An automatic EEG-based sleep staging system with introducing NAoSP and NAoGP as new metrics for sleep staging systems

Different biological signals are recorded in sleep labs during sleep for the diagnosis and treatment of human sleep problems. Classification of sleep stages with electroencephalography (EEG) is preferred to other biological signals due to its advantages such as providing clinical information, cost-effectiveness, comfort, and ease of use. The evaluation of EEG signals taken during sleep by clinicians is a tiring, time-consuming, and error-prone method. Therefore, it is clinically mandatory to determine sleep stages by using software-supported systems. Like all classification problems, the accuracy rate is used to compare the performance of studies in this domain, but this metric can be accurate when the number of observations is equal in classes. However, since there is not an equal number of observations in sleep stages, this metric is insufficient in the evaluation of such systems. For this purpose, in recent years, Cohen’s kappa coefficient and even the sensitivity of NREM1 have been used for comparing the performance of these systems. Still, none of them examine the system from all dimensions. Therefore, in this study, two new metrics based on the polygon area metric, called the normalized area of sensitivity polygon and normalized area of the general polygon, are proposed for the performance evaluation of sleep staging systems. In addition, a new sleep staging system is introduced using the applications offered by the MATLAB program. The existing systems discussed in the literature were examined with the proposed metrics, and the best systems were compared with the proposed sleep staging system. According to the results, the proposed system excels in comparison with the most advanced machine learning methods. The single-channel method introduced based on the proposed metrics can be used for robust and reliable sleep stage classification from all dimensions required for real-time applications.Electronic supplementary materialThe online version of this article (10.1007/s11571-020-09641-2) contains supplementary material, which is available to authorized users.     

Sleep classification in infants based on artificial neural networks.

The study reports on the possibility of classifying sleep stages in infants using an artificial neural network. The polygraphic data from 4 babies aged 6 weeks, 6 months and 1 year recorded over 8 hours were available for classification. From each baby 22 signals were recorded, digitized and stored on an optical disc. Subsets of these signals and additional calculated parameters were used to obtain data vectors, each of which represents an interval of 30 sec. For classification, two types of neural networks were used, a Multilayer Perceptron and a Learning Vector Quantizer. The teaching input for both networks was provided by a human expert. For the 6 sleep classes in babies aged 6 months, a 65% to 80% rate of correct classification (4 babies) was obtained for the testing data not previously seen.     

Feature selection for sleep/wake stages classification using data driven methods

This paper focuses on the problem of selecting relevant features extracted from human polysomnographic (PSG) signals to perform accurate sleep/wake stages classification. Extraction of various features from the electroencephalogram (EEG), the electro-oculogram (EOG) and the electromyogram (EMG) processed in the frequency and time domains was achieved using a database of 47 night sleep recordings obtained from healthy adults in laboratory settings. Multiple iterative feature selection and supervised classification methods were applied together with a systematic statistical assessment of the classification performances. Our results show that using a simple set of features such as relative EEG powers in five frequency bands yields an agreement of 71% with the whole database classification of two human experts. These performances are within the range of existing classification systems. The addition of features extracted from the EOG and EMG signals makes it possible to reach about 80% of agreement with the expert classification. The most significant improvement on classification accuracy is obtained on NREM sleep stage I, a stage of transition between sleep and wakefulness.     

Probabilistic Identification of Cerebellar Cortical Neurones across Species

Despite our fine-grain anatomical knowledge of the cerebellar cortex, electrophysiological studies of circuit information processing over the last fifty years have been hampered by the difficulty of reliably assigning signals to identified cell types. We approached this problem by assessing the spontaneous activity signatures of identified cerebellar cortical neurones. A range of statistics describing firing frequency and irregularity were then used, individually and in combination, to build Gaussian Process Classifiers (GPC) leading to a probabilistic classification of each neurone type and the computation of equi-probable decision boundaries between cell classes. Firing frequency statistics were useful for separating Purkinje cells from granular layer units, whilst firing irregularity measures proved most useful for distinguishing cells within granular layer cell classes. Considered as single statistics, we achieved classification accuracies of 72.5% and 92.7% for granular layer and molecular layer units respectively. Combining statistics to form twin-variate GPC models substantially improved classification accuracies with the combination of mean spike frequency and log-interval entropy offering classification accuracies of 92.7% and 99.2% for our molecular and granular layer models, respectively. A cross-species comparison was performed, using data drawn from anaesthetised mice and decerebrate cats, where our models offered 80% and 100% classification accuracy. We then used our models to assess non-identified data from awake monkeys and rabbits in order to highlight subsets of neurones with the greatest degree of similarity to identified cell classes. In this way, our GPC-based approach for tentatively identifying neurones from their spontaneous activity signatures, in the absence of an established ground-truth, nonetheless affords the experimenter a statistically robust means of grouping cells with properties matching known cell classes. Our approach therefore may have broad application to a variety of future cerebellar cortical investigations, particularly in awake animals where opportunities for definitive cell identification are limited.     

