Automatic sleep staging in obstructive sleep apnea patients using photoplethysmography, heart rate variability signal and machine learning techniques

Improved sleep stage predictions by deep learning of photoplethysmogram and respiration patterns

Sleep staging is a crucial tool for diagnosing and monitoring sleep disorders, but the standard clinical approach using polysomnography (PSG) in a sleep lab is time-consuming, expensive, uncomfortable, and limited to a single night. Advancements in sensor technology have enabled home sleep monitoring, but existing devices still lack sufficient accuracy to inform clinical decisions. To address this challenge, we propose a deep learning architecture that combines a convolutional neural network and bidirectional long short-term memory to accurately classify sleep stages. By supplementing photoplethysmography (PPG) signals with respiratory sensor inputs, we demonstrated significant improvements in prediction accuracy and Cohen's kappa (k) for 2- (92.7 %; k = 0.768), 3- (80.2 %; k = 0.714), 4- (76.8 %, k = 0.550), and 5-stage (76.7 %, k = 0.616) sleep classification using raw data. This relatively translatable approach, with a less intensive AI model and leveraging only a few, inexpensive sensors, shows promise in accurately staging sleep. This has potential for diagnosing and managing sleep disorders in a more accessible and practical manner, possibly even at home.

Sleep staging algorithm based on smartwatch sensors for healthy and sleep apnea populations

OBJECTIVE

Sleep stages can provide valuable insights into an individual's sleep quality. By leveraging movement and heart rate data collected by modern smartwatches, it is possible to enable the sleep staging feature and enhance users' understanding about their sleep and health conditions.

METHOD

In this paper, we present and validate a recurrent neural network based model with 23 input features extracted from accelerometer and photoplethysmography sensors data for both healthy and sleep apnea populations. We designed a lightweight and fast solution to enable the prediction of sleep stages for each 30-s epoch. This solution was developed using a large dataset of 1522 night recordings collected from a highly heterogeneous population and different versions of Samsung smartwatch.

RESULTS

In the classification of four sleep stages (wake, light, deep, and rapid eye movements sleep), the proposed solution achieved 71.6 % of balanced accuracy and a Cohen's kappa of 0.56 in a test set with 586 recordings.

CONCLUSION

The results presented in this paper validate our proposal as a competitive wearable solution for sleep staging. Additionally, the use of a large and diverse data set contributes to the robustness of our solution, and corroborates the validation of algorithm's performance. Some additional analysis performed for healthy and sleep apnea population demonstrated that algorithm's performance has low correlation with demographic variables.

Sampling rate requirement for accurate calculation of heart rate and its variability based on the electrocardiogram

Objective. To develop analytical formulas which can serve as quantitative guidelines for the selection of the sampling rate for the electrocardiogram (ECG) required to calculate heart rate (HR) and heart rate variability (HRV) with a desired level of accuracy.Approach. We developed analytical formulas which relate the ECG sampling rate to conservative bounds on HR and HRV errors: (i) one relating HR and sampling rate to a HR error bound and (ii) the others relating sampling rate to HRV error bounds (in terms of root-mean-square of successive differences (RMSSD) and standard deviation of normal sinus beats (SDNN)). We validated the formulas using experimental data collected from 58 young healthy volunteers which encompass a wide HR and HRV ranges through strenuous exercise.Main results. The results strongly supported the validity of the analytical formulas as well as their tightness. The formulas can be used to (i) predict an upper bound of inaccuracy in HR and HRV for a given sampling rate in conjunction with HR and HRV as well as to (ii) determine a sampling rate to achieve a desired accuracy requirement at a given HR or HRV (or its range).Significance. HR and its variability (HRV) derived from the ECG have been widely utilized in a wide range of research in physiology and psychophysiology. However, there is no established guideline for the selection of the sampling rate for the ECG required to calculate HR and HRV with a desired level of accuracy. Hence, the analytical formulas may guide in selecting sampling rates for the ECG tailored to various applications of HR and HRV.

