mammals, ostriches often exhibit brainstem-mediated features of REM sleep (muscle atonia and REMs) while the hyperpallium shows EEG slow waves typical of NREM sleep. Finally, although mice show slow waves in thalamic input layers of primary sensory cortices during REM sleep, this is not the case in the hyperpallium of pigeons, suggesting that this phenomenon is not a universal feature of REM sleep. Collectively, the local aspects of sleep described in birds and mammals reveal that wakefulness, NREM sleep, and REM sleep are not always discrete states.

IntroductionDuring sleep periods, most mammals alternate multiple times between rapid-eye-movement (REM) sleep and non-REM (NREM) sleep. A common theory proposes that these transitions are governed by an “hourglass-like” homeostatic need to enter REM sleep that accumulates during the inter-REM interval and partially discharges during REM sleep. However, markers or mechanisms for REM homeostatic pressure remain undetermined. Recently, an analysis of sleep in mice demonstrated that the cumulative distribution function (CDF) of the amount of NREM sleep between REM bouts correlates with REM bout duration, suggesting that time in NREM sleep influences REM sleep need. Here, we build on those results and construct a predictive measure for the propensity to enter REM sleep as a function of time in NREM sleep since the previous REM episode.MethodsThe REM propensity measure is precisely defined as the probability to enter REM sleep before the accumulation of an additional pre-specified amount of NREM sleep.ResultsAnalyzing spontaneous sleep in mice, we find that, as NREM sleep accumulates between REM bouts, the REM propensity exhibits a peak value and then decays to zero with further NREM accumulation. We show that the REM propensity at REM onset predicts features of the subsequent REM bout under certain conditions. Specifically, during the light phase and for REM propensities occurring before the peak in propensity, the REM propensity at REM onset is correlated with REM bout duration, and with the probability of the occurrence of a short REM cycle called a sequential REM cycle. Further, we also find that proportionally more REM sleep occurs during sequential REM cycles, supporting a correlation between high values of our REM propensity measure and high REM sleep need.DiscussionThese results support the theory that a homeostatic need to enter REM sleep accrues during NREM sleep, but only for a limited range of NREM sleep accumulation.

Ginseng Extract Regulates the Alterations of Sleep Architecture and EEG Power Spectra in Restraint Stressed Rats

Introduction Although obstructive sleep apnea (OSA) is associated with abnormal glycometabolism, current evidence on the association between hyperglycemia and abnormal sleep structure is still limited among patients with OSA. We sought to evaluate whether hyperglycemia was associated with abnormal sleep architecture. Methods A total of 452 patients with OSA, who were free of previously diagnosed diabetes mellitus, were consecutively recruited. All participants underwent overnight polysomnography and 75-g oral glucose tolerance test. Patients were divided into normal glucose tolerance (NGT) and hyperglycemia (i.e. prediabetes and type 2 diabetes) according to the ADA criteria. The association between hyperglycemia and sleep architecture was examined using logistic regression model. Results Of 452 patients, 283 (63%) had hyperglycemia (age 43.9 ± 11.1) and 169 (37%) had NGT (age 40.1 ± 11.1). Compared to the NGT group, the hyperglycemia group had older age (P &amp;lt; 0.05), higher body mass index (27.5 ± 4.1 vs. 26.33 ± 4.4; P &amp;lt; 0.05) and higher AHI (apnea-hypopnea index) (57.41 ± 28.6 vs. 48.3 ± 28.2; P &amp;lt; 0.05). There were no differences in total sleep time, the percentage of time spent in rapid eye movement (REM) or non-rapid eye movement (NREM) sleep between groups. However, patients with hyperglycemia had more microarousal events, especially during the NREM sleep (214 (range 19-662) events/h vs. 148 (range 37-600) events/h; P &amp;lt; 0.05). In addition, sleep variables related to oxygen saturation measures, such as the percentage of time spent with oxygen saturation ≤80%, were significantly greater during the REM sleep in patients with hyperglycemia (1.4 (total range 0-91.1) % vs. 1.1(0-78.6) %; P &amp;lt; 0.05). After adjusting potential confounders, logistic regression analyses showed that the presence of hyperglycemia was independently associated with the number of microarousals in NREM sleep (OR = 1.01, 95% CI = 1.00-1.02, P = 0.02). Conclusion Hyperglycemia is independently associated with abnormal sleep architecture among patients with OSA. Patients with hyperglycemia have significantly increased sleep fragmentation in NREM sleep and significantly increased hypoxia in REM sleep. Support This work was supported by the National Natural Science Foundation of China (81700087).

Do neurotoxic lesions in rostral medullary nuclei induce/accentuate hypoventilation during NREM sleep?