Genioglossus and breathing responses to airway occlusion: effect of sleep and route of occlusion

We examined the effect of sleep state on the response of genioglossus muscle (EMGgg) activity to total airway occlusion applied at 1) nasal (N) airway [and thus exposing the upper airway (UAW) to pressure changes] and 2) tracheal (T) airway (thus excluding UAW from pressure changes). A total of 233 tests were performed during wakefulness (W), 98 tests in slow-wave sleep (SWS), and 72 tests in rapid-eye-movement (REM) sleep. Prolongation of inspiratory time (TI) of the first occluded effort occurred in all tests irrespective of behavioral state, with the greatest increase seen in awake N tests. Nasal tests augmented EMGgg activity in the first occluded breath and produced a linear increase in EMGgg during occlusion. The EMGgg activity at any given time during nasal occlusion in SWS was less than that recorded during W tests. There was a marked reduction in EMGgg response to N occlusion during REM sleep. The EMGgg activity during awake T tests was significantly less than that of N tests at any given time during occlusion. There was no relationship between the level of EMGgg activity and asphyxia in T tests performed during SWS and REM sleep. Nasal tests decreased the force generated by the inspiratory pump muscles and the central drive to breathing compared with T tests. These results confirm the important role of the UAW in regulating breathing pattern and indicate that both immediate and progressive load-compensating responses during nasal occlusion are influenced by information arising from the UAW.     

Upper airway resistance and geniohyoid muscle activity in normal men during wakefulness and sleep

Sleep-related reduction in geniohyoid muscular support may lead to increased airway resistance in normal subjects. To test this hypothesis, we studied seven normal men throughout a single night of sleep. We recorded inspiratory supraglottic airway resistance, geniohyoid muscle electromyographic (EMGgh) activity, sleep staging, and ventilatory parameters in these subjects during supine nasal breathing. Mean inspiratory upper airway resistance was significantly (P less than 0.01) increased in these subjects during all stages of sleep compared with wakefulness, reaching highest levels during non-rapid-eye-movement (NREM) sleep [awake 2.5 +/- 0.6 (SE) cmH2O.l-1.s, stage 2 NREM sleep 24.1 +/- 11.1, stage 3/4 NREM sleep 30.2 +/- 12.3, rapid-eye-movement (REM) sleep 13.0 +/- 6.7]. Breath-by-breath linear correlation analyses of upper airway resistance and time-averaged EMGgh amplitude demonstrated a significant (P less than 0.05) negative correlation (r = -0.44 to -0.55) between these parameters in five of seven subjects when data from all states (wakefulness and sleep) were combined. However, we found no clear relationship between normalized upper airway resistance and EMGgh activity during individual states (wakefulness, stage 2 NREM sleep, stage 3/4 NREM sleep, and REM sleep) when data from all subjects were combined. The timing of EMGgh onset relative to the onset of inspiratory airflow did not change significantly during wakefulness, NREM sleep, and REM sleep. Inspiratory augmentation of geniohyoid activity generally preceded the start of inspiratory airflow. The time from onset of inspiratory airflow to peak inspiratory EMGgh activity was significantly increased during sleep compared with wakefulness (awake 0.81 +/- 0.04 s, NREM sleep 1.01 +/- 0.04, REM sleep 1.04 +/- 0.05; P less than 0.05). These data indicate that sleep-related changes in geniohyoid muscle activity may influence upper airway resistance in some subjects. However, the relationship between geniohyoid muscle activity and upper airway resistance was complex and varied among subjects, suggesting that other factors must also be considered to explain sleep influences on upper airway patency.     

