A review of signals used in sleep analysis

A Review on Automated Sleep Study

In recent years, research on automated sleep analysis has witnessed significant growth, reflecting advancements in understanding sleep patterns and their impact on overall health. This review synthesizes findings from an exhaustive analysis of 87 papers, systematically retrieved from prominent databases such as Google Scholar, PubMed, IEEE Xplore, and ScienceDirect. The selection criteria prioritized studies focusing on methods employed, signal modalities utilized, and machine learning algorithms applied in automated sleep analysis. The overarching goal was to critically evaluate the strengths and weaknesses of the proposed methods, shedding light on the current landscape and future directions in sleep research. An in-depth exploration of the reviewed literature revealed a diverse range of methodologies and machine learning approaches employed in automated sleep studies. Notably, K-Nearest Neighbors (KNN), Ensemble Learning Methods, and Support Vector Machine (SVM) emerged as versatile and potent classifiers, exhibiting high accuracies in various applications. However, challenges such as performance variability and computational demands were observed, necessitating judicious classifier selection based on dataset intricacies. In addition, the integration of traditional feature extraction methods with deep structures and the combination of different deep neural networks were identified as promising strategies to enhance diagnostic accuracy in sleep-related studies. The reviewed literature emphasized the need for adaptive classifiers, cross-modality integration, and collaborative efforts to drive the field toward more accurate, robust, and accessible sleep-related diagnostic solutions. This comprehensive review serves as a solid foundation for researchers and practitioners, providing an organized synthesis of the current state of knowledge in automated sleep analysis. By highlighting the strengths and challenges of various methodologies, this review aims to guide future research toward more effective and nuanced approaches to sleep diagnostics.

[Wearables in rheumatology]

As a result of digitalization in medicine wearable computing devices (wearables) are becoming increasingly more important. Wearables are small portable electronic devices with which the user can record data relevant to health, such as number of steps, activity profile, electrocardiogram (ECG), heart and breathing frequency or oxygen saturation. Initial studies on the use of wearables in patients with rheumatological diseases show the opening up of new possibilities for prevention, disease monitoring and treatment. This study provides the current data situation and the implementation of wearables in the discipline of rheumatology. Additionally, future potential fields of application as well as challenges and limits of the implementation of wearables are illustrated.

Evaluating Accuracy in Five Commercial Sleep-Tracking Devices Compared to Research-Grade Actigraphy and Polysomnography

The development of consumer sleep-tracking technologies has outpaced the scientific evaluation of their accuracy. In this study, five consumer sleep-tracking devices, research-grade actigraphy, and polysomnography were used simultaneously to monitor the overnight sleep of fifty-three young adults in the lab for one night. Biases and limits of agreement were assessed to determine how sleep stage estimates for each device and research-grade actigraphy differed from polysomnography-derived measures. Every device, except the Garmin Vivosmart, was able to estimate total sleep time comparably to research-grade actigraphy. All devices overestimated nights with shorter wake times and underestimated nights with longer wake times. For light sleep, absolute bias was low for the Fitbit Inspire and Fitbit Versa. The Withings Mat and Garmin Vivosmart overestimated shorter light sleep and underestimated longer light sleep. The Oura Ring underestimated light sleep of any duration. For deep sleep, bias was low for the Withings Mat and Garmin Vivosmart while other devices overestimated shorter and underestimated longer times. For REM sleep, bias was low for all devices. Taken together, these results suggest that proportional bias patterns in consumer sleep-tracking technologies are prevalent and could have important implications for their overall accuracy.

How does obstructive sleep apnea alter cerebral hemodynamics?

STUDY OBJECTIVES

We aimed to characterize the cerebral hemodynamic response to obstructive sleep apnea/hypopnea events, and evaluate their association to polysomnographic parameters. The characterization of the cerebral hemodynamics in obstructive sleep apnea (OSA) may add complementary information to further the understanding of the severity of the syndrome beyond the conventional polysomnography.

METHODS

Severe OSA patients were studied during night sleep while monitored by polysomnography. Transcranial, bed-side diffuse correlation spectroscopy (DCS) and frequency-domain near-infrared diffuse correlation spectroscopy (NIRS-DOS) were used to follow microvascular cerebral hemodynamics in the frontal lobes of the cerebral cortex. Changes in cerebral blood flow (CBF), total hemoglobin concentration (THC), and cerebral blood oxygen saturation (StO2) were analyzed.

RESULTS

We considered 3283 obstructive apnea/hypopnea events from sixteen OSA patients (Age (median, interquartile range) 57 (52-64.5); females 25%; AHI (apnea-hypopnea index) 84.4 (76.1-93.7)). A biphasic response (maximum/minimum followed by a minimum/maximum) was observed for each cerebral hemodynamic variable (CBF, THC, StO2), heart rate and peripheral arterial oxygen saturation (SpO2). Changes of the StO2 followed the dynamics of the SpO2, and were out of phase from the THC and CBF. Longer events were associated with larger CBF changes, faster responses and slower recoveries. Moreover, the extrema of the response to obstructive hypopneas were lower compared to apneas (p < .001).

CONCLUSIONS

Obstructive apneas/hypopneas cause profound, periodic changes in cerebral hemodynamics, including periods of hyper- and hypo-perfusion and intermittent cerebral hypoxia. The duration of the events is a strong determinant of the cerebral hemodynamic response, which is more pronounced in apnea than hypopnea events.

Prediction of obstructive sleep apnea using deep learning in 3D craniofacial reconstruction

Background

Obstructive sleep apnea (OSA) is a common sleep disorder. However, current diagnostic methods are labor-intensive and require professionally trained personnel. We aimed to develop a deep learning model using upper airway computed tomography (CT) to predict OSA and to warn the medical technician if a patient has OSA while the patient is undergoing any head and neck CT scan, even for other diseases.

Methods

A total of 219 patients with OSA [apnea-hypopnea index (AHI) ≥10/h] and 81 controls (AHI <10/h) were enrolled. We reconstructed each patient's CT into 3 types (skeletal structures, external skin structures, and airway structures) and captured reconstructed models in 6 directions (front, back, top, bottom, left profile, and right profile). The 6 images from each patient were imported into the ResNet-18 network to extract features and output the probability of OSA using two fusion methods: Add and Concat. Five-fold cross-validation was used to reduce bias. Finally, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were calculated.

Results

All 18 views with Add as the feature fusion performed better than did the other reconstruction and fusion methods. This gave the best performance for this prediction method with an AUC of 0.882.

Conclusions

We present a model for predicting OSA using upper airway CT and deep learning. The model has satisfactory performance and enables CT to accurately identify patients with moderate to severe OSA.

Device-based and subjective measurements of sleep in children with cerebral palsy: a comparison of sleep diary, actigraphy, and bed sensor data

STUDY OBJECTIVES

To investigate how subjective assessments and device-based measurements of sleep relate to each other in children with cerebral palsy (CP).

METHODS

Sleep of children with CP, classified at Gross Motor Function Classification System levels I-III, was measured during 7 consecutive nights using 1 subjective (ie, sleep diary) and 2 device-based (ie, actigraphy and bed sensor) instruments. The agreement between the instruments was assessed for all nights and separately for school- and weekend nights, using intraclass correlation coefficients (ICC) and Bland-Altman plots.

