Sleep stage classification with ECG and respiratory effort

REM sleep breathing: Insights beyond conventional respiratory metrics

Breathing and sleep state are tightly linked. The traditional approach to evaluation of breathing in rapid eye movement sleep has been to focus on apneas and hypopneas, and associated hypoxia or hypercapnia. However, rapid eye movement sleep breathing offers novel insights into sleep physiology and pathology, secondary to complex interactions of rapid eye movement state and cardiorespiratory biology. In this review, morphological analysis of clinical polysomnogram data to assess respiratory patterns and associations across a range of health and disease is presented. There are several relatively unique insights that may be evident by assessment of breathing during rapid eye movement sleep. These include the original discovery of rapid eye movement sleep and scoring of neonatal sleep, control of breathing in rapid eye movement sleep, rapid eye movement sleep homeostasis, sleep apnea endotyping and pharmacotherapy, rapid eye movement sleep stability, non-electroencephalogram sleep staging, influences on cataplexy, mimics of rapid eye movement behaviour disorder, a reflection of autonomic health, and insights into cardiac arrhythmogenesis. In summary, there is rich clinically actionable information beyond sleep apnea encoded in the respiratory patterns of rapid eye movement sleep.

Characterising the motion and cardiorespiratory interaction of preterm infants can improve the classification of their sleep state

AIM

This study aimed to classify quiet sleep, active sleep and wake states in preterm infants by analysing cardiorespiratory signals obtained from routine patient monitors.

METHODS

We studied eight preterm infants, with an average postmenstrual age of 32.3 ± 2.4 weeks, in a neonatal intensive care unit in the Netherlands. Electrocardiography and chest impedance respiratory signals were recorded. After filtering and R-peak detection, cardiorespiratory features and motion and cardiorespiratory interaction features were extracted, based on previous research. An extremely randomised trees algorithm was used for classification and performance was evaluated using leave-one-patient-out cross-validation and Cohen's kappa coefficient.

RESULTS

A sleep expert annotated 4731 30-second epochs (39.4 h) and active sleep, quiet sleep and wake accounted for 73.3%, 12.6% and 14.1% respectively. Using all features, and the extremely randomised trees algorithm, the binary discrimination between active and quiet sleep was better than between other states. Incorporating motion and cardiorespiratory interaction features improved the classification of all sleep states (kappa 0.38 ± 0.09) than analyses without these features (kappa 0.31 ± 0.11).

CONCLUSION

Cardiorespiratory interactions contributed to detecting quiet sleep and motion features contributed to detecting wake states. This combination improved the automated classifications of sleep states.

An automatic method using MFCC features for sleep stage classification

Sleep stage classification is a necessary step for diagnosing sleep disorders. Generally, experts use traditional methods based on every 30 seconds (s) of the biological signals, such as electrooculograms (EOGs), electrocardiograms (ECGs), electromyograms (EMGs), and electroencephalograms (EEGs), to classify sleep stages. Recently, various state-of-the-art approaches based on a deep learning model have been demonstrated to have efficient and accurate outcomes in sleep stage classification. In this paper, a novel deep convolutional neural network (CNN) combined with a long short-time memory (LSTM) model is proposed for sleep scoring tasks. A key frequency domain feature named Mel-frequency Cepstral Coefficient (MFCC) is extracted from EEG and EMG signals. The proposed method can learn features from frequency domains on different bio-signal channels. It firstly extracts the MFCC features from multi-channel signals, and then inputs them to several convolutional layers and an LSTM layer. Secondly, the learned representations are fed to a fully connected layer and a softmax classifier for sleep stage classification. The experiments are conducted on two widely used sleep datasets, Sleep Heart Health Study (SHHS) and Vincent's University Hospital/University College Dublin Sleep Apnoea (UCDDB) to test the effectiveness of the method. The results of this study indicate that the model can perform well in the classification of sleep stages using the features of the 2-dimensional (2D) MFCC feature. The advantage of using the feature is that it can be used to input a two-dimensional data stream, which can be used to retain information about each sleep stage. Using 2D data streams can reduce the time it takes to retrieve the data from the one-dimensional stream. Another advantage of this method is that it eliminates the need for deep layers, which can help improve the performance of the model. For instance, by reducing the number of layers, our seven layers of the model structure takes around 400 s to train and test 100 subjects in the SHHS1 dataset. Its best accuracy and Cohen's kappa are 82.35% and 0.75 for the SHHS dataset, and 73.07% and 0.63 for the UCDDB dataset, respectively.

Review and perspective on sleep-disordered breathing research and translation to clinics

Sleep-disordered breathing, ranging from habitual snoring to severe obstructive sleep apnea, is a prevalent public health issue. Despite rising interest in sleep and awareness of sleep disorders, sleep research and diagnostic practices still rely on outdated metrics and laborious methods reducing the diagnostic capacity and preventing timely diagnosis and treatment. Consequently, a significant portion of individuals affected by sleep-disordered breathing remain undiagnosed or are misdiagnosed. Taking advantage of state-of-the-art scientific, technological, and computational advances could be an effective way to optimize the diagnostic and treatment pathways. We discuss state-of-the-art multidisciplinary research, review the shortcomings in the current practices of SDB diagnosis and management in adult populations, and provide possible future directions. We critically review the opportunities for modern data analysis methods and machine learning to combine multimodal information, provide a perspective on the pitfalls of big data analysis, and discuss approaches for developing analysis strategies that overcome current limitations. We argue that large-scale and multidisciplinary collaborative efforts based on clinical, scientific, and technical knowledge and rigorous clinical validation and implementation of the outcomes in practice are needed to move the research of sleep-disordered breathing forward, thus increasing the quality of diagnostics and treatment.

Development of generalizable automatic sleep staging using heart rate and movement based on large databases

Purpose

With the advancement of deep neural networks in biosignals processing, the performance of automatic sleep staging algorithms has improved significantly. However, sleep staging using only non-electroencephalogram features has not been as successful, especially following the current American Association of Sleep Medicine (AASM) standards. This study presents a fine-tuning based approach to widely generalizable automatic sleep staging using heart rate and movement features trained and validated on large databases of polysomnography.

Methods

A deep neural network is used to predict sleep stages using heart rate and movement features. The model is optimized on a dataset of 8731 nights of polysomnography recordings labeled using the Rechtschaffen & Kales scoring system, and fine-tuned to a smaller dataset of 1641 AASM-labeled recordings. The model prior to and after fine-tuning is validated on two AASM-labeled external datasets totaling 1183 recordings. In order to measure the performance of the model, the output of the optimized model is compared to reference expert-labeled sleep stages using accuracy and Cohen's κ as key metrics.

Results

The fine-tuned model showed accuracy of 76.6% with Cohen's κ of 0.606 in one of the external validation datasets, outperforming a previously reported result, and showed accuracy of 81.0% with Cohen's κ of 0.673 in another external validation dataset.

Conclusion

These results indicate that the proposed model is generalizable and effective in predicting sleep stages using features which can be extracted from non-contact sleep monitors. This holds valuable implications for future development of home sleep evaluation systems.

Automatic sleep-stage classification of heart rate and actigraphy data using deep and transfer learning approaches

Manual sleep-stage scoring based on full-night polysomnography data recorded in a sleep lab has been the gold standard of clinical sleep medicine. This costly and time-consuming approach is unfit for long-term studies as well as assessment of sleep on a population level. With the vast amount of physiological data becoming available from wrist-worn devices, deep learning techniques provide an opportunity for fast and reliable automatic sleep-stage classification tasks. However, training a deep neural network requires large annotated sleep databases, which are not available for long-term epidemiological studies. In this paper, we introduce an end-to-end temporal convolutional neural network able to automatically score sleep stages from raw heartbeat RR interval (RRI) and wrist actigraphy data. Moreover, a transfer learning approach enables the training of the network on a large public database (Sleep Heart Health Study, SHHS) and its subsequent application to a much smaller database recorded by a wristband device. The transfer learning significantly shortens training time and improves sleep-scoring accuracy from 68.9% to 73.8% and inter-rater reliability (Cohen's kappa) from 0.51 to 0.59. We also found that for the SHHS database, automatic sleep-scoring accuracy using deep learning shows a logarithmic relationship with the training size. Although deep learning approaches for automatic sleep scoring are not yet comparable to the inter-rater reliability among sleep technicians, performance is expected to significantly improve in the near future when more large public databases become available. We anticipate those deep learning techniques, when combined with our transfer learning approach, will leverage automatic sleep scoring of physiological data from wearable devices and enable the investigation of sleep in large cohort studies.