Coordination of respiratory muscles assessed by means of nonlinear forecasting of demodulated myographic signals

Pulmonary diseases such as obstructive sleep apnea syndrome (OSAS) affect function of respiratory muscles. Individuals with OSAS suffer intermittent collapse of the upper airways during sleep due to unbalanced forces generated by the contraction of the diaphragm and upper airway dilator muscles.Respiratory rhythm and pattern generation can be described via nonlinear or coupled oscillators; therefore, the resulting activation of different respiratory muscles may be related to complex nonlinear interactions. The aims of this work were: to evaluate locally linear models for fitting and prediction of demodulated myographic signals from respiratory muscles; and to analyze quantitatively the influence of a pulmonary disease on this nonlinear forecasting related to low and moderate levels of respiratory effort.Electromyographic and mechanomyographic signals from three respiratory muscles (genioglossus, sternomastoid and diaphragm) were recorded in OSAS patients and controls while awake during an increased respiratory effort.Variables related to auto and cross prediction between muscles were calculated from the r² coefficient and the estimation of residuals, as functions of prediction horizon. In general, prediction improved linearly with higher levels of effort.A better prediction between muscle activities was obtained in OSAS patients when using genioglossus as the predictor signal. The prediction was significant for more than two respiratory cycles in OSAS patients compared to only a half cycle in controls. It could be concluded that nonlinear forecasting applied to genioglossus coupling with other muscles provides a promising assessment to monitor pulmonary diseases.     

Evaluation of two minimally invasive techniques for electroencephalogram recording in wild or freely behaving animals

Insight into the function of sleep may be gained by studying animals in the ecological context in which sleep evolved. Until recently, technological constraints prevented electroencephalogram (EEG) studies of animals sleeping in the wild. However, the recent development of a small recorder (Neurologger 2) that animals can carry on their head permitted the first recordings of sleep in nature. To facilitate sleep studies in the field and to improve the welfare of experimental animals, herein, we test the feasibility of using minimally invasive surface and subcutaneous electrodes to record the EEG in barn owls. The EEG and behaviour of four adult owls in captivity and of four chicks in a nest box in the field were recorded. We scored a 24-h period for each adult bird for wakefulness, slow-wave sleep (SWS), and rapid-eye movement (REM) sleep using 4 s epochs. Although the quality and stability of the EEG signals recorded via subcutaneous electrodes were higher when compared to surface electrodes, the owls’ state was readily identifiable using either electrode type. On average, the four adult owls spent 13.28 h awake, 9.64 h in SWS, and 1.05 h in REM sleep. We demonstrate that minimally invasive methods can be used to measure EEG-defined wakefulness, SWS, and REM sleep in owls and probably other animals.     

Automatic analysis of sleep using two parameters based on principal component analysis of electroencephalography spectral data

A computer program for the analysis of a sleep electroencephalogram (EEG) is presented. The method relies on two steps. First, a spectral analysis is performed for signals recorded from one or more electrode locations. Then, two EEG parameters are obtained by storing the spectral activity in a multidimensional space, whose dimension is reduced using principal component analysis (PCA) techniques. The main advantage of these parameters is in describing the process of sleep on a continuous scale as a function of time. Validation of the method was performed with the data collected from 16 subjects (8 young volunteers and 8 elderly insomniacs). Results snowed that the parameters correlate highly with the hypnograms established by conventional visual scoring. This signal parametrisation, however, offers more information regarding the time course of sleep, since small variations within individual sleep stages as well as smooth transitions between stages are assessed. Finally, the concurrent use of both parameters provides an original way of considering sleep as a dynamic process evolving cyclically in a single plane.     

Analysis and automatic identification of sleep stages using higher order spectra

Electroencephalogram (EEG) signals are widely used to study the activity of the brain, such as to determine sleep stages. These EEG signals are nonlinear and non-stationary in nature. It is difficult to perform sleep staging by visual interpretation and linear techniques. Thus, we use a nonlinear technique, higher order spectra (HOS), to extract hidden information in the sleep EEG signal. In this study, unique bispectrum and bicoherence plots for various sleep stages were proposed. These can be used as visual aid for various diagnostics application. A number of HOS based features were extracted from these plots during the various sleep stages (Wakefulness, Rapid Eye Movement (REM), Stage 1-4 Non-REM) and they were found to be statistically significant with p-value lower than 0.001 using ANOVA test. These features were fed to a Gaussian mixture model (GMM) classifier for automatic identification. Our results indicate that the proposed system is able to identify sleep stages with an accuracy of 88.7%.     