RESULTS

A total of 227 nights from 38 children with CP (53% male; median age [range] 6 [2-12] years), were included in the analyses. Sleep parameters showed poor agreement between the 3 instruments, except for total time in bed, which showed satisfactory agreement between (1) actigraphy and sleep diary (ICC > 0.86), (2) actigraphy and bed sensor (ICC > 0.84), and (3) sleep diary and bed sensor (ICC > 0.83). Furthermore, agreement between sleep diary and bed sensor was also satisfactory for total sleep time (ICC > 0.70) and wakefulness after sleep onset (ICC = 0.55; only during weekend nights).

CONCLUSIONS

Researchers and clinicians need to be aware of the discrepancies between instruments for sleep monitoring in children with CP. We recommend combining both subjective and device-based measures to provide information on the perception as well as an unbiased estimate of sleep. Further research needs to be conducted on the use of a bed sensor for sleep monitoring in children with CP.

CITATION

van Rijssen IM, Hulst RY, Gorter JW, et al. Device-based and subjective measurements of sleep in children with cerebral palsy: a comparison of sleep diary, actigraphy, and bed sensor data. J Clin Sleep Med. 2023;19(1):35-43.

Sensing Devices for Detecting and Processing Acoustic Signals in Healthcare

Acoustic signals are important markers to monitor physiological and pathological conditions, e.g., heart and respiratory sounds. The employment of traditional devices, such as stethoscopes, has been progressively superseded by new miniaturized devices, usually identified as microelectromechanical systems (MEMS). These tools are able to better detect the vibrational content of acoustic signals in order to provide a more reliable description of their features (e.g., amplitude, frequency bandwidth). Starting from the description of the structure and working principles of MEMS, we provide a review of their emerging applications in the healthcare field, discussing the advantages and limitations of each framework. Finally, we deliver a discussion on the lessons learned from the literature, and the open questions and challenges in the field that the scientific community must address in the near future.

Jumping Knowledge Based Spatial-temporal Graph Convolutional Networks for Automatic Sleep Stage Classification

A novel jumping knowledge spatial-temporal graph convolutional network (JK-STGCN) is proposed in this paper to classify sleep stages. Based on this method, different types of multi-channel bio-signals, including electroencephalography (EEG), electromyogram (EMG), electrooculogram (EOG), and electrocardiogram (ECG) are utilized to classify sleep stages, after extracting features by a standard convolutional neural network (CNN) named FeatureNet. Intrinsic connections among different bio-signal channels from the identical epoch and neighboring epochs can be obtained through two adaptive adjacency matrices learning methods. A jumping knowledge spatial-temporal graph convolution module helps the JK-STGCN model to extract spatial features from the graph convolutions efficiently and temporal features are extracted from its common standard convolutions to learn the transition rules among sleep stages. Experimental results on the ISRUC-S3 dataset showed that the overall accuracy achieved 0.831 and the F1-score and Cohen kappa reached 0.814 and 0.782, respectively, which are the competitive classification performance with the state-of-the-art baselines. Further experiments on the ISRUC-S3 dataset are also conducted to evaluate the execution efficiency of the JK-STGCN model. The training time on 10 subjects is 2621s and the testing time on 50 subjects is 6.8s, which indicates its highest calculation speed compared with the existing high-performance graph convolutional networks and U-Net architecture algorithms. Experimental results on the ISRUC-S1 dataset also demonstrate its generality, whose accuracy, F1-score, and Cohen kappa achieve 0.820, 0.798, and 0.767 respectively.

Detection of Sleep Apnea from Electrocardiogram and Pulse Oximetry Signals Using Random Forest

Sleep apnea (SA) is a common sleep disorder which could impair the human physiological system. Therefore, early diagnosis of SA is of great interest. The traditional method of diagnosing SA is an overnight polysomnography (PSG) evaluation. When PSG has limited availability, automatic SA screening with a fewer number of signals should be considered. The primary purpose of this study is to develop and evaluate a SA detection model based on electrocardiogram (ECG) and blood oxygen saturation (SpO2). We adopted a multimodal approach to fuse ECG and SpO2 signals at the feature level. Then, feature selection was conducted using the recursive feature elimination with cross-validation (RFECV) algorithm and random forest (RF) classifier used to discriminate between apnea and normal events. Experiments were conducted on the Apnea-ECG database. The introduced algorithm obtained an accuracy of 97.5%, a sensitivity of 95.9%, a specificity of 98.4% and an AUC of 0.992 in per-segment classification, and outperformed previous works. The results showed that ECG and SpO2 are complementary in detecting SA, and that the combination of ECG and SpO2 enhances the ability to diagnose SA. Therefore, the proposed method has the potential to be an alternative to conventional detection methods.

Towards Sleep Study Automation: Detection Evaluation of Respiratory-Related Events

The diagnosis of sleep disordered breathing depends on the detection of several respiratory-related events: apneas, hypopneas, snores, or respiratory event-related arousals from sleep studies. While a number of automatic detection methods have been proposed, reproducibility of these methods has been an issue, in part due to the absence of a generally accepted protocol for evaluating their results. With sleep measurements this is usually treated as a classification problem and the accompanying issue of localization is not treated as similarly critical. To address these problems we present a detection evaluation protocol that is able to qualitatively assess the match between two annotations of respiratory-related events. This protocol relies on measuring the relative temporal overlap between two annotations in order to find an alignment that maximizes their F1-score at the sequence level. This protocol can be used in applications which require a precise estimate of the number of events, total event duration, and a joint estimate of event number and duration. We assess its application using a data set that contains over 10,000 manually annotated snore events from 9 subjects, and show that when using the American Academy of Sleep Medicine Manual standard, two sleep technologists can achieve an F1-score of 0.88 when identifying the presence of snore events. In addition, we drafted rules for marking snore boundaries and showed that one sleep technologist can achieve F1-score of 0.94 at the same tasks. Finally, we compared our protocol against the protocol that is used to evaluate sleep spindle detection and highlighted the differences.

A Comprehensive Review: Computational Models for Obstructive Sleep Apnea Detection in Biomedical Applications

Obstructive sleep apnea (OSA) is a sleep disorder characterized by periodic episodes of partial or complete upper airway obstruction caused by narrowing or collapse of the pharyngeal airway despite ongoing breathing efforts during sleep. Fall in the blood oxygen saturation and cortical arousals are prompted by this reduction in the airflow which lasts for at least 10 seconds. Impaired labor performance, debilitated quality of life, excessive daytime sleepiness, high snoring, and tiredness even after a whole night's sleep are the primary symptoms of OSA. In due course, the long-standing contributions of OSA culminate in hypertension, arrhythmia, cerebrovascular disease, and heart failure. The traditional diagnostic approach of OSA is the laboratory-based polysomnography (PSG) overnight sleep study, which is a tedious and labor-intensive process that exaggerates the discomfort to the patient. With the advent of computer-aided diagnosis (CAD), automatic detection of OSA has gained increasing interest among researchers in the area of sleep disorders as it influences both diagnostic and therapeutic decisions. The research literature on sleep apnea published during the last decade has been surveyed, focusing on the varied screening approaches accustomed to identifying OSA events and the developmental knowledge offered by multiple contributors from the software perspective. The current study presents an overview of the pathophysiology of OSA, the detection methods, physiological signals related to OSA, the different preprocessing, feature extraction, feature selection, and classification techniques employed for the detection and classification of OSA. Consequently, the research challenges and research gaps in the diagnosis of OSA are identified, critically analyzed, and presented in the best possible light.