Single-Channel Ecg-Based Sleep Stage Classification With End-To-End Trainable Deep Neural Networks

The demand for automatic sleep stage classification using easily obtainable signals like electrocardiograms (ECGs) is rising due to the growing number of sleep disorder cases. Our study examined the potential of using single-channel ECG signals for user-friendly automatic sleep stage classification. Unlike previous studies that relied on manual features such as heart rate and variability, we propose using fully neural network-based features. The proposed model uses a ContextNet-based feature encoder applied to the ECG spectrogram, and a Transformer model to capture the temporal properties of sleep cycles over the course of the night.

Automated sleep staging in people with intellectual disabilities using heart rate and respiration variability

BACKGROUND

People with intellectual disabilities (ID) have a higher risk of sleep disorders. Polysomnography (PSG) remains the diagnostic gold standard in sleep medicine. However, PSG in people with ID can be challenging, as sensors can be burdensome and have a negative influence on sleep. Alternative methods of assessing sleep have been proposed that could potentially transfer to less obtrusive monitoring devices. The goal of this study was to investigate whether analysis of heart rate variability and respiration variability is suitable for the automatic scoring of sleep stages in sleep-disordered people with ID.

METHODS

Manually scored sleep stages in PSGs of 73 people with ID (borderline to profound) were compared with the scoring of sleep stages by the CardioRespiratory Sleep Staging (CReSS) algorithm. CReSS uses cardiac and/or respiratory input to score the different sleep stages. Performance of the algorithm was analysed using input from electrocardiogram (ECG), respiratory effort and a combination of both. Agreement was determined by means of epoch-per-epoch Cohen's kappa coefficient. The influence of demographics, comorbidities and potential manual scoring difficulties (based on comments in the PSG report) was explored.

RESULTS

The use of CReSS with combination of both ECG and respiratory effort provided the best agreement in scoring sleep and wake when compared with manually scored PSG (PSG versus ECG = kappa 0.56, PSG versus respiratory effort = kappa 0.53 and PSG versus both = kappa 0.62). Presence of epilepsy or difficulties in manually scoring sleep stages negatively influenced agreement significantly, but nevertheless, performance remained acceptable. In people with ID without epilepsy, the average kappa approximated that of the general population with sleep disorders.

CONCLUSIONS

Using analysis of heart rate and respiration variability, sleep stages can be estimated in people with ID. This could in the future lead to less obtrusive measurements of sleep using, for example, wearables, more suitable to this population.

Validating Force Sensitive Resistor Strip Sensors for Cardiorespiratory Measurement during Sleep: A Preliminary Study

Sleep disorders can impact daily life, affecting physical, emotional, and cognitive well-being. Due to the time-consuming, highly obtrusive, and expensive nature of using the standard approaches such as polysomnography, it is of great interest to develop a noninvasive and unobtrusive in-home sleep monitoring system that can reliably and accurately measure cardiorespiratory parameters while causing minimal discomfort to the user's sleep. We developed a low-cost Out of Center Sleep Testing (OCST) system with low complexity to measure cardiorespiratory parameters. We tested and validated two force-sensitive resistor strip sensors under the bed mattress covering the thoracic and abdominal regions. Twenty subjects were recruited, including 12 males and 8 females. The ballistocardiogram signal was processed using the 4th smooth level of the discrete wavelet transform and the 2nd order of the Butterworth bandpass filter to measure the heart rate and respiration rate, respectively. We reached a total error (concerning the reference sensors) of 3.24 beats per minute and 2.32 rates for heart rate and respiration rate, respectively. For males and females, heart rate errors were 3.47 and 2.68, and respiration rate errors were 2.32 and 2.33, respectively. We developed and verified the reliability and applicability of the system. It showed a minor dependency on sleeping positions, one of the major cumbersome sleep measurements. We identified the sensor under the thoracic region as the optimal configuration for cardiorespiratory measurement. Although testing the system with healthy subjects and regular patterns of cardiorespiratory parameters showed promising results, further investigation is required with the bandwidth frequency and validation of the system with larger groups of subjects, including patients.

Sleep stage classification in EEG signals using the clustering approach based probability distribution features coupled with classification algorithms

Sleep scoring is one of the primary tasks for the classification of sleep stages in Electroencephalogram (EEG) signals. Manual visual scoring of sleep stages is time-consuming as well as being dependent on the experience of a highly qualified sleep expert. This paper aims to address these issues by developing a new method to automatically classify sleep stages in EEG signals. In this research, a robust method has been presented based on the clustering approach, coupled with probability distribution features, to identify six sleep stages with the use of EEG signals. Using this method, each 30-second EEG signal is firstly segmented into small epochs and then each epoch is divided into 60 sub-segments. Each sub-segment is decomposed into five levels by using a discrete wavelet transform (DWT) to obtain the approximation and detailed coefficient. The wavelet coefficient of each level is clustered using the k-means algorithm. Subsequently, features are extracted based on the probability distribution for each wavelet coefficient. The extracted features then are forwarded to the least squares support vector machine classifier (LS-SVM) to identify sleep stages. Comparisons with several existing methods are also made in this study. The proposed method for the classification of the sleep stages achieves an average accuracy rate of 97.4%. It can be an effective tool for sleep stages classification and can be useful for doctors and neurologists for diagnosing sleep disorders.

Extraction of cardiac-related signals from a suprasternal pressure sensor during sleep

Objective.The accurate detection of respiratory effort during polysomnography is a critical element in the diagnosis of sleep-disordered breathing conditions such as sleep apnea. Unfortunately, the sensors currently used to estimate respiratory effort are either indirect and ignore upper airway dynamics or are too obtrusive for patients. One promising alternative is the suprasternal notch pressure (SSP) sensor: a small element placed on the skin in the notch above the sternum within an airtight capsule that detects pressure swings in the trachea. Besides providing information on respiratory effort, the sensor is sensitive to small cardiac oscillations caused by pressure perturbations in the carotid arteries or the trachea. While current clinical research considers these as redundant noise, they may contain physiologically relevant information.Approach.We propose a method to separate the signal generated by cardiac activity from the one caused by breathing activity. Using only information available from the SSP sensor, we estimate the heart rate and track its variations, then use a set of tuned filters to process the original signal in the frequency domain and reconstruct the cardiac signal. We also include an overview of the technical and physiological factors that may affect the quality of heart rate estimation. The output of our method is then used as a reference to remove the cardiac signal from the original SSP pressure signal, to also optimize the assessment of respiratory activity. We provide a qualitative comparison against methods based on filters with fixed frequency cutoffs.Main results.In comparison with electrocardiography (ECG)-derived heart rate, we achieve an agreement error of 0.06 ± 5.09 bpm, with minimal bias drift across the measurement range, and only 6.36% of the estimates larger than 10 bpm.Significance.Together with qualitative improvements in the characterization of respiratory effort, this opens the development of novel portable clinical devices for the detection and assessment of sleep disordered breathing.