Sleep Cystometrography: A Preliminary Study of Bladder Function During Sleep

Bladder function during sleep was studied by the use of a cystometer which recorded detrusor contractions and intravesical pressure as urine accumulated in the bladder during diuresis. The cystometrographic tracing was obtained while the patient was awake. A detrusor contraction can occur during sleep. Results of such studies on five patients are presented, with photographs of representative cystometrographic tracings.The general pattern of the cystometrogram during sleep was found to be different from that obtained while the patient was awake. A detrusor contraction can occur during sleep and may subsequently: (a) subside without awakening the patient; (b) be associated with the involuntary escape of urine or flatus; or (c) cause the patient to awaken. It is suggested that detrusor contractions rather than increases in urinary volume are responsible for the individual''s awakening at night to urinate.In the light of these observations, further study of patients with enuresis and those with non-obstructive nocturia is required.     

Sleep stages classification based on heart rate variability and random forest

An alternative technique for sleep stages classification based on heart rate variability (HRV) was presented in this paper. The simple subject specific scheme and a more practical subject independent scheme were designed to classify wake, rapid eye movement (REM) sleep and non-REM (NREM) sleep. 41 HRV features extracted from RR sequence of 45 healthy subjects were trained and tested through random forest (RF) method. Among the features, 25 were newly proposed or applied to sleep study for the first time. For the subject independent classifier, all features were normalized with our developed fractile values based method. Besides, the importance of each feature for sleep staging was also assessed by RF and the appropriate number of features was explored. For the subject specific classifier, a mean accuracy of 88.67% with Cohen's kappa statistic κ of 0.7393 was achieved. While the accuracy and κ dropped to 72.58% and 0.4627, respectively when the subject independent classifier was considered. Some new proposed HRV features even performed more effectively than the conventional ones. The proposed method could be used as an alternative or aiding technique for rough and convenient sleep stages classification.     

The influence of internal time, time awake, and sleep duration on cognitive performance in shiftworkers

To date, studies investigating the consequences of shiftwork have predominantly focused on external (local) time. Here, we report the daily variation in cognitive performance in rotating shiftworkers under real-life conditions using the psychomotor vigilance test (PVT) and show that this function depends both on external and internal (biological) time. In addition to this high sensitivity of PVT performance to time-of-day, it has also been extensively applied in sleep deprivation protocols. We, therefore, also investigated the impact of shift-specific sleep duration and time awake on performance. In two separate field studies, 44 young workers (17 females, 27 males; age range 20-36 yrs) performed a PVT test every 2?h during each shift. We assessed chronotype by the MCTQ(Shift) (Munich ChronoType Questionnaire for shiftworkers). Daily sleep logs over the 4-wk study period allowed for the extraction of shift-specific sleep duration and time awake in a given shift, as well as average sleep duration ("sleep need"). Median reaction times (RTs) significantly varied across shifts, depending on both Local Time and Internal Time. Variability of reaction times around the 24?h mean (≈ ±5%) was best explained by a regression model comprising both factors, Local Time and Internal Time (p < .001). Short (15th percentile; RT(15%)) and long (85th percentile; RT(85%)) reaction times were differentially affected by Internal Time and Local Time. During night shifts, only median RT and RT(85%) were impaired by the duration of time workers had been awake (p?相似文献   

Electroencephalogram bands modulated by vigilance states in an anuran species: a factor analytic approach

Dramatic changes in neocortical electroencephalogram (EEG) rhythms are associated with the sleep–waking cycle in mammals. Although amphibians are thought to lack a neocortical homologue, changes in rest–activity states occur in these species. In the present study, EEG signals were recorded from the surface of the cerebral hemispheres and midbrain on both sides of the brain in an anuran species, Babina daunchina, using electrodes contacting the meninges in order to measure changes in mean EEG power across behavioral states. Functionally relevant frequency bands were identified using factor analysis. The results indicate that: (1) EEG power was concentrated in four frequency bands during the awake or active state and in three frequency bands during rest; (2) EEG bands in frogs differed substantially from humans, especially in the fast frequency band; (3) bursts similar to mammalian sleep spindles, which occur in non-rapid eye movement mammalian sleep, were observed when frogs were at rest suggesting sleep spindle-like EEG activity appeared prior to the evolution of mammals.     