Obstructive Sleep Apnea Detection Based on Sleep Sounds via Deep Learning

PURPOSE

This study aimed to propose a novel deep-learning method for automatic sleep apneic event detection and thus to estimate the apnea hypopnea index (AHI) and identify obstructive sleep apnea (OSA) in an event-by-event manner solely based on sleep sounds obtained by a noncontact audio recorder.

METHODS

We conducted a cross-sectional study of participants with habitual snoring or heavy breathing sounds during sleep to train and test a deep convolutional neural network named OSAnet for the detection of OSA based on sleep sounds. Polysomnography (PSG) was conducted, and sleep sounds were recorded simultaneously in a regular room without noise attenuation. The study was conducted in two phases. In phase one, eligible participants were enrolled and randomly allocated into training and validation groups for deep learning algorithm development. In phase two, eligible patients were enrolled in a test group for algorithm assessment. Sensitivity, specificity, accuracy, unweighted Cohen kappa coefficient (κ) and the area under the curve (AUC) were calculated using PSG as the reference standard.

RESULTS

A total of 135 participants were randomly divided into a training group (n, 116) and a validation group (n, 19). An independent test group of 59 participants was subsequently enrolled. Our algorithm achieved a precision of 0.81 and sensitivity of 0.78 in the test group for overall sleep event detection. The algorithm exhibited robust diagnostic performance to identify severe cases with a sensitivity of 95.6% and specificity of 91.6%.

CONCLUSION

Our results showed that a deep learning algorithm based on sleep sounds recorded by a noncontact voice recorder served as a feasible tool for apneic event detection and OSA identification. This technique may hold promise for OSA assessment in the community in a relatively comfortable and low-cost manner. Further studies to develop a tool based on a home-based setting are warranted.

Emergence and fragmentation of the alpha-band driven by neuronal network dynamics

Rhythmic neuronal network activity underlies brain oscillations. To investigate how connected neuronal networks contribute to the emergence of the α-band and to the regulation of Up and Down states, we study a model based on synaptic short-term depression-facilitation with afterhyperpolarization (AHP). We found that the α-band is generated by the network behavior near the attractor of the Up-state. Coupling inhibitory and excitatory networks by reciprocal connections leads to the emergence of a stable α-band during the Up states, as reflected in the spectrogram. To better characterize the emergence and stability of thalamocortical oscillations containing α and δ rhythms during anesthesia, we model the interaction of two excitatory networks with one inhibitory network, showing that this minimal topology underlies the generation of a persistent α-band in the neuronal voltage characterized by dominant Up over Down states. Finally, we show that the emergence of the α-band appears when external inputs are suppressed, while fragmentation occurs at small synaptic noise or with increasing inhibitory inputs. To conclude, α-oscillations could result from the synaptic dynamics of interacting excitatory neuronal networks with and without AHP, a principle that could apply to other rhythms.

Brain oscillations, recorded from electroencephalograms characterize behaviors such as sleep, wakefulness, brain evoked responses, coma or anesthesia. The underlying rhythms for these oscillations are associated at a neuronal population level to fluctuations of the membrane potential between Up (depolarized) and Down (hyperpolarized) states. During anesthesia with propofol, a dominant α-band (8–12Hz) can emerge or disappear, but the underlying mechanism remains unclear. Using modeling, we report that the α-band appears during Up states in neuronal populations driven by short-term synaptic plasticity and synaptic noise. Moreover, we show that three connected neuronal networks representing the thalamocortical loop reproduce the dynamics of the α-band, which emerges following the arrest of excitatory stimulations, but that can disappear by increasing inhibitory inputs. To conclude, short-term plasticity in well connected neuronal networks can explain the emergence and fragmentation of the α-band.

Development of a Smart Sleep Mask with Multiple Sensors

In this work, we demonstrated a Smart Sleep Mask with several integrated physiological sensors such as 3-axis accelerometers, respiratory acoustic sensor, and an eye movement sensor. In particular, using infrared optical sensors, eye movement frequency, direction, and amplitude can be directly monitored and recorded during sleep sessions. We also developed a mobile app for data storage, signal processing and data analytics. Aggregation of these signals from a single wearable device may offer ease of use and more insights for sleep monitoring and REM sleep assessment. The user-friendly mask design can enable at-home use applications in the studies of digital biomarkers for sleep disorder related neurodegenerative diseases. Examples include REM Sleep Behavior Disorder, epilepsy event detection and stroke induced facial and eye movement disorder.Clinical Relevance-Many diseases such as stroke, epilepsy, and Parkinson's disease can cause significant abnormal events during sleep or are associated with sleep disorder. A smart sleep mask may serve as a simple platform to provide various physiological signals and generate clinical meaningful insights by revealing the neurological activities during various sleep stages.

Consumer Smartwatches As a Portable PSG: LSTM Based Neural Networks for a Sleep-Related Physiological Parameters Estimation

Recently, mobile and wearable devices have become an increasingly integral part of our lives. They provide a possibility of detailed health monitoring using noninvasive and user-friendly techniques. However, lack of continuous monitoring, the need of specific sensors, and the limitations in memory and power consumption are only some of the potential drawbacks of such devices. In the current paper a system based on a deep recurrent neural network is developed for an automatic continuous monitoring of sleep-related physiological parameters by means of a wearable biosignal monitoring systems. Smartwatches based algorithm for non-invasive monitoring of sleep stages, respiratory events (including sleep apnea and hypopnea), snore and blood oxygen saturation is developed. Our experimental results demonstrate that proposed model constitutes a noninvasive and inexpensive screening system for sleep-related physiological parameters and pathological states. The model has shown a 77 % accuracy in sleep stages prediction, more than 80 % accuracy in epoch-by-epoch respiratory events classification, above 60 % accuracy in snore events classification and above 70 % accuracy in blood oxygen saturation (SpO₂) level classification (for a two class problem with a SpO₂ threshold of 95 %).

Metrics of sleep apnea severity: beyond the apnea-hypopnea index

Obstructive sleep apnea (OSA) is thought to affect almost 1 billion people worldwide. OSA has well established cardiovascular and neurocognitive sequelae, although the optimal metric to assess its severity and/or potential response to therapy remains unclear. The apnea-hypopnea index (AHI) is well established; thus, we review its history and predictive value in various different clinical contexts. Although the AHI is often criticized for its limitations, it remains the best studied metric of OSA severity, albeit imperfect. We further review the potential value of alternative metrics including hypoxic burden, arousal intensity, odds ratio product, and cardiopulmonary coupling. We conclude with possible future directions to capture clinically meaningful OSA endophenotypes including the use of genetics, blood biomarkers, machine/deep learning and wearable technologies. Further research in OSA should be directed towards providing diagnostic and prognostic information to make the OSA diagnosis more accessible and to improving prognostic information regarding OSA consequences, in order to guide patient care and to help in the design of future clinical trials.