Effects of Ballistocardiogram Peak Detection Jitters on the Quality of Heart Rate Variability Features: A Simulation-Based Case Study in the Context of Sleep Staging

Heart rate variability (HRV) features support several clinical applications, including sleep staging, and ballistocardiograms (BCGs) can be used to unobtrusively estimate these features. Electrocardiography is the traditional clinical standard for HRV estimation, but BCGs and electrocardiograms (ECGs) yield different estimates for heartbeat intervals (HBIs), leading to differences in calculated HRV parameters. This study examines the viability of using BCG-based HRV features for sleep staging by quantifying the impact of these timing differences on the resulting parameters of interest. We introduced a range of synthetic time offsets to simulate the differences between BCG- and ECG-based heartbeat intervals, and the resulting HRV features are used to perform sleep staging. Subsequently, we draw a relationship between the mean absolute error in HBIs and the resulting sleep-staging performances. We also extend our previous work in heartbeat interval identification algorithms to demonstrate that our simulated timing jitters are close representatives of errors between heartbeat interval measurements. This work indicates that BCG-based sleep staging can produce accuracies comparable to ECG-based techniques such that at an HBI error range of up to 60 ms, the sleep-scoring error could increase from 17% to 25% based on one of the scenarios we examined.

The Virtual Sleep Lab-A Novel Method for Accurate Four-Class Sleep Staging Using Heart-Rate Variability from Low-Cost Wearables

Sleep staging based on polysomnography (PSG) performed by human experts is the de facto "gold standard" for the objective measurement of sleep. PSG and manual sleep staging is, however, personnel-intensive and time-consuming and it is thus impractical to monitor a person's sleep architecture over extended periods. Here, we present a novel, low-cost, automatized, deep learning alternative to PSG sleep staging that provides a reliable epoch-by-epoch four-class sleep staging approach (Wake, Light [N1 + N2], Deep, REM) based solely on inter-beat-interval (IBI) data. Having trained a multi-resolution convolutional neural network (MCNN) on the IBIs of 8898 full-night manually sleep-staged recordings, we tested the MCNN on sleep classification using the IBIs of two low-cost (<EUR 100) consumer wearables: an optical heart rate sensor (VS) and a breast belt (H10), both produced by POLAR®. The overall classification accuracy reached levels comparable to expert inter-rater reliability for both devices (VS: 81%, κ = 0.69; H10: 80.3%, κ = 0.69). In addition, we used the H10 and recorded daily ECG data from 49 participants with sleep complaints over the course of a digital CBT-I-based sleep training program implemented in the App NUKKUAA™. As proof of principle, we classified the IBIs extracted from H10 using the MCNN over the course of the training program and captured sleep-related changes. At the end of the program, participants reported significant improvements in subjective sleep quality and sleep onset latency. Similarly, objective sleep onset latency showed a trend toward improvement. Weekly sleep onset latency, wake time during sleep, and total sleep time also correlated significantly with the subjective reports. The combination of state-of-the-art machine learning with suitable wearables allows continuous and accurate monitoring of sleep in naturalistic settings with profound implications for answering basic and clinical research questions.

A novel automated robust dual-channel EEG-based sleep scoring system using optimal half-band pair linear-phase biorthogonal wavelet filter bank

Nowadays, the hectic work life of people has led to sleep deprivation. This may further result in sleep-related disorders and adverse physiological conditions. Therefore, sleep study has become an active research area. Sleep scoring is crucial for detecting sleep-related disorders like sleep apnea, insomnia, narcolepsy, periodic leg movement (PLM), and restless leg syndrome (RLS). Sleep is conventionally monitored in a sleep laboratory using polysomnography (PSG) which is the recording of various physiological signals. The traditional sleep stage scoring (SSG) done by professional sleep scorers is a tedious, strenuous, and time-consuming process as it is manual. Hence, developing a machine-learning model for automatic SSG is essential. In this study, we propose an automated SSG approach based on the biorthogonal wavelet filter bank's (BWFB) novel least squares (LS) design. We have utilized a huge Wisconsin sleep cohort (WSC) database in this study. The proposed study is a pioneering work on automatic sleep stage classification using the WSC database, which includes good sleepers and patients suffering from various sleep-related disorders, including apnea, insomnia, hypertension, diabetes, and asthma. To investigate the generalization of the proposed system, we evaluated the proposed model with the following publicly available databases: cyclic alternating pattern (CAP), sleep EDF, ISRUC, MIT-BIH, and the sleep apnea database from St. Vincent's University. This study uses only two unipolar EEG channels, namely O1-M2 and C3-M2, for the scoring. The Hjorth parameters (HP) are extracted from the wavelet subbands (SBS) that are obtained from the optimal BWFB. To classify sleep stages, the HP features are fed to several supervised machine learning classifiers. 12 different datasets have been created to develop a robust model. A total of 12 classification tasks (CT) have been conducted employing various classification algorithms. Our developed model achieved the best accuracy of 83.2% and Cohen's Kappa of 0.7345 to reliably distinguish five sleep stages, using an ensemble bagged tree classifier with 10-fold cross-validation using WSC data. We also observed that our system is either better or competitive with existing state-of-art systems when we tested with the above-mentioned five databases other than WSC. This method yielded promising results using only two EEG channels using a huge WSC database. Our approach is simple and hence, the developed model can be installed in home-based clinical systems and wearable devices for sleep scoring.

An automatic sleep-scoring system in elderly women with osteoporosis fractures using frequency localized finite orthogonal quadrature Fejer Korovkin kernels

Healthy sleep signifies a good physical and mental state of the body. However, factors such as inappropriate work schedules, medical complications, and others can make it difficult to get enough sleep, leading to various sleep disorders. The identification of these disorders requires sleep stage classification. Visual evaluation of sleep stages is time intensive, placing a significant strain on sleep experts and prone to human errors. As a result, it is crucial to develop machine learning algorithms to score sleep stages to acquire an accurate diagnosis. Hence, a new methodology for automated sleep stage classification is suggested using machine learning and filtering electroencephalogram (EEG) signals. The national sleep research resource's (NSRR) study of osteoporotic fractures (SOF) dataset comprising 453 subjects' polysomnograph (PSG) data is used in this study. Only two unipolar EEG derivations C4-A1 and C3-A2 are employed individually and jointly in this work. The EEG signals are decomposed into sub-bands using a frequency-localized finite orthogonal quadrature Fejer Korovkin wavelet filter bank. The wavelet-based entropy features are extracted from sub-bands. Subsequently, extracted features are classified using machine learning techniques. Our developed model obtained the highest classification accuracy of 81.3%, using an ensembled bagged trees classifier with a 10-fold cross-validation method and Cohen's Kappa coefficient of 0.72. The proposed model is accurate, dependable, and easy to implement and can be employed as an alternative to a PSG-based system at home with minimal resources. It is also ready to be tested on other EEG data to evaluate the sleep stages of healthy and unhealthy subjects.

Sleep Quality Evaluation Based on Single-Lead Wearable Cardiac Cycle Acquisition Device

In clinical conditions, polysomnography (PSG) is regarded as the "golden standard" for detecting sleep disease and offering a reference of objective sleep quality. For healthy adults, scores from sleep questionnaires are more reliable than other methods in obtaining knowledge of subjective sleep quality. In practice, the need to simplify PSG to obtain subjective sleep quality by recording a few channels of physiological signals such as single-lead electrocardiogram (ECG) or photoplethysmography (PPG) signal is still very urgent. This study provided a two-step method to differentiate sleep quality into "good sleep" and "poor sleep" based on the single-lead wearable cardiac cycle data, with the comparison of the subjective sleep questionnaire score. First, heart rate variability (HRV) features and ECG-derived respiration features were extracted to construct a sleep staging model (wakefulness (W), rapid eye movement (REM), light sleep (N1&N2) and deep sleep (N3)) using the multi-classifier fusion method. Then, features extracted from the sleep staging results were used to construct a sleep quality evaluation model, i.e., classifying the sleep quality as good and poor. The accuracy of the sleep staging model, tested on the international public database, was 0.661 and 0.659 in Cardiology Challenge 2018 training database and Sleep Heart Health Study Visit 1 database, respectively. The accuracy of the sleep quality evaluation model was 0.786 for our recording subjects, with an average F1-score of 0.771. The proposed sleep staging model and sleep quality evaluation model only requires one channel of wearable cardiac cycle signal. It is very easy to transplant to portable devices, which facilitates daily sleep health monitoring.