A transition-constrained discrete hidden Markov model for automatic sleep staging

ABSTRACT: BACKGROUND: Approximately one-third of the human lifespan is spent sleeping. To diagnose sleep problems, all-night polysomnographic (PSG) recordings including electroencephalograms (EEGs), electrooculograms (EOGs) and electromyograms (EMGs), are usually acquired from the patient and scored by a well-trained expert according to Rechtschaffen & Kales (R&K) rules. Visual sleep scoring is a time-consuming and subjective process. Therefore, the development of an automatic sleep scoring method is desirable. METHOD: The EEG, EOG and EMG signals from twenty subjects were measured. In addition to selecting sleep characteristics based on the 1968 R&K rules, features utilized in other research were collected. Thirteen features were utilized including temporal and spectrum analyses of the EEG, EOG and EMG signals, and a total of 158 hours of sleep data were recorded. Ten subjects were used to train the Discrete Hidden Markov Model (DHMM), and the remaining ten were tested by the trained DHMM for recognition. Furthermore, the 2-fold cross validation was performed during this experiment. RESULTS: Overall agreement between the expert and the results presented is 85.29%. With the exception of S1, the sensitivities of each stage were more than 81%. The most accurate stage was SWS (94.9%), and the least-accurately classified stage was S1 (<34%). In the majority of cases, S1 was classified as Wake (21%), S2 (33%) or REM sleep (12%), consistent with previous studies. However, the total time of S1 in the 20 all-night sleep recordings was less than 4%. CONCLUSION: The results of the experiments demonstrate that the proposed method significantly enhances the recognition rate when compared with prior studies.     

Personality correlates with sleep-wake variables

A mail-in questionnaire study and two confirmatory archival analyses are described. Variables related to personality and measures of sleep timing, sleep quality, and sleep duration were initially assessed by self-report in a sample of 54 working adults (31.5% male, 23-48 yrs). Extraversion and neuroticism were measured by the Eysenck Personality Inventory (EPI), and the level of sub-clinical manic-type symptoms by the Attitude to Life Questionnaire (ATLQ). The quality of sleep was measured by the Pittsburgh Sleep Quality Index (PSQI) and by questions relating to habitual sleep latency and minutes awake after sleep onset from the Sleep Timing Questionnaire (STQ). The duration and timing of sleep was assessed using the STQ separately for work-week nights (Sunday-Thursday) and for weekend nights (Friday and Saturday). Morningness-eveningness was assessed using the Composite Scale of Morningness (CSM). Two confirmatory analyses using separate archival samples (Study A: n=201, 55.7% male, 20-57 yrs; Study B: n=101, 47.5% male, 18-59 yrs) were then used to confirm specific correlations of interest. In both initial and confirmatory studies, increased sub-clinical manic-type symptoms were found to be significantly associated with later bedtimes and wake-times during the work-week and lower (more evening-type) CSM scores, and higher neuroticism was associated with poorer sleep as indicated by higher PSQI scores. In contrast, no significant correlations emerged between any of the personality variables and any of the sleep duration variables. Personality appears to affect certain aspects of the timing and subjective quality of sleep, but not necessarily its duration.     

Hypercapnic cerebral vascular reactivity is decreased, in humans, during sleep compared with wakefulness.

During wakefulness, increases in the partial pressure of arterial CO(2) result in marked rises in cortical blood flow. However, during stage III-IV, non-rapid eye movement (NREM) sleep, and despite a relative state of hypercapnia, cortical blood flow is reduced compared with wakefulness. In the present study, we tested the hypothesis that, in normal subjects, hypercapnic cerebral vascular reactivity is decreased during stage III-IV NREM sleep compared with wakefulness. A 2-MHz pulsed Doppler ultrasound system was used to measure the left middle cerebral artery velocity (MCAV; cm/s) in 12 healthy individuals while awake and during stage III-IV NREM sleep. The end-tidal Pco(2) (Pet(CO(2))) was elevated during the awake and sleep states by regulating the inspired CO(2) load. The cerebral vascular reactivity to CO(2) was calculated from the relationship between Pet(CO(2)) and MCAV by using linear regression. From wakefulness to sleep, the Pet(CO(2)) increased by 3.4 Torr (P < 0.001) and the MCAV fell by 11.7% (P < 0.001). A marked decrease in cerebral vascular reactivity was noted in all subjects, with an average fall of 70.1% (P = 0.001). This decrease in hypercapnic cerebral vascular reactivity may, at least in part, explain the stage III-IV NREM sleep-related reduction in cortical blood flow.     