Deconstructing Commercial Wearable Technology: Contributions toward Accurate and Free-Living Monitoring of Sleep

Despite prolific demands and sales, commercial sleep assessment is primarily limited by the inability to "measure" sleep itself; rather, secondary physiological signals are captured, combined, and subsequently classified as sleep or a specific sleep state. Using markedly different approaches compared with gold-standard polysomnography, wearable companies purporting to measure sleep have rapidly developed during recent decades. These devices are advertised to monitor sleep via sensors such as accelerometers, electrocardiography, photoplethysmography, and temperature, alone or in combination, to estimate sleep stage based upon physiological patterns. However, without regulatory oversight, this market has historically manufactured products of poor accuracy, and rarely with third-party validation. Specifically, these devices vary in their capacities to capture a signal of interest, process the signal, perform physiological calculations, and ultimately classify a state (sleep vs. wake) or sleep stage during a given time domain. Device performance depends largely on success in all the aforementioned requirements. Thus, this review provides context surrounding the complex hardware and software developed by wearable device companies in their attempts to estimate sleep-related phenomena, and outlines considerations and contributing factors for overall device success.

Effects of antipsychotics on circadian rhythms in humans: a systematic review and meta-analysis

Antipsychotics are widely used to treat psychiatric illness and insomnia. However, the etiology of insomnia is multifactorial, including disrupted circadian rhythms. Several studies show that antipsychotics might modulate even healthy circadian rhythms. The purpose of this systematic review is to integrate current knowledge about the effects of antipsychotics on the circadian rhythms in humans, and to conduct a meta- analysis with the available data. Nine electronic databases were searched. We followed the PRISMA guidelines and included randomized controlled trials (RCTs), non-RCTs, case-control studies, case series, and case reports. Of 7,217 articles, 70 were included. The available data was mainly from healthy individuals, or patients having schizophrenia, but the findings showed a transdiagnostic impact on circadian parameters. This was consistently seen as decreased amplitude of cortisol, melatonin, and body temperature. Particularly, a meta-analysis of 16 RCTs measuring cortisol rhythm showed that antipsychotics, especially atypical antipsychotics, decreased the cortisol area under the curve and morning cortisol level, compared to placebo. The data with melatonin or actigraphy was limited. Overall, this evidence about the circadian effect of antipsychotics showed a need for longitudinal, real-time monitoring of specific circadian markers to differentiate a change in amplitude from a shift in phasing, and for knowledge about optimal timing of administration of antipsychotics, according to individual baseline circadian parameters. Standardizing selection criteria and outcome methods could facilitate good quality intervention studies and evidence-based treatment guidelines. This is relevant considering the accumulating evidence of the high prevalence and unfavorable impact of disrupted circadian rhythms in psychiatric disorders.

Automatic Sleep Stage Classification Using Temporal Convolutional Neural Network and New Data Augmentation Technique from Raw Single-Channel EEG

BACKGROUND AND OBJECTIVE

This paper presents a new framework for automatic classification of sleep stages using a deep learning algorithm from single-channel EEG signals. Each segmented EEG signal appended with its label of stages is fed into a deep learning model to create an automatic sleep stage classification. This is one of the most important problems that is critical to the realization of monitoring patients with sleep disorder.

METHODS

In the present study, a neural network architecture is introduced utilizing Convolutional Neural Networks (CNNs) to extract features, followed by Temporal Convolutional Neural Network to extract the temporal features from the extracted features vector of CNN. Finally, the performance of our model is improved by a Conditional Random Field layer. We also employed a new data augmentation technique to enhance the CNNs training which has auxiliary effects.

RESULTS

We evaluated our model by two different single-channel EEG signals (i.e., Fpz-Cz and Pz-Oz EEG channels) from two public sleep datasets, named Sleep-EDF-2013 and Sleep-EDF-2018. The evaluation results on both datasets showed that our model obtains the best total accuracy and kappa score (EDF-2013: 85.39%- 0.80, EDF-2018: 82.46%- 0.76) compared to the state-of-the-art methods.

CONCLUSIONS

This study will possibly allow us to have a wearable sleep monitoring system with a single-channel EEG. Also, unlike hand-crafted features methods, our model finds its own patterns through training epochs, and therefore, it may minimize engineering bias.

Positional obstructive sleep apnea within a large multicenter French cohort: prevalence, characteristics, and treatment outcomes

STUDY OBJECTIVES

To assess, in a large cohort of patients with obstructive sleep apnea, the factors that are independently associated with positional obstructive sleep apnea (POSA) and exclusive POSA (e-POSA) and determine their prevalence. The secondary objective was to evaluate the outcome of positive airway pressure (PAP) therapy for patients with POSA and e-POSA.

METHODS

This retrospective study included 6,437 patients with typical mild-to-severe OSA from the Pays de la Loire sleep cohort. Patients with POSA and e-POSA were compared to those with non-POSA for clinical and polysomnographic characteristics. In a subgroup of patients (n = 3,000) included in a PAP follow-up analysis, we determined whether POSA and e-POSA phenotypes were associated with treatment outcomes at 6 months.

RESULTS

POSA and e-POSA had a prevalence of 53.5% and 20.1%, respectively, and were independently associated with time in supine position, male sex, younger age, lower apnea-hypopnea index and lower body mass index. After adjustment for confounding factors, patients with POSA and e-POSA had a significantly lower likelihood of treatment adherence (PAP daily use ≥ 4 h) at 6 months and were at higher risk of PAP treatment withdrawal compared to those with non-POSA.

CONCLUSIONS

The prevalence and independent predictors of POSA and e-POSA were determined in this large clinical population. Patients with POSA and e-POSA have lower PAP therapy adherence, and this choice of treatment may not be optimal. Thus, there is a need to offer these patients an alternative therapy.

A fused-image-based approach to detect obstructive sleep apnea using a single-lead ECG and a 2D convolutional neural network

Obstructive sleep apnea (OSA) is a common chronic sleep disorder that disrupts breathing during sleep and is associated with many other medical conditions, including hypertension, coronary heart disease, and depression. Clinically, the standard for diagnosing OSA involves nocturnal polysomnography (PSG). However, this requires expert human intervention and considerable time, which limits the availability of OSA diagnosis in public health sectors. Therefore, electrocardiogram (ECG)-based methods for OSA detection have been proposed to automate the polysomnography procedure and reduce its discomfort. So far, most of the proposed approaches rely on feature engineering, which calls for advanced expert knowledge and experience. This paper proposes a novel fused-image-based technique that detects OSA using only a single-lead ECG signal. In the proposed approach, a convolutional neural network extracts features automatically from images created with one-minute ECG segments. The proposed network comprises 37 layers, including four residual blocks, a dense layer, a dropout layer, and a soft-max layer. In this study, three time-frequency representations, namely the scalogram, the spectrogram, and the Wigner-Ville distribution, were used to investigate the effectiveness of the fused-image-based approach. We found that blending scalogram and spectrogram images further improved the system's discriminative characteristics. Seventy ECG recordings from the PhysioNet Apnea-ECG database were used to train and evaluate the proposed model using 10-fold cross validation. The results of this study demonstrated that the proposed classifier can perform OSA detection with an average accuracy, recall, and specificity of 92.4%, 92.3%, and 92.6%, respectively, for the fused spectral images.

Can Machine Learning Assist Locating the Excitation of Snore Sound? A Review

In the past three decades, snoring (affecting more than 30 % adults of the UK population) has been increasingly studied in the transdisciplinary research community involving medicine and engineering. Early work demonstrated that, the snore sound can carry important information about the status of the upper airway, which facilitates the development of non-invasive acoustic based approaches for diagnosing and screening of obstructive sleep apnoea and other sleep disorders. Nonetheless, there are more demands from clinical practice on finding methods to localise the snore sound's excitation rather than only detecting sleep disorders. In order to further the relevant studies and attract more attention, we provide a comprehensive review on the state-of-the-art techniques from machine learning to automatically classify snore sounds. First, we introduce the background and definition of the problem. Second, we illustrate the current work in detail and explain potential applications. Finally, we discuss the limitations and challenges in the snore sound classification task. Overall, our review provides a comprehensive guidance for researchers to contribute to this area.