An automated heart rate-based algorithm for sleep stage classification: Validation using conventional polysomnography and an innovative wearable electrocardiogram device

Background

The rapid advancement in wearable solutions to monitor and score sleep staging has enabled monitoring outside of the conventional clinical settings. However, most of the devices and algorithms lack extensive and independent validation, a fundamental step to ensure robustness, stability, and replicability of the results beyond the training and testing phases. These systems are thought not to be feasible and reliable alternatives to the gold standard, polysomnography (PSG).

Materials and methods

This validation study highlights the accuracy and precision of the proposed heart rate (HR)-based deep-learning algorithm for sleep staging. The illustrated solution can perform classification at 2-levels (Wake; Sleep), 3-levels (Wake; NREM; REM) or 4- levels (Wake; Light; Deep; REM) in 30-s epochs. The algorithm was validated using an open-source dataset of PSG recordings (Physionet CinC dataset, n = 994 participants, 994 recordings) and a proprietary dataset of ECG recordings (Z3Pulse, n = 52 participants, 112 recordings) collected with a chest-worn, wireless sensor and simultaneous PSG collection using SOMNOtouch.

Results

We evaluated the performance of the models in both datasets in terms of Accuracy (A), Cohen's kappa (K), Sensitivity (SE), Specificity (SP), Positive Predictive Value (PPV), and Negative Predicted Value (NPV). In the CinC dataset, the highest value of accuracy was achieved by the 2-levels model (0.8797), while the 3-levels model obtained the best value of K (0.6025). The 4-levels model obtained the lowest SE (0.3812) and the highest SP (0.9744) for the classification of Deep sleep segments. AHI and biological sex did not affect scoring, while a significant decrease of performance by age was reported across the models. In the Z3Pulse dataset, the highest value of accuracy was achieved by the 2-levels model (0.8812), whereas the 3-levels model obtained the best value of K (0.611). For classification of the sleep states, the lowest SE (0.6163) and the highest SP (0.9606) were obtained for the classification of Deep sleep segment.

Conclusion

The results of the validation procedure demonstrated the feasibility of accurate HR-based sleep staging. The combination of the proposed sleep staging algorithm with an inexpensive HR device, provides a cost-effective and non-invasive solution deployable in the home environment and robust across age, sex, and AHI scores.

Non-Contact Supervision of COVID-19 Breathing Behaviour With FMCW Radar and Stacked Ensemble Learning Model in Real-Time

A respiratory disorder that attacks COVID-19 patients requires intensive supervision of medical practitioners during the isolation period. A non-contact monitoring device will be a suitable solution for reducing the spread risk of the virus while monitoring the COVID-19 patient. This study uses Frequency-Modulated Continuous Wave (FMCW) radar and Machine Learning (ML) to obtain respiratory information and analyze respiratory signals, respectively. Multiple subjects in a room can be detected simultaneously by calculating the Angle of Arrival (AoA) of the received signal and utilizing the Multiple Input Multiple Output (MIMO) of FMCW radar. Fast Fourier Transform (FFT) and some signal processing are implemented to obtain a breathing waveform. ML helps the system to analyze the respiratory signals automatically. This paper also compares the performance of several ML algorithms such as Multinomial Logistic Regression (MLR), Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), eXtreme Gradient Boosting (XGB), Light Gradient Boosting Machine (LGBM), CatBoosting (CB) Classifier, Multilayer Perceptron (MLP), and three proposed stacked ensemble models, namely Stacked Ensemble Classifier (SEC), Boosting Tree-based Stacked Classifier (BTSC), and Neural Stacked Ensemble Model (NSEM) to obtain the best ML model. The results show that the NSEM algorithm achieves the best performance with 97.1% accuracy. In the real-time implementation, the system could simultaneously detect several objects with different breathing characteristics and classify the respiratory signals into five different classes.

Long Coronavirus Infection is Associated with Significant Sleep Disturbances as Detected by Wearable Health Devices

Background

Patients with COVID-19 have increased sleep disturbances and decreased sleep quality during and after the infection. The current published literature focuses mainly on qualitative analyses based on surveys and subjective measurements rather than quantitative data.

Objective

In this paper, we assessed the long-term effects of COVID-19 through sleep patterns from continuous signals collected via wearable wristbands.

Methods

Patients with a history of COVID-19 were compared to a control arm of individuals who never had COVID-19. Baseline demographics were collected for each subject. Linear correlations among the mean duration of each sleep phase and the mean daily biometrics were performed. The average duration for each subject’s total sleep time and sleep phases per night was calculated and compared between the 2 groups.

Results

This study includes 122 patients with COVID-19 and 588 controls (N=710). Total sleep time was positively correlated with respiratory rate (RR) and oxygen saturation (SpO₂). Increased awake sleep phase was correlated with increased heart rate, decreased RR, heart rate variability (HRV), and SpO₂. Increased light sleep time was correlated with increased RR and SpO₂ in the group with COVID-19. Deep sleep duration was correlated with decreased heart rate as well as increased RR and SpO₂. When comparing different sleep phases, patients with long COVID-19 had decreased light sleep (244, SD 67 vs 258, SD 67; P=.003) and decreased deep sleep time (123, SD 66 vs 128, SD 58; P=.02).

Conclusions

Regardless of the demographic background and symptom levels, patients with a history of COVID-19 infection demonstrated altered sleep architecture when compared to matched controls. The sleep of patients with COVID-19 was characterized by decreased total sleep and deep sleep.

Objective sleep assessments for healthy people in environmental research: A literature review

To date, although many studies had focused on the impact of environmental factors on sleep, how to choose the proper assessment method for objective sleep quality was often ignored, especially for healthy subjects in bedroom environment. In order to provide methodological guidance for future research, this paper reviewed the assessments of objective sleep quality applied in environmental researches, compared them from the perspective of accuracy and interference, and statistically analyzed the impact of experimental type and subjects' information on method selection. The review results showed that, in contrast to polysomnography (PSG), the accuracy of actigraphy (ACT), respiratory monitoring-oxygen saturation monitoring (RM-OSM), and electrocardiograph (ECG) could reach up to 97%, 80.38%, and 79.95%, respectively. In terms of sleep staging, PSG and ECG performed the best, ACT the second, and RM-OSM the worst; as compared to single methods, mix methods were more accurate and better at sleep staging. PSG interfered with sleep a great deal, while ECG and ACT could be non-contact, and thus, the least interference with sleep was present. The type of experiment significantly influenced the choice of assessment method (p < 0.001), 85.3% of researchers chose PSG in laboratory study while 82.5% ACT in field study; moreover, PSG was often used in a relatively small number of young subjects, while ACT had a wide applicable population. In general, researchers need to pay more attention at selection of assessments in future studies, and this review can be used as a reliable reference for experimental design.