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.

Paediatric sleep apnea event prediction using nasal air pressure and machine learning

Sleep-disordered breathing is an important health issue for children. The objective of this study was to develop a machine learning classifier model for the identification of sleep apnea events taken exclusively from nasal air pressure measurements acquired during overnight polysomnography for paediatric patients. A secondary objective of this study was to differentiate site of obstruction exclusively from hypopnea event data using the model. Computer vision classifiers were developed via transfer learning to either normal breathing while asleep, obstructive hypopnea, obstructive apnea or central apnea. A separate model was trained to identify site of obstruction as either adeno-tonsillar or tongue base. In addition, a survey of board-certified and board-eligible sleep physicians was completed to compare clinician versus model classification performance of sleep events, and indicated very good performance of our model relative to human raters. The nasal air pressure sample database available for modelling comprised 417 normal, 266 obstructive hypopnea, 122 obstructive apnea and 131 central apnea events derived from 28 paediatric patients. The four-way classifier achieved a mean prediction accuracy of 70.0% (95% confidence interval [67.1-72.9]). Clinician raters correctly identified sleep events from nasal air pressure tracings 53.8% of the time, whereas the local model was 77.5% accurate. The site of obstruction classifier achieved a mean prediction accuracy of 75.0% (95% confidence interval [68.7-81.3]). Machine learning applied to nasal air pressure tracings is feasible and may exceed the diagnostic performance of expert clinicians. Nasal air pressure tracings of obstructive hypopneas may "encode" information regarding the site of obstruction, which may only be discernable by machine learning.

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.

Multi-stage sleep classification using photoplethysmographic sensor

The conventional approach to monitoring sleep stages requires placing multiple sensors on patients, which is inconvenient for long-term monitoring and requires expert support. We propose a single-sensor photoplethysmographic (PPG)-based automated multi-stage sleep classification. This experimental study recorded the PPG during the entire night's sleep of 10 patients. Data analysis was performed to obtain 79 features from the recordings, which were then classified according to sleep stages. The classification results using support vector machine (SVM) with the polynomial kernel yielded an overall accuracy of 84.66%, 79.62% and 72.23% for two-, three- and four-stage sleep classification. These results show that it is possible to conduct sleep stage monitoring using only PPG. These findings open the opportunities for PPG-based wearable solutions for home-based automated sleep monitoring.

Photoplethysmography Driven Hypertension Identification: A Pilot Study

To prevent and diagnose hypertension early, there has been a growing demand to identify its states that align with patients. This pilot study aims to research how a non-invasive method using photoplethysmographic (PPG) signals works together with deep learning algorithms. A portable PPG acquisition device (Max30101 photonic sensor) was utilized to (1) capture PPG signals and (2) wirelessly transmit data sets. In contrast to traditional feature engineering machine learning classification schemes, this study preprocessed raw data and applied a deep learning algorithm (LSTM-Attention) directly to extract deeper correlations between these raw datasets. The Long Short-Term Memory (LSTM) model underlying a gate mechanism and memory unit enables it to handle long sequence data more effectively, avoiding gradient disappearance and possessing the ability to solve long-term dependencies. To enhance the correlation between distant sampling points, an attention mechanism was introduced to capture more data change features than a separate LSTM model. A protocol with 15 healthy volunteers and 15 hypertension patients was implemented to obtain these datasets. The processed result demonstrates that the proposed model could present satisfactory performance (accuracy: 0.991; precision: 0.989; recall: 0.993; F1-score: 0.991). The model we proposed also demonstrated superior performance compared to related studies. The outcome indicates the proposed method could effectively diagnose and identify hypertension; thus, a paradigm to cost-effectively screen hypertension could rapidly be established using wearable smart devices.