Bed Sensor Technology for Objective Sleep Monitoring Within the Clinical Rehabilitation Setting: Observational Feasibility Study

Background

Since adequate sleep is essential for optimal inpatient rehabilitation, there is an increased interest in sleep assessment. Unobtrusive, contactless, portable bed sensors show great potential for objective sleep analysis.

Objective

The aim of this study was to investigate the feasibility of a bed sensor for continuous sleep monitoring overnight in a clinical rehabilitation center.

Methods

Patients with incomplete spinal cord injury (iSCI) or stroke were monitored overnight for a 1-week period during their in-hospital rehabilitation using the Emfit QS bed sensor. Feasibility was examined based on missing measurement nights, coverage percentages, and missing periods of heart rate (HR) and respiratory rate (RR). Furthermore, descriptive data of sleep-related parameters (nocturnal HR, RR, movement activity, and bed exits) were reported.

Results

In total, 24 participants (12 iSCI, 12 stroke) were measured. Of the 132 nights, 5 (3.8%) missed sensor data due to Wi-Fi (2), slipping away (1), or unknown (2) errors. Coverage percentages of HR and RR were 97% and 93% for iSCI and 99% and 97% for stroke participants. Two-thirds of the missing HR and RR periods had a short duration of ≤120 seconds. Patients with an iSCI had an average nocturnal HR of 72 (SD 13) beats per minute (bpm), RR of 16 (SD 3) cycles per minute (cpm), and movement activity of 239 (SD 116) activity points, and had 86 reported and 84 recorded bed exits. Patients with a stroke had an average nocturnal HR of 61 (SD 8) bpm, RR of 15 (SD 1) cpm, and movement activity of 136 (SD 49) activity points, and 42 reported and 57 recorded bed exits. Patients with an iSCI had significantly higher nocturnal HR (t₁₈=−2.1, P=.04) and movement activity (t₁₈=−1.2, P=.02) compared to stroke patients. Furthermore, there was a difference between self-reported and recorded bed exits per night in 26% and 38% of the nights for iSCI and stroke patients, respectively.

Conclusions

It is feasible to implement the bed sensor for continuous sleep monitoring in the clinical rehabilitation setting. This study provides a good foundation for further bed sensor development addressing sleep types and sleep disorders to optimize care for rehabilitants.

Low Power Bio-Impedance Sensor Interfaces: Review and Electronics Design Methodology

Assessing blood flow, respiration patterns, and body composition with wearable and noninvasive bio-impedance (BioZ) sensors has distinctive advantages over the conventional clinical practice. The merits of BioZ sensors derive from having long-term monitoring capability and improved user friendliness. These open up the way to build medical grade wearable devices for chronic conditions. Low power, high precision BioZ sensor interface IC is the heart of such devices, it also determines the signal integrity of the overall system. Nevertheless, electrical design challenges from both circuit and system perspective still need to be addressed. This paper reviews the pioneering BioZ interface ICs and systems, and proposes major electrical specifications for wearable BioZ sensors. System design methodologies and circuit optimization techniques are summarized as guidelines to develop the next generation BioZ interface electronics.

Glucose control upon waking is unaffected by hourly sleep fragmentation during the night, but is impaired by morning caffeinated coffee

Morning coffee is a common remedy following disrupted sleep, yet each factor can independently impair glucose tolerance and insulin sensitivity in healthy adults. Remarkably, the combined effects of sleep fragmentation and coffee on glucose control upon waking per se have never been investigated. In a randomised crossover design, twenty-nine adults (mean age: 21 (sd 1) years, BMI: 24·4 (sd 3·3) kg/m2) underwent three oral glucose tolerance tests (OGTT). One following a habitual night of sleep (Control; in bed, lights-off trying to sleep approximately 23.00-07.00 hours), the others following a night of sleep fragmentation (as Control but waking hourly for 5 min), with and without morning coffee approximately 1 h after waking (approximately 300 mg caffeine as black coffee 30 min prior to OGTT). Individualised peak plasma glucose and insulin concentrations were unaffected by sleep quality but were higher following coffee consumption (mean (normalised CI) for Control, Fragmented and Fragmented + Coffee, respectively; glucose: 8·20 (normalised CI 7·93, 8·47) mmol/l v. 8·23 (normalised CI 7·96, 8·50) mmol/l v. 8·96 (normalised CI 8·70, 9·22) mmol/l; insulin: 265 (normalised CI 247, 283) pmol/l; and 235 (normalised CI 218, 253) pmol/l; and 310 (normalised CI 284, 337) pmol/l). Likewise, incremental AUC for plasma glucose was higher in the Fragmented + Coffee trial compared with Fragmented. Whilst sleep fragmentation did not alter glycaemic or insulinaemic responses to morning glucose ingestion, if a strong caffeinated coffee is consumed, then a reduction in glucose tolerance can be expected.

Late and Instable Sleep Phasing is Associated With Irregular Eating Patterns in Eating Disorders

BACKGROUND

Sleep problems are common in eating disorders (EDs).

PURPOSE

We evaluated whether sleep-phasing regularity associates with the regularity of daily eating events.

METHODS

ED patients (n = 29) completed hourly charts of mood and eating occasions for 2 weeks. Locomotor activity was recorded continuously by wrist actigraphy for a minimum of 10 days, and sleep was calculated based on periods of inactivity. We computed the center of daily inactivity (CenDI) as a measure of sleep phasing and consolidation of the daily inactivity (ConDI) as a measure of daily sleep rhythm strength. We assessed interday irregularities in the temporal structure of food intake using the standard deviation (SD) of frequency (IFRQ), timing (ITIM), and interval (IINT) of food intake. A self-evaluation of other characteristics included mood, anxiety, and early trauma.

RESULTS

A later phasing of sleep associated with a lower frequency of eating (eating frequency with the CenDI rho = -0.49, p = .007). The phasing and rhythmic strength of sleep correlated with the degree of eating irregularity (CenDI with ITIM rho = 0.48, p = .008 and with IINT rho = 0.56, p = .002; SD of CenDI with ITIM rho = 0.47, p = .010, and SD of ConDI with IINT rho = 0.37, p = .048). Childhood Trauma Questionnaire showed associations with variation of sleep onset (rho = -0.51, p = .005) and with IFRQ (rho = 0.43, p = .023).

CONCLUSIONS

Late and variable phasing of sleep associated robustly with irregular pattern of eating. Larger data sets are warranted to enable the analysis of diagnostic subgroups, current medication, and current symptomatology and to confirm the likely bidirectional association between eating pattern stability and the timing of sleep.

A novel deep feature transfer-based OSA detection method using sleep sound signals

OBJECTIVE

Polysomnography is typically used to evaluate the severity of obstructive sleep apnea (OSA) but the inconvenience of application and high cost considerably affect the diagnostics. In this study, sleep sound signals are used to detect OSA in patients.

APPROACH

A deep feature transfer-based OSA detection approach is proposed. First, a deep convolutional neural network is trained on large-scale labeled audio data sets to distinguish respiration sounds from environmental noise. Second, the trained model is transferred to recognize respiration sounds in sleep sound signals. Third, the deep features of the detected respiration sounds are used to train a logistic regression classifier to identify OSA patients from potential patients. Polysomnography-based diagnosis is used as a reference.