Interbeat interval-based sleep staging: work in progress toward real-time implementation

Objective. Cardiac activity changes during sleep enable real-time sleep staging. We developed a deep neural network (DNN) to detect sleep stages using interbeat intervals (IBIs) extracted from electrocardiogram signals.Approach. Data from healthy and apnea subjects were used for training and validation; 2 additional datasets (healthy and sleep disorders subjects) were used for testing. R-peak detection was used to determine IBIs before resampling at 2 Hz; the resulting signal was segmented into 150 s windows (30 s shift). DNN output approximated the probabilities of a window belonging to light, deep, REM, or wake stages. Cohen's Kappa, accuracy, and sensitivity/specificity per stage were determined, and Kappa was optimized using thresholds on probability ratios for each stage versus light sleep.Main results. Mean (SD) Kappa and accuracy for 4 sleep stages were 0.44 (0.09) and 0.65 (0.07), respectively, in healthy subjects. For 3 sleep stages (light+deep, REM, and wake), Kappa and accuracy were 0.52 (0.12) and 0.76 (0.07), respectively. Algorithm performance on data from subjects with REM behavior disorder or periodic limb movement disorder was significantly worse, with Kappa of 0.24 (0.09) and 0.36 (0.12), respectively. Average processing time by an ARM microprocessor for a 300-sample window was 19.2 ms.Significance. IBIs can be obtained from a variety of cardiac signals, including electrocardiogram, photoplethysmography, and ballistocardiography. The DNN algorithm presented is 3 orders of magnitude smaller compared with state-of-the-art algorithms and was developed to perform real-time, IBI-based sleep staging. With high specificity and moderate sensitivity for deep and REM sleep, small footprint, and causal processing, this algorithm may be used across different platforms to perform real-time sleep staging and direct intervention strategies.Novelty & Significance(92/100 words) This article describes the development and testing of a deep neural network-based algorithm to detect sleep stages using interbeat intervals, which can be obtained from a variety of cardiac signals including photoplethysmography, electrocardiogram, and ballistocardiography. Based on the interbeat intervals identified in electrocardiogram signals, the algorithm architecture included a group of convolution layers and a group of long short-term memory layers. With its small footprint, fast processing time, high specificity and good sensitivity for deep and REM sleep, this algorithm may provide a good option for real-time sleep staging to direct interventions.

The Home-Based Sleep Laboratory

Sleep disturbances are prevalent in neurodegenerative diseases in general, and in Parkinson's disease (PD) in particular. Recent evidence points to the clinical value of sleep in disease progression and improving quality of life. Therefore, monitoring sleep quality in an ongoing manner at the convenience of one's home has the potential to improve clinical research and to contribute to significantly better personalized treatment. Further, precise mapping of sleep patterns of each patient can contribute to a better understanding of the disease, its progression and the appropriate medical treatment. Here we review selective, state-of-the-art, home-based devices for assessing sleep and sleep related disorders. We highlight the large potential as well as the main challenges. In particular, we discuss medical validity, standardization and regulatory concerns that currently impede widespread clinical adoption of existing devices. Finally, we propose a roadmap with the technological and scientific steps that are required to impact PD research and treatment.

Automated Scoring of Sleep and Associated Events

Conventionally, sleep and associated events are scored visually by trained technologists according to the rules summarized in the American Academy of Sleep Medicine Manual. Since its first publication in 2007, the manual was continuously updated; the most recent version as of this writing was published in 2020. Human expert scoring is considered as gold standard, even though there is increasing evidence of limited interrater reliability between human scorers. Significant advances in machine learning have resulted in powerful methods for addressing complex classification problems such as automated scoring of sleep and associated events. Evidence is increasing that these autoscoring systems deliver performance comparable to manual scoring and offer several advantages to visual scoring: (1) avoidance of the rather expensive, time-consuming, and difficult visual scoring task that can be performed only by well-trained and experienced human scorers, (2) attainment of consistent scoring results, and (3) proposition of added value such as scoring in real time, sleep stage probabilities per epoch (hypnodensity), estimates of signal quality and sleep/wake-related features, identifications of periods with clinically relevant ambiguities (confidence trends), configurable sensitivity and rule settings, as well as cardiorespiratory sleep staging for home sleep apnea testing. This chapter describes the development of autoscoring systems since the first attempts in the 1970s up to the most recent solutions based on deep neural network approaches which achieve an accuracy that allows to use the autoscoring results directly for review and interpretation by a physician.

Sleep Stage Classification Based on Multi-Centers: Comparison Between Different Ages, Mental Health Conditions and Acquisition Devices

PURPOSE

To investigate the general sleep stage classification performance of deep learning networks, three datasets, across different age groups, mental health conditions, and acquisition devices, comprising adults (SHHS) and children without mental health conditions (CCSHS), and subjects with mental health conditions (XJ), were included in this study.

METHODS

A long short-term memory (LSTM) network was used to evaluate the effect of different ages, mental health conditions, and acquisition devices on the sleep stage classification performance and the general performance.

RESULTS

Results showed that the age and different mental health conditions may affect the sleep stage classification performance of the network. The same acquisition device using different parameters may not have an obvious effect on the classification performance. When using a single dataset and two datasets for training, the network performed better only on the training dataset. When training was conducted with three datasets, the network performed well for all datasets with a Cohen's Kappa of 0.8192 and 0.8472 for the SHHS and CCSHS, respectively, but performed relatively worse (0.6491) for the XJ, which indicated the complexity effect of different mental health conditions on the sleep stage classification task. Moreover, the performance of the network trained using three datasets was similar for each dataset to that of the network trained using a single dataset and tested on the same dataset.

CONCLUSION

These results suggested that when more datasets across different age groups, mental health conditions, and acquisition devices (ie, more datasets with different feature distributions for each sleep stage) are used for training, the general performance of a deep learning network will be superior for sleep stage classification tasks with varied conditions.

Hybrid Sleep Stage Classification for Clinical Practices across Different Polysomnography Systems Using Frontal EEG

Automatic bio-signal processing and scoring have been a popular topic in recent years. This includes sleep stage classification, which is time-consuming when carried out by hand. Multiple sleep stage classification has been proposed in recent years. While effective, most of these processes are trained and validated against a singular set of data in uniformed pre-processing, whilst in a clinical environment, polysomnography (PSG) may come from different PSG systems that use different signal processing methods. In this study, we present a generalized sleep stage classification method that uses power spectra and entropy. To test its generality, we first trained our system using a uniform dataset and then validated it against another dataset with PSGs from different PSG systems. We found that the system achieved an accuracy of 0.80 and that it is highly consistent across most PSG records. A few samples of NREM3 sleep were classified poorly, and further inspection showed that these samples lost crucial NREM3 features due to aggressive filtering. This implies that the system’s effectiveness can be evaluated by human knowledge. Overall, our classification system shows consistent performance against PSG records that have been collected from different PSG systems, which gives it high potential in a clinical environment.

Assessment of autonomic function by long-term heart rate variability: beyond the classical framework of LF and HF measurements

In the assessment of autonomic function by heart rate variability (HRV), the framework that the power of high-frequency component or its surrogate indices reflects parasympathetic activity, while the power of low-frequency component or LF/HF reflects sympathetic activity has been used as the theoretical basis for the interpretation of HRV. Although this classical framework has contributed greatly to the widespread use of HRV for the assessment of autonomic function, it was obtained from studies of short-term HRV (typically 5‑10 min) under tightly controlled conditions. If it is applied to long-term HRV (typically 24 h) under free-running conditions in daily life, erroneous conclusions could be drawn. Also, long-term HRV could contain untapped useful information that is not revealed in the classical framework. In this review, we discuss the limitations of the classical framework and present studies that extracted autonomic function indicators and other useful biomedical information from long-term HRV using novel approaches beyond the classical framework. Those methods include non-Gaussianity index, HRV sleep index, heart rate turbulence, and the frequency and amplitude of cyclic variation of heart rate.