基于奇异值第一主成分的睡眠脑电分期方法研究

目的:脑电信号含多种噪声和伪迹,信噪比较低,特征提取前必须进行复杂的预处理,严重影响睡眠分期的速度。鉴于此,本文提出一种基于奇异值第一主成分的睡眠脑电分期方法,该方法抗噪性能较强,可省去预处理过程,减少计算量,提高睡眠分期的效率。方法:对未经过预处理的睡眠脑电进行奇异系统分析,研究奇异谱曲线,提取奇异值第一主成分,探索其随睡眠状态变化的规律。并通过支持向量机利用奇异值第一主成分对睡眠分期。结果:奇异值第一主成分不仅能表征脑电信号主体,而且可以抑制噪声、降低维数。随着睡眠的深入,奇异值第一主成分的值逐渐增大,但在REM期处于S1期和S2期之间。经MIT-BIH睡眠数据库中5例同导联位置的脑电数据测试(仅1导脑电数据),睡眠脑电分期的准确率达到86.4%。结论:在未对脑电信号进行预处理的情况下,提取的睡眠脑电的奇异值第一主成分能有效表征睡眠状态,是一种有效的睡眠分期依据。本文运用提出的方法仅采用1导脑电数据,就能得到较为满意的睡眠分期结果。该方法有较强的分类性能,且抗噪能力强,不需要对脑电作复杂的预处理,计算量小,方法简单,很大程度上提高了睡眠分期的效率。     

Multi-scale AM–FM analysis for the classification of surface electromyographic signals

In this work, multi-scale amplitude modulation–frequency modulation (AM–FM) features are extracted from surface electromyographic (SEMG) signals and they are used for the classification of neuromuscular disorders. The method is validated on SEMG signals recorded from a total of 40 subjects: 20 normal and 20 abnormal cases (11 myopathy, and 9 neuropathy cases), at 10%, 30%, 50%, 70% and 100% of maximum voluntary contraction (MVC), from the biceps brachii muscle. For the classification, three classifiers are used: (i) the statistical K-nearest neighbor (KNN), (ii) the self-organizing map (SOM) and (iii) the support vector machine (SVM). For all classifiers, the leave-one-out methodology is used to validate the classification of the SEMG signals into normal or abnormal (myopathy or neuropathy). A classification success rate of 78% for the AM–FM features and SVM models was achieved. These results also show that SEMG can be used as a non-invasive alternative to needle EMG for differentiating between normal and abnormal (myopathy, or neuropathy) cases.     

Sleep apnea and effect of chemostimulation on breathing instability in mice.

Sleep apnea occurs in humans and experimental animals. We examined whether it also arises in adult mice. Ventilation in male adult 129/Sv mice was recorded concomitantly by electroencephalograms and electromyograms for 6 h by use of body plethysmography. Apnea was defined as cessation of plethysmographic signals for longer than two respiratory cycles. While mice breathed room air, 32.3 +/- 6.9 (mean +/- SE, n = 5) apneas were observed during sleep but not in quiet awake periods. Sleep apneas were further classified into two types. Postsigh apneas occurred exclusively during slow-wave sleep (SWS), whereas spontaneous apneas arose during both SWS and rapid eye movement sleep. Compared with room air (9.1 +/- 1.4/h of SWS), postsigh apneas were more frequent in hypoxia (13.7 +/- 2.1) and less frequent in hyperoxia (3.6 +/- 1.7) and hypercapnia (2.8 +/- 2.1). Our data indicated that significant sleep apnea occurs in normal adult mice and suggested that the mouse could be a promising experimental model with which to study the genetic and molecular basis of respiratory regulation during sleep.