MAIN RESULTS

A self-collected data set of 132 potential OSA patients is applied in OSA detection experiments. The OSA detection performances are tested on four models for different apnea-hypopnea index thresholds and sexes resulting in accuracies of 80.17%, 80.21%, 81.63% and 77.22%. The corresponding areas under the receiver operating characteristic curves are 0.82, 0.80, 0.81 and 0.79. In addition, the proposed method presented a significant performance improvement compared with the state-of-the-art methods.

SIGNIFICANCE

Big data, deep learning and transfer learning can be successfully applied to improve diagnostic accuracy in OSA detection. The performance of the proposed approach is superior to that of traditional audio analysis technology. The proposed method significantly reduces difficulties in OSA detection and diagnosis, such that potential OSA patients can perform initial inspections by themselves at home.

Automatic Sleep Stage Detection: A Study on the Influence of Various PSG Input Signals

Automatic sleep stage detection can be performed using a variety of input signals from a polysomnographic (PSG) recording. In this study, we investigate the effect of different input signals on the performance of feature-based automatic sleep stage classification algorithms with both a Random Forest (RF) and Multilayer Perceptron (MLP) classifier. Combinations of the EEG (electroencephalographic) signal and ECG (electrocardiographic), EMG (electromyographic) and respiratory signals as input are investigated as input with respect to using single channel and multi-channel EEG as input. The Physionet "You Snooze, You Win" dataset is used for the study. The RF classifier consistently outperforms our MLP implementation in all cases and is positively affected by specific signal combinations. The overall classification performance using a single channel EEG is high (an accuracy, precision and recall of 86.91 %, 89.52%, 86.91% respectively) using RF. The results are comparable to the performance obtained using six EEG channels as input. Adding respiratory signals to the inputs processed by RF increases the N2 stage detection performance with 20%, while adding the EMG signal improves the accuracy of the REM stage detection with 5%. Our analysis shows that adding specific signals as input to RF improves the accuracy of specific sleep stages and increases the overall performance. Using a combination of EEG and respiratory signals we achieved an accuracy of 93% for the RF classifier.

Feasibility of a Sensor-Based Technological Platform in Assessing Gait and Sleep of In-Hospital Stroke and Incomplete Spinal Cord Injury (iSCI) Patients

Recovery of the walking function is one of the most common rehabilitation goals of neurological patients. Sufficient and adequate sleep is a prerequisite for recovery or training. To objectively monitor patients’ progress, a combination of different sensors measuring continuously over time is needed. A sensor-based technological platform offers possibilities to monitor gait and sleep. Implementation in clinical practice is of utmost relevance and has scarcely been studied. Therefore, this study examined the feasibility of a sensor-based technological platform within the clinical setting. Participants (12 incomplete spinal cord injury (iSCI), 13 stroke) were asked to wear inertial measurement units (IMUs) around the ankles during daytime and the bed sensor was placed under their mattress for one week. Feasibility was established based on missing data, error cause, and user experience. Percentage of missing measurement days and nights was 14% and 4%, respectively. Main cause of lost measurement days was related to missing IMU sensor data. Participants were not impeded, did not experience any discomfort, and found the sensors easy to use. The sensor-based technological platform is feasible to use within the clinical rehabilitation setting for continuously monitoring gait and sleep of iSCI and stroke patients.

Automated sleep apnea detection from cardio-pulmonary signal using bivariate fast and adaptive EMD coupled with cross time-frequency analysis

Sleep apnea is a sleep related pathology in which breathing or respiratory activity of an individual is obstructed, resulting in variations in the cardio-pulmonary (CP) activity. The monitoring of both cardiac (heart rate (HR)) and pulmonary (respiration rate (RR)) activities are important for the automated detection of this ailment. In this paper, we propose a novel automated approach for sleep apnea detection using the bivariate CP signal. The bivariate CP signal is formulated using both HR and RR signals extracted from the electrocardiogram (ECG) signal. The approach consists of three stages. First, the bivariate CP signal is decomposed into intrinsic mode functions (IMFs) and residuals for both HR and RR channels using bivariate fast and adaptive empirical mode decomposition (FAEMD). Second, the features are extracted using time-domain analysis, spectral analysis, and time-frequency domain analysis of IMFs from CP signal. The time-frequency domain features are computed from the cross time-frequency matrices of IMFs of CP signal. The cross time-frequency matrix of each IMF is evaluated using the Stockwell (S)-transform. Third, the support vector machine (SVM) and the random forest (RF) classifiers are used for automated detection of sleep apnea with the features from the bivariate CP signal. Our proposed approach has demonstrated an average sensitivity and specificity of 82.27% and 78.67%, respectively for sleep apnea detection using the 10-fold cross-validation method. The approach has yielded an average sensitivity and specificity of 73.19% and 73.13%, respectively for the subject-specific cross-validation. The performance of the approach was compared with other CPC features used for the detection of sleep apnea.

Sensors Capabilities, Performance, and Use of Consumer Sleep Technology

Sleep is crucial for the proper functioning of bodily systems and for cognitive and emotional processing. Evidence indicates that sleep is vital for health, well-being, mood, and performance. Consumer sleep technologies (CSTs), such as multisensory wearable devices, have brought attention to sleep and there is growing interest in using CSTs in research and clinical applications. This article reviews how CSTs can process information about sleep, physiology, and environment. The growing number of sensors in wearable devices and the meaning of the data collected are reviewed. CSTs have the potential to provide opportunities to measure sleep and sleep-related physiology on a large scale.

Comparing Different Methods of Hand-crafted HRV, EDR and CPC Features for Sleep Apnoea Detection

In this paper, we extracted hand crafted features from the ECG signals and evaluated the performance of different combination of features for sleep apnoea detection. We calculated the ECG derived respiratory (EDR) signal using three methods (QRS area, amplitude demodulation and fast PCA methods) and then calculated the cardiopulmonary coupling (CPC) spectrum using each EDR method. We then extracted features from the CPC spectrums and the time and frequency representations of the heart rate variability (HRV) and EDR signals Then, we compared the performance results of different combinations of the features used for automated sleep apnoea detection. We also applied a temporal optimisation method by averaging the features of every three adjacent epochs. Two classifiers were used to detect sleep apnoea: the extreme learning machine (ELM), and linear discriminant analysis. The features were evaluated on the MIT PhysioNet Apnea-ECG database. Apnoea detection was evaluated with leave-one-record-out cross-validation. The PCA CPC features obtained the highest accuracy of 86.5% and AUC of 0.94 using LDA classifier. The performance results of the combined features (of PCA method) obtained the same results. We conclude that for this study, the CPC features using fast PCA method are our best feature set for sleep apnoea detection.