Effects of Touchscreen Media Use on Toddlers' Sleep: Insights from Longtime ECG Monitoring

Wearable biomedical sensor technology enables reliable monitoring of physiological data, even in very young children. The purpose of the present study was to develop algorithms for gaining valid physiological indicators of sleep quality in toddlers, using data from an undisturbing and easy-to-use wearable device. The study further reports the application of this technique to the investigation of potential impacts of early touchscreen media use. Toddlers' touchscreen media use is of strong interest for parents, educators, and researchers. Mostly, negative effects of media use are assumed, among them, disturbances of sleep and impairments of learning and development. In 55 toddlers (32 girls, 23 boys; 27.4 ± 4.9 months; range: 16-37 months), ECG monitoring was conducted for a period of 30 (±3) h. Parents were asked about their children's touchscreen media use and they rated their children's sleep quality. The use of touchscreen media predicted the physiologically determined quality of sleep but not parent-reported sleep quality (such as sleep onset latency). Greater heart rate differences between restless sleep phases and restful sleep indicated poorer nighttime recovery in children with more frequent use of touchscreen media. The study demonstrates that the expert analysis of the ECG during sleep is a potent tool for the estimation of sleep quality in toddlers.

Self-Applied Home Sleep Recordings: The Future of Sleep Medicine

Sleep disorders form a massive global health burden and there is an increasing need for simple and cost-efficient sleep recording devices. Recent machine learning-based approaches have already achieved scoring accuracy of sleep recordings on par with manual scoring, even with reduced recording montages. Simple and inexpensive monitoring over multiple consecutive nights with automatic analysis could be the answer to overcome the substantial economic burden caused by poor sleep and enable more efficient initial diagnosis, treatment planning, and follow-up monitoring for individuals suffering from sleep disorders.

A New Sleep Staging System for Type III Sleep Studies Equipped with a Tracheal Sound Sensor

Type III sleep studies record cardio-respiratory channels only. Compared with polysomnography, which also records electrophysiological channels, they present many advantages: they are less expensive, less time-consuming, and more likely to be performed at home. However, their accuracy is limited by missing sleep information. That is why many studies present specific cardio-respiratory parameters to assess the causal effects of sleep stages upon cardiac or respiratory activities. For this paper, we gathered many parameters proposed in literature, leading to 1,111 features. The pulse oximeter, the PneaVoX sensor (recording tracheal sounds), respiratory inductance plethysmography belts, the nasal cannula and the actimeter provided the 112 worthiest ones for automatic sleep scoring. Then, a 3-step model was implemented: classification with a multi-layer perceptron, sleep transition rules corrections (from the AASM guidelines), and sequence corrections using a Viterbi hidden Markov model. The whole process was trained and tested using 300 and 100 independent recordings provided from patients suspected of having sleep breathing disorders. Results indicated that the system achieves substantial agreement with manual scoring for classifications into 2 stages (wake vs. sleep: mean Cohen's Kappa of 0.63 and accuracy rate Acc of 87.8%) and 3 stages (wake vs. R stage vs. NREM stage: mean of 0.60 and Acc of 78.5%). It indicates that the method could provide information to help specialists while diagnosing sleep. The presented model had promising results and may enhance clinical diagnosis.

A Dynamically Reconfigurable ECG Analog Front-End With a 2.5× Data-Dependent Power Reduction

This paper presents a reconfigurable electrocardiogram (ECG) analog front-end (AFE) exploiting bio-signals' inherent low activity and quasi-periodicity to reduce power consumption. This is realized by an agile, on-the-fly dynamic noise-power trade-off performed over specific cardiac cycle regions guided by a least mean squares (LMS)-based adaptive predictor leading to ∼2.5× data-dependent power savings. Implemented in 65 nm CMOS, the AFE has tunable performance exhibiting an input-referred noise ranging from 2.38 - 3.64 μV_rms while consuming 307 - 769 nW from a 0.8 V supply. A comprehensive system performance verification was performed using ECG records from standard databases to establish the feasibility of the proposed predictor-based approach for power savings without compromising the system's anomaly detection capability or ability to extract pristine ECG features.

A deep transfer learning approach for wearable sleep stage classification with photoplethysmography

Unobtrusive home sleep monitoring using wrist-worn wearable photoplethysmography (PPG) could open the way for better sleep disorder screening and health monitoring. However, PPG is rarely included in large sleep studies with gold-standard sleep annotation from polysomnography. Therefore, training data-intensive state-of-the-art deep neural networks is challenging. In this work a deep recurrent neural network is first trained using a large sleep data set with electrocardiogram (ECG) data (292 participants, 584 recordings) to perform 4-class sleep stage classification (wake, rapid-eye-movement, N1/N2, and N3). A small part of its weights is adapted to a smaller, newer PPG data set (60 healthy participants, 101 recordings) through three variations of transfer learning. Best results (Cohen's kappa of 0.65 ± 0.11, accuracy of 76.36 ± 7.57%) were achieved with the domain and decision combined transfer learning strategy, significantly outperforming the PPG-trained and ECG-trained baselines. This performance for PPG-based 4-class sleep stage classification is unprecedented in literature, bringing home sleep stage monitoring closer to clinical use. The work demonstrates the merit of transfer learning in developing reliable methods for new sensor technologies by reusing similar, older non-wearable data sets. Further study should evaluate our approach in patients with sleep disorders such as insomnia and sleep apnoea.

Automatic sleep staging by cardiorespiratory signals: a systematic review

BACKGROUND

Because of problems with the recording and analysis of the EEG signal, automatic sleep staging using cardiorespiratory signals has been employed as an alternative. This study reports on certain critical points which hold considerable promise for the improvement of the results of the automatic sleep staging using cardiorespiratory signals.

METHODS

A systematic review.

RESULTS

The review and analysis of the literature in this area revealed four outstanding points: (1) the feature extraction epoch length, denoting that the standard 30-s segments of cardiorespiratory signals do not carry enough information for automatic sleep staging and that a 4.5-min length segment centering on each 30-s segment is proper for staging, (2) the time delay between the EEG signal extracted from the central nervous system activity and the cardiorespiratory signals extracted from the autonomic nervous system activity should be considered in the automatic sleep staging using cardiorespiratory signals, (3) the information in the morphology of ECG signals can contribute to the improvement of sleep staging, and (4) applying convolutional neural network (CNN) and long short-term memory network (LSTM) deep structures simultaneously to a large PSG recording database can lead to more reliable automatic sleep staging results.

CONCLUSIONS

Considering the above-mentioned points simultaneously can improve automatic sleep staging by cardiorespiratory signals. It is hoped that by considering the points, staging sleep automatically using cardiorespiratory signals, which does not have problems with the recording and analysis of EEG signals, yields results acceptably close to the results of automatic sleep staging by EEG signals.

Estimation of Sleep Stages Analyzing Respiratory and Movement Signals

The scoring of sleep stages is an essential part of sleep studies. The main objective of this research is to provide an algorithm for the automatic classification of sleep stages using signals that may be obtained in a non-obtrusive way. After reviewing the relevant research, the authors selected a multinomial logistic regression as the basis for their approach. Several parameters were derived from movement and breathing signals, and their combinations were investigated to develop an accurate and stable algorithm. The algorithm was implemented to produce successful results: the accuracy of the recognition of Wake/NREM/REM stages is equal to 73%, with Cohen's kappa of 0.44 for the analyzed 19324 sleep epochs of 30 seconds each. This approach has the advantage of using the only movement and breathing signals, which can be recorded with less effort than heart or brainwave signals, and requiring only four derived parameters for the calculations. Therefore, the new system is a significant improvement for non-obtrusive sleep stage identification compared to existing approaches.

Assessment of Obstructive Sleep Apnea-Related Sleep Fragmentation Utilizing Deep Learning-Based Sleep Staging from Photoplethysmography

STUDY OBJECTIVES

To assess the relationship between obstructive sleep apnea (OSA) severity and sleep fragmentation, accurate differentiation between sleep and wakefulness is needed. Sleep staging is usually performed manually using electroencephalography (EEG). This is time-consuming due to complexity of EEG setup and the amount of work in manual scoring. In this study, we aimed to develop an automated deep learning-based solution to assess OSA-related sleep fragmentation based on photoplethysmography (PPG)-signal.

METHODS

A combination of convolutional and recurrent neural networks was used for PPG-based sleep staging. The models were trained using two large clinical datasets from Israel (n=2149) and Australia (n=877) and tested separately on three-class (wake/NREM/REM), four-class (wake/N1+N2/N3/REM), and five-class (wake/N1/N2/N3/REM) classification. The relationship between OSA severity categories and sleep fragmentation was assessed using survival analysis of mean continuous sleep. Overlapping PPG epochs were applied to artificially obtain denser hypnograms for better identification of fragmented sleep.

RESULTS

Automatic PPG-based sleep staging showed accuracy of 83.3% on three-class, 74.1% on four-class, and 68.7% on five-class models. The hazard ratios for decreased mean continuous sleep compared to the non-OSA group obtained with Cox proportional hazards models with 5-second epoch-to-epoch intervals were 1.70, 3.30, and 8.11 for mild, moderate, and severe OSA, respectively. With manually scored EEG-based hypnograms, the corresponding hazard ratios were 1.18, 1.78, and 2.90.

CONCLUSIONS

PPG-based automatic sleep staging can be used to differentiate between OSA severity categories based on sleep continuity. The differences between the OSA severity categories become more apparent when a shorter epoch-to-epoch interval is used.

Estimation of respiratory rate and effort from a chest-worn accelerometer using constrained and recursive principal component analysis

Objective. Measurement of respiratory rate and effort is useful in various applications, such as the diagnosis of sleep apnea and early detection of patient deterioration in medical conditions, such as infections. A chest-worn accelerometer may be an easy and non-intrusive method, provided it is accurate and robust. We investigate the use of a novel method that can perform under realistic sleeping conditions such as variable sensor positions and body posture.Approach. Twenty subjects (aged 46-65 years) wore an accelerometer on the chest and a respiratory impedance plethysmography band as a reference. The subjects underwent an experimental protocol lasting approximately 90 min, under various postures and with different sensor positions. We used a novel, constrained, and recursive form of principal component analysis (PCA) to estimate the respiratory effort signal robustly. To obtain an estimate for the respiratory rate, first, multiple estimates were aggregated into a single frequency. Subsequently, a quality index was determined, such that unreliable estimates could be identified, and a trade-off could be made between coverage (percentage of time that the quality index is above a threshold) and limits of agreement.Main results. Results were determined over all recorded data, including changes in sensor position and posture. For respiratory effort, it was found that recursive and constrained computation of PCA reduced the estimation error significantly. For respiratory rate, a relation between coverage and limits of agreement was determined. If a minimum coverage of 80% was required, the limits of agreement could be kept below 1.45 breaths per minute. If the limits of agreement were constrained to 0.2 breaths per minute, a mean coverage of 5% was still attainable.Significance. We have shown that chest-worn accelerometery can be a robust and accurate method for measurement of respiratory features under realistic conditions.

Dimensionality reduction for EEG-based sleep stage detection: comparison of autoencoders, principal component analysis and factor analysis

Methods developed for automatic sleep stage detection make use of large amounts of data in the form of polysomnographic (PSG) recordings to build predictive models. In this study, we investigate the effect of several dimensionality reduction techniques, i.e., principal component analysis (PCA), factor analysis (FA), and autoencoders (AE) on common classifiers, e.g., random forests (RF), multilayer perceptron (MLP), long-short term memory (LSTM) networks, for automated sleep stage detection. Experimental testing is carried out on the MGH Dataset provided in the "You Snooze, You Win: The PhysioNet/Computing in Cardiology Challenge 2018". The signals used as input are the six available (EEG) electoencephalographic channels and combinations with the other PSG signals provided: ECG - electrocardiogram, EMG - electromyogram, respiration based signals - respiratory efforts and airflow. We observe that a similar or improved accuracy is obtained in most cases when using all dimensionality reduction techniques, which is a promising result as it allows to reduce the computational load while maintaining performance and in some cases also improves the accuracy of automated sleep stage detection. In our study, using autoencoders for dimensionality reduction maintains the performance of the model, while using PCA and FA the accuracy of the models is in most cases improved.

Deep learning enables sleep staging from photoplethysmogram for patients with suspected sleep apnea

Study Objectives

Accurate identification of sleep stages is essential in the diagnosis of sleep disorders (e.g. obstructive sleep apnea [OSA]) but relies on labor-intensive electroencephalogram (EEG)-based manual scoring. Furthermore, long-term assessment of sleep relies on actigraphy differentiating only between wake and sleep periods without identifying specific sleep stages and having low reliability in identifying wake periods after sleep onset. To address these issues, we aimed to develop an automatic method for identifying the sleep stages from the photoplethysmogram (PPG) signal obtained with a simple finger pulse oximeter.

Methods

PPG signals from the diagnostic polysomnographies of susptected OSA patients (n = 894) were utilized to develop a combined convolutional and recurrent neural network. The deep learning model was trained individually for three-stage (wake/NREM/REM), four-stage (wake/N1+N2/N3/REM), and five-stage (wake/N1/N2/N3/REM) classification of sleep.

Results

The three-stage model achieved an epoch-by-epoch accuracy of 80.1% with Cohen’s κ of 0.65. The four- and five-stage models achieved 68.5% (κ = 0.54), and 64.1% (κ = 0.51) accuracies, respectively. With the five-stage model, the total sleep time was underestimated with a mean bias error (SD) of of 7.5 (55.2) minutes.

Conclusion

The PPG-based deep learning model enabled accurate estimation of sleep time and differentiation between sleep stages with a moderate agreement to manual EEG-based scoring. As PPG is already included in ambulatory polygraphic recordings, applying the PPG-based sleep staging could improve their diagnostic value by enabling simple, low-cost, and reliable monitoring of sleep and help assess otherwise overlooked conditions such as REM-related OSA.

Automatic sleep staging using heart rate variability, body movements, and recurrent neural networks in a sleep disordered population

STUDY OBJECTIVES

To validate a previously developed sleep staging algorithm using heart rate variability (HRV) and body movements in an independent broad cohort of unselected sleep disordered patients.

METHODS

We applied a previously designed algorithm for automatic sleep staging using long short-term memory recurrent neural networks to model sleep architecture. The classifier uses 132 HRV features computed from electrocardiography and activity counts from accelerometry. We retrained our algorithm using two public datasets containing both healthy sleepers and sleep disordered patients. We then tested the performance of the algorithm on an independent hold-out validation set of sleep recordings from a wide range of sleep disorders collected in a tertiary sleep medicine center.

RESULTS

The classifier achieved substantial agreement on four-class sleep staging (wake/N1-N2/N3/rapid eye movement [REM]), with an average κ of 0.60 and accuracy of 75.9%. The performance of the sleep staging algorithm was significantly higher in insomnia patients (κ = 0.62, accuracy = 77.3%). Only in REM parasomnias, the performance was significantly lower (κ = 0.47, accuracy = 70.5%). For two-class wake/sleep classification, the classifier achieved a κ of 0.65, with a sensitivity (to wake) of 72.9% and specificity of 94.0%.

CONCLUSIONS

This study shows that the combination of HRV, body movements, and a state-of-the-art deep neural network can reach substantial agreement in automatic sleep staging compared with polysomnography, even in patients suffering from a multitude of sleep disorders. The physiological signals required can be obtained in various ways, including non-obtrusive wrist-worn sensors, opening up new avenues for clinical diagnostics.

Sleep staging from electrocardiography and respiration with deep learning

STUDY OBJECTIVES

Sleep is reflected not only in the electroencephalogram but also in heart rhythms and breathing patterns. We hypothesized that it is possible to accurately stage sleep based on the electrocardiogram (ECG) and respiratory signals.

METHODS

Using a dataset including 8682 polysomnograms, we develop deep neural networks to stage sleep from ECG and respiratory signals. Five deep neural networks consisting of convolutional networks and long- and short-term memory networks are trained to stage sleep using heart and breathing, including the timing of R peaks from ECG, abdominal and chest respiratory effort, and the combinations of these signals.