Non-invasive Diagnosis of Sleep Apnoea Using ECG and Respiratory Bands

In this paper, we used ECG signals and repiratory inductance plethysmography (RIP) or respiratory bands. We evaluated the performance of the signals individually as well as different combinations of features and signals for sleep apnoea detection. We implemented two methods (QRS area, and fast principal component analysis (PCA) methods) for estimating the ECG derived respiratory (EDR) signal and the cardiopulmonary coupling (CPC) spectrum. We then extracted features from the time and frequency representations of the ECG and RIP signals. Finally, we applied different features sets to a linear discriminant analysis (LDA) for classification. The results were examined on the MIT PhysioNet Apnea-ECG database. Apnoea classification was carried out using leave-one-record-out crossvalidation approach. The highest performance of our algorithm was achieved using the RIP and RR-interval features as well as using the RIP and PCA CPC features with an accuracy of 90% and AUC of 0.97. The highest performance results of using only RIP or ECG features achieved an accuracy of 87% and AUC of 0.95. We conclude that although ECG sensors are more convenient for patients in sleep studies, using both RIP and ECG sensors enhances the performance results for automated diagnosis of sleep apnoea.

Actigraphy for Assessing Light Effects on Sleep and Circadian Activity Rhythm in Alzheimer's Dementia: A Narrative Review

Background:

Alzheimer's Disease (AD) is often accompanied by severe sleep problems and circadian rhythm disturbances which may to some extent be attributed to a dysfunction in the biological clock. The 24-h light/dark cycle is the strongest Zeitgeber for the biological clock. People with AD, however, often live in environments with inappropriate photic Zeitgebers. Timed bright light exposure may help to consolidate sleep- and circadian rest/activity rhythm problems in AD, and may be a low-risk alternative to pharmacological treatment.

Objective & Method:

In the present review, experts from several research disciplines summarized the results of twenty-seven light intervention studies which used wrist actigraphy to measure sleep and circadian activity in AD patients.

Results:

Taken together, the findings remain inconclusive with regard to beneficial light effects. However, the considered studies varied substantially with respect to the utilized light intervention, study design, and usage of actigraphy. The paper provides a comprehensive critical discussion of these issues.

Conclusion:

Fusing knowledge across complementary research disciplines has the potential to critically advance our understanding of the biological input of light on health and may contribute to architectural lighting designs in hospitals, as well as our homes and work environments.

Evidence for an Association Between Hearing Impairment and Disrupted Sleep: Scoping Review

Purpose Hearing impairment (HI) is the most common sensory impairment and may negatively impact sleep through reduced auditory input. Factors associated with HI such as anxiety regarding communication in daily life may also adversely impact an individual's sleep. Here, research on the relationship between HI and sleep disruption was catalogued using scoping review methodology. Method A systematic strategy was employed to search various electronic databases. This review is reported according to the Preferred Reporting Items for Systematic Review and Meta-Analyses Scoping Review Extension. Results Sixteen records met inclusion criteria. Studies have investigated sleep in HI as a primary aim in noise-exposed workers or large surveys in older participants. Experimental and quasi-experimental studies report alterations to sleep architecture of potential neuroplastic origins. Studies reporting sleep as a secondary aim generally report poorer sleep in HI participants. Conclusions This scoping review has catalogued evidence that altered or negatively impacted sleep may be associated with HI. Potential confounding factors, mechanisms, and considerations for future research are discussed. Supplemental Material https://doi.org/10.23641/asha.9968369.

Assessing Physical Activity and Sleep in Axial Spondyloarthritis: Measuring the Gap

Patients with axial spondyloarthritis (axSpA) frequently report pain, stiffness, fatigue, and sleep problems, which may lead to impaired physical activity. The majority of reported-on measures evaluating physical activity and sleep disturbance in axSpA are self-reported questionnaires, which can be impacted by patient recall (reporting bias). One objective measure, polysomnography, has been employed to evaluate sleep in patients with axSpA; however, it is an intrusive measure and cannot be used over the long term. More convenient objective measures are therefore needed to allow for the long-term assessment of both sleep and physical activity in patients' daily lives. Wearable technology that utilizes actigraphy is increasingly being used for the objective measurement of physical activity and sleep in various therapy areas, as it is unintrusive and suitable for continuous tracking to allow longitudinal assessment. Actigraphy characterizes sleep disruption as restless movement while sleeping, which is particularly useful when studying conditions such as axSpA in which chronic pain and discomfort due to stiffness may be evident. Studies have also shown that actigraphy can effectively assess the impact of disease on physical activity. More research is needed to establish the usefulness of objective monitoring of sleep and physical activity specifically in axSpA patients over time. This review summarizes the current perspectives on physical activity and sleep quality in patients with axSpA, and the possible role of actigraphy in the future to more accurately evaluate the impact of treatment interventions on sleep and physical activity in axSpA.Funding: Novartis Pharmaceuticals Corporation.Plain Language Summary: Plain language summary available for this article.

Excessive daytime sleepiness with snoring or witnessed apnea is associated with handgrip strength: a population-based study

BACKGROUND

Sarcopenia is emerging as an important public health problem, and evidences have determined that poor sleep is associated with muscle strength, but the potential effects of excessive daytime sleepiness (EDS), snoring and witnessed apnea on handgrip strength have not been evaluated.

AIM

We aimed to examine the association between EDS, snoring, witnessed apnea and muscle strength in an adult population.

DESIGN

Cross-sectional study.

METHODS

This cross-sectional study comprised 19 434 adults. Handgrip strength was measured using a handheld digital dynamometer. EDS was assessed by Epworth Sleepiness Scale, snoring and witnessed apnea during sleep were reported through simple yes/no questions. Analysis of covariance was carried out to determine the association between EDS with snoring or witnessed apnea and muscle strength.

RESULTS

The means (95% confidence interval) for average handgrip strength/body weight (kg/kg) across symptoms categories were 0.396 (0.333-0.472), 0.393 (0.330-0.467), 0.396 (0.333-0.471) and 0.386 (0.325-0.460) (P < 0.0001), respectively. Similar results were observed with maximal handgrip strength/body weight (kg/kg).

CONCLUSIONS

Self-reported EDS accompanied with snoring or apnea is associated with lowest handgrip strength, independently of confounding factors. Whether improvement of EDS, snoring and apnea, can ameliorate age-associated decline in muscle strength warrants further studies.

A hierarchical sequential neural network with feature fusion for sleep staging based on EOG and RR signals

OBJECTIVE

Currently, the automatic sleep staging methods mainly face two problems: the first problem is that although the algorithms which use electroencephalogram (EEG) signals perform well, acquiring EEG signals is complicated and uncomfortable; the second problem is that if the methods utilize physiological signals collected by user-friendly devices, such as cardiorespiratory signals, whose accuracies are hard to be accepted by clinicians, although the employed signals are easy and comfortable to acquire.

APPROACH

To overcome the two issues, an automatic sleep staging method is proposed by developing a hierarchical sequential neural network to process only the electrooculogram (EOG) and R-R interval (RR) signals. The two signals are convenient and comfortable to acquire. The proposed network mainly contains two parts: comprehensive feature learning and sequence learning. The first part extracts hand-crafted features, and network trained features are simultaneously learned by a two-scale network. Then the two kinds of features are fused. The second part utilized a two-flow recurrent neural network (RNN) to learn temporal information between sleep epochs.

MAIN RESULTS

The proposed method was evaluated on 86 subjects from two public databases, the Montreal archive of sleep studies (MASS) and sleep apnea (SA). The proposed method can discriminate five sleep stages with the F1-score of 0.781 and 0.740 for MASS and SA, respectively. And discriminate four stages with the F1-score of 0.858 and 0.802 for MASS and SA, respectively.

SIGNIFICANCE

The proposed method can achieve comparable performance as using EEG signals for sleep staging and have better performance compared to five related state-of-the-art methods. Model analysis displayed that the network can learn effective features and sequence information from EOG and RR signals. In summary, the proposed method is promising to enable new sleep monitoring in a more convenient way while having a good performance on sleep staging.

A Performant Web-Based Visualization, Assessment, and Collaboration Tool for Multidimensional Biosignals

Biosignal-based research is often multidisciplinary and benefits greatly from multi-site collaboration. This requires appropriate tooling that supports collaboration, is easy to use, and is accessible. However, current software tools do not provide the necessary functionality, usability, and ubiquitous availability. The latter is particularly crucial in environments, such as hospitals, which often restrict users' permissions to install software. This paper introduces a new web-based application for interactive biosignal visualization and assessment. A focus has been placed on performance to allow for handling files of any size. The proposed solution can load local and remote files. It parses data locally on the client, and harmonizes channel labels. The data can then be scored, annotated, pseudonymized and uploaded to a clinical data management system for further analysis. The data and all actions can be interactively shared with a second party. This lowers the barrier to quickly visually examine data, collaborate and make informed decisions.

Daily Torpor and Sleep in a Non-human Primate, the Gray Mouse Lemur (Microcebus murinus)

Daily torpor is an energy-saving process that evolved as an extension of non-rapid eye movement (NREM) sleep mechanisms. In many heterothermic species there is a relation between torpor expression and the repartition of the different behavioral states of sleep. Despite the presence of sleep during this period of hypothermia, torpor induces an accumulation of sleep debt which results in a rebound of sleep in mammals. We aimed to investigate the expression of sleep-wake rhythms and delta waves during daily torpor at various ambient temperatures in a non-human primate model, the gray mouse lemur (Microcebus murinus). Cortical activity was measured with telemetric electroencephalography (EEG) recordings in the prefrontal cortex (PFC) during the torpor episode and the next 24 h following hypothermia. Gray mouse lemurs were divided into two groups: the first group was subjected to normal ambient temperatures (25°C) whereas the second group was placed at lower ambient temperatures (10°C). Contrary to normal ambient temperatures, sleep-wake rhythms were maintained during torpor until body temperature (Tb) of the animals reached 21°C. Below this temperature, NREM and REM sleep strongly decreased or were absent whereas the EEG became isoelectric. The different states of sleep were proportional to Tb_min during prior torpor in contrast to active phases. Delta waves increased after torpor but low Tb did not induce greater delta power compared to higher temperatures. Our results showed that Tb was a determining factor for the quality and quantity of sleep. Low Tb might be inconsistent with the recovery function of sleep. Heterothermy caused a sleep debt thus there was a rebound of sleep at the beginning of euthermia to compensate for the lack of sleep.

Feasibility of Single Channel Oximetry for Mass Screening of Obstructive Sleep Apnea

BACKGROUND

The growing awareness for the high prevalence of obstructive sleep apnea (OSA) coupled with the dramatic proportion of undiagnosed individuals motivates the elaboration of a simple but accurate screening test. This study assesses, for the first time, the performance of oximetry combined with demographic information as a screening tool for identifying OSA in a representative (i.e. non-referred) population sample.

METHODS

A polysomnography (PSG) clinical database of 887 individuals from a representative population sample of São Paulo's city (Brazil) was used. Using features derived from the oxygen saturation signal during sleep periods and demographic information, a logistic regression model (termed OxyDOSA) was trained to distinguish between non-OSA and OSA individuals (mild, moderate, and severe). The OxyDOSA model performance was assessed against the PSG-based diagnosis of OSA (AASM 2017) and compared to the NoSAS and STOP-BANG questionnaires.

FINDINGS

The OxyDOSA model had mean AUROC = 0.94 ± 0.02, Se = 0.87 ± 0.04 and Sp = 0.85 ± 0.03. In particular, it did not miss any of the 75 severe OSA individuals. In comparison, the NoSAS questionnaire had AUROC = 0.83 ± 0.03, and missed 23/75 severe OSA individuals. The STOP-BANG had AUROC = 0.77 ± 0.04 and missed 14/75 severe OSA individuals.

INTERPRETATION

We provide strong evidence on a representative population sample that oximetry biomarkers combined with few demographic information, the OxyDOSA model, is an effective screening tool for OSA. Our results suggest that sleep questionnaires should be used with caution for OSA screening as they fail to identify many moderate and even some severe cases. The OxyDOSA model will need to be further validated on data recorded using overnight portable oximetry.

Microvascular cerebral blood flow fluctuations in association with apneas and hypopneas in acute ischemic stroke

In a pilot study on acute ischemic stroke (AIS) patients, unexpected periodic fluctuations in microvascular cerebral blood flow (CBF) had been observed. Motivated by the relative lack of information about the impact of the emergence of breathing disorders in association with stroke on cerebral hemodynamics, we hypothesized that these fluctuations are due to apneic and hypopneic events. A total of 28 patients were screened within the first week after stroke with a pulse oximeter. Five (18%) showed fluctuations of arterial blood oxygen saturation ( ≥ 3 % ) and were included in the study. Near-infrared diffuse correlation spectroscopy (DCS) was utilized bilaterally to measure the frontal lobe CBF alongside respiratory polygraphy. Biphasic CBF fluctuations were observed with a bilateral increase of 27.1 % ± 17.7 % and 29.0 % ± 17.4 % for the ipsilesional and contralesional hemispheres, respectively, and a decrease of - 19.3 % ± 9.1 % and - 21.0 % ± 8.9 % for the ipsilesional and contralesional hemispheres, respectively. The polygraph revealed that, in general, the fluctuations were associated with apneic and hypopneic events. This study motivates us to investigate whether the impact of altered respiratory patterns on cerebral hemodynamics can be detrimental in AIS patients.

Automated sleep stage classification based on tracheal body sound and actigraphy

The current gold standard for assessment of most sleep disorders is the in-laboratory polysomnography (PSG). This approach produces high costs and inconveniences for the patients. An accessible and simple preliminary screening method to diagnose the most common sleep disorders and to decide whether a PSG is necessary or not is therefore desirable. A minimalistic type-4 monitoring system which utilized tracheal body sound and actigraphy to accurately diagnose the obstructive sleep apnea syndrome was previously developed. To further improve the diagnostic ability of said system, this study aims to examine if it is possible to perform automated sleep staging utilizing body sound to extract cardiorespiratory features and actigraphy to extract movement features.

A linear discriminant classifier based on those features was used for automated sleep staging using the type-4 sleep monitor. For validation 53 subjects underwent a full-night screening at Ulm University Hospital using the developed sleep monitor in addition to polysomnography. To assess sleep stages from PSG, a trained technician manually evaluated EEG, EOG, and EMG recordings.

The classifier reached 86.9% accuracy and a Kappa of 0.69 for sleep/wake classification, 76.3% accuracy and a Kappa of 0.42 for Wake/REM/NREM classification, and 56.5% accuracy and a Kappa of 0.36 for Wake/REM/light sleep/deep sleep classification. For the calculation of sleep efficiency (SE), a coefficient of determination r² of 0.78 is reached. Additionally, subjects were classified into groups of SEs (SE≥40%, SE≥60% and SE≥80%). A Cohen’s Kappa >0.61 was reached for all groups, which is considered as substantial agreement.

The presented method provides satisfactory performance in sleep/wake and wake/REM/NREM sleep staging while maintaining a simple setup and offering high comfort. This minimalistic approach may address the need for a simple yet reliable preliminary sleep screening in an ambulatory setting.