RESULTS

ECG in combination with the abdominal respiratory effort achieved the best performance for staging all five sleep stages with a Cohen's kappa of 0.585 (95% confidence interval ±0.017); and 0.760 (±0.019) for discriminating awake vs. rapid eye movement vs. nonrapid eye movement sleep. Performance is better for younger ages, whereas it is robust for body mass index, apnea severity, and commonly used outpatient medications.

CONCLUSIONS

Our results validate that ECG and respiratory effort provide substantial information about sleep stages in a large heterogeneous population. This opens new possibilities in sleep research and applications where electroencephalography is not readily available or may be infeasible.

Proof of concept: Screening for REM sleep behaviour disorder with a minimal set of sensors

OBJECTIVE

Rapid-Eye-Movement (REM) sleep behaviour disorder (RBD) is an early predictor of Parkinson's disease, dementia with Lewy bodies, and multiple system atrophy. This study investigated the use of a minimal set of sensors to achieve effective screening for RBD in the population, integrating automated sleep staging (three state) followed by RBD detection without the need for cumbersome electroencephalogram (EEG) sensors.

METHODS

Polysomnography signals from 50 participants with RBD and 50 age-matched healthy controls were used to evaluate this study. Three stage sleep classification was achieved using a random forest classifier and features derived from a combination of cost-effective and easy to use sensors, namely electrocardiogram (ECG), electrooculogram (EOG), and electromyogram (EMG) channels. Subsequently, RBD detection was achieved using established and new metrics derived from ECG and EMG channels.

RESULTS

The EOG and EMG combination provided the optimal minimalist fully-automated performance, achieving 0.57 ± 0.19 kappa (3 stage) for sleep staging and an RBD detection accuracy of 0.90 ± 0.11, (sensitivity and specificity of 0.88 ± 0.13 and 0.92 ± 0.098, respectively). A single ECG sensor achieved three state sleep staging with 0.28 ± 0.06 kappa and RBD detection accuracy of 0.62 ± 0.10.

CONCLUSIONS

This study demonstrates the feasibility of using signals from a single EOG and EMG sensor to detect RBD using fully-automated techniques.

SIGNIFICANCE

This study proposes a cost-effective, practical, and simple RBD identification support tool using only two sensors (EMG and EOG); ideal for screening purposes.

Study Protocol on the Validation of the Quality of Sleep Data from Xiaomi Domestic Wristbands

(1) Background: Sleep disorders are a common problem for public health since they are considered potential triggers and predictors of some mental and physical diseases. Evaluating the sleep quality of a person may be a first step to prevent further health issues that diminish their independence and quality of life. Polysomnography (PSG) is the “gold standard” for sleep studies, but this technique presents some drawbacks. Thus, this study intends to assess the capability of the new Xiaomi Mi Smart Band 5 to be used as a tool for sleep self-assessment. (2) Methods: This study will be an observational and prospective study set at the sleep unit of a hospital in A Coruña, Spain. Forty-three participants who meet the inclusion criteria will be asked to participate. Specific statistical methods will be used to analyze the data collected using the Xiaomi Mi Smart Band 5 and PSG. (3) Discussion: This study offers a promising approach to assess whether the Xiaomi Mi Smart Band 5 correctly records our sleep. Even though these devices are not expected to replace PSG, they may be used as an initial evaluation tool for users to manage their own sleep quality and, if necessary, consult a health professional. Further, the device may help users make simple changes to their habits to improve other health issues as well. Trial registration: NCT04568408 (Registered 23 September 2020).

A Multi-Class Automatic Sleep Staging Method Based on Photoplethysmography Signals

Automatic sleep staging with only one channel is a challenging problem in sleep-related research. In this paper, a simple and efficient method named PPG-based multi-class automatic sleep staging (PMSS) is proposed using only a photoplethysmography (PPG) signal. Single-channel PPG data were obtained from four categories of subjects in the CAP sleep database. After the preprocessing of PPG data, feature extraction was performed from the time domain, frequency domain, and nonlinear domain, and a total of 21 features were extracted. Finally, the Light Gradient Boosting Machine (LightGBM) classifier was used for multi-class sleep staging. The accuracy of the multi-class automatic sleep staging was over 70%, and the Cohen's kappa statistic k was over 0.6. This also showed that the PMSS method can also be applied to stage the sleep state for patients with sleep disorders.

The relationship between machine-learning-derived sleep parameters and behavior problems in 3- and 5-year-old children: results from the CHILD Cohort study

STUDY OBJECTIVES

Machine learning (ML) may provide insights into the underlying sleep stages of accelerometer-assessed sleep duration. We examined associations between ML-sleep patterns and behavior problems among preschool children.

METHODS

Children from the CHILD Cohort Edmonton site with actigraphy and behavior data at 3-years (n = 330) and 5-years (n = 304) were included. Parent-reported behavior problems were assessed by the Child Behavior Checklist. The Hidden Markov Model (HMM) classification method was used for ML analysis of the accelerometer sleep period. The average time each participant spent in each HMM-derived sleep state was expressed in hours per day. We analyzed associations between sleep and behavior problems stratified by children with and without sleep-disordered breathing (SDB).

RESULTS

Four hidden sleep states were identified at 3 years and six hidden sleep states at 5 years using HMM. The first sleep state identified for both ages (HMM-0) had zero counts (no movement). The remaining hidden states were merged together (HMM-mov). Children spent an average of 8.2 ± 1.2 h/day in HMM-0 and 2.6 ± 0.8 h/day in HMM-mov at 3 years. At age 5, children spent an average of 8.2 ± 0.9 h/day in HMM-0 and 1.9 ± 0.7 h/day in HMM-mov. Among SDB children, each hour in HMM-0 was associated with 0.79-point reduced externalizing behavior problems (95% CI -1.4, -0.12; p < 0.05), and a 1.27-point lower internalizing behavior problems (95% CI -2.02, -0.53; p < 0.01).

CONCLUSIONS

ML-sleep states were not associated with behavior problems in the general population of children. Children with SDB who had greater sleep duration without movement had lower behavioral problems. The ML-sleep states require validation with polysomnography.

Automatic sleep scoring: A deep learning architecture for multi-modality time series

BACKGROUND

Sleep scoring is an essential but time-consuming process, and therefore automatic sleep scoring is crucial and urgent to help address the growing unmet needs for sleep research. This paper aims to develop a versatile deep-learning architecture to automate sleep scoring using raw polysomnography recordings.

METHOD

The model adopts a linear function to address different numbers of inputs, thereby extending model applications. Two-dimensional convolution neural networks are used to learn features from multi-modality polysomnographic signals, a "squeeze and excitation" block to recalibrate channel-wise features, together with a long short-term memory module to exploit long-range contextual relation. The learnt features are finally fed to the decision layer to generate predictions for sleep stages.

RESULT

Model performance is evaluated on three public datasets. For all tasks with different available channels, our model achieves outstanding performance not only on healthy subjects but even on patients with sleep disorders (SHHS: Acc-0.87, K-0.81; ISRUC: Acc-0.86, K-0.82; Sleep-EDF: Acc-0.86, K-0.81). The highest classification accuracy is achieved by a fusion of multiple polysomnographic signals.

COMPARISON

Compared to state-of-the-art methods that use the same dataset, the proposed model achieves a comparable or better performance, and exhibits low computational cost.

CONCLUSIONS

The model demonstrates its transferability among different datasets, without changing model architecture or hyper-parameters across tasks. Good model transferability promotes the application of transfer learning on small group studies with mismatched channels. Due to demonstrated availability and versatility, the proposed method can be integrated with diverse polysomnography systems, thereby facilitating sleep monitoring in clinical or routine care.