Peripheral blood flow estimated by laser doppler flowmetry provides additional information about sleep state beyond that provided by pulse rate variability

Pulse rate variability (PRV), derived from Laser Doppler flowmetry (LDF) or photoplethysmography, has recently become widely used for sleep state assessment, although it cannot identify all the sleep stages. Peripheral blood flow (BF), also estimated by LDF, may be modulated by sleep stages; however, few studies have explored its potential for assessing sleep state. Thus, we aimed to investigate whether peripheral BF could provide information about sleep stages, and thus improve sleep state assessment. We performed electrocardiography and simultaneously recorded BF signals by LDF from the right-index finger and ear concha of 45 healthy participants (13 women; mean age, 22.5 ± 3.4 years) during one night of polysomnographic recording. Time- and frequency-domain parameters of peripheral BF, and time-domain, frequency-domain, and non-linear indices of PRV and heart rate variability (HRV) were calculated. Finger-BF parameters in the time and frequency domains provided information about different sleep stages, some of which (such as the difference between N1 and rapid eye movement sleep) were not revealed by finger-PRV. In addition, finger-PRV patterns and HRV patterns were similar for most parameters. Further, both finger- and ear-BF results showed 0.2-0.3 Hz oscillations that varied with sleep stages, with a significant increase in N3, suggesting a modulation of respiration within this frequency band. These results showed that peripheral BF could provide information for different sleep stages, some of which was complementary to the information provided by PRV. Furthermore, the combination of peripheral BF and PRV may be more advantageous than HRV alone in assessing sleep states and related autonomic nervous activity.

Automation of classification of sleep stages and estimation of sleep efficiency using actigraphy

Introduction

Sleep is a fundamental and essential physiological process for recovering physiological function. Sleep disturbance or deprivation has been known to be a causative factor of various physiological and psychological disorders. Therefore, sleep evaluation is vital for diagnosing or monitoring those disorders. Although PSG (polysomnography) has been the gold standard for assessing sleep quality and classifying sleep stages, PSG has various limitations for common uses. In substitution for PSG, there has been vigorous research using actigraphy.

Methods

For classifying sleep stages automatically, we propose machine learning models with HRV (heart rate variability)-related features and acceleration features, which were processed from the actigraphy (Maxim band) data. Those classification results were transformed into a binary classification for estimating sleep efficiency. With 30 subjects, we conducted PSG, and they slept overnight with wrist-type actigraphy. We assessed the performance of four proposed machine learning models.

Results

With HRV-related and raw features of actigraphy, Cohen's kappa was 0.974 (p < 0.001) for classifying sleep stages into five stages: wake (W), REM (Rapid Eye Movement) (R), Sleep N1 (Non-Rapid Eye Movement Stage 1, S1), Sleep N2 (Non-Rapid Eye Movement Stage 2, S2), Sleep N3 (Non-Rapid Eye Movement Stage 3, S3). In addition, our machine learning model for the estimation of sleep efficiency showed an accuracy of 0.86.

Discussion

Our model demonstrated that automated sleep classification results could perfectly match the PSG results. Since models with acceleration features showed modest performance in differentiating some sleep stages, further research on acceleration features must be done. In addition, the sleep efficiency model demonstrated modest results. However, an investigation into the effects of HRV-derived and acceleration features is required.

A new diagnostic method for chronic obstructive pulmonary disease using the photoplethysmography signal and hybrid artificial intelligence

Background and Purpose

Chronic obstructive pulmonary disease (COPD), is a primary public health issue globally and in our country, which continues to increase due to poor awareness of the disease and lack of necessary preventive measures. COPD is the result of a blockage of the air sacs known as alveoli within the lungs; it is a persistent sickness that causes difficulty in breathing, cough, and shortness of breath. COPD is characterized by breathing signs and symptoms and airflow challenge because of anomalies in the airways and alveoli that occurs as the result of significant exposure to harmful particles and gases. The spirometry test (breath measurement test), used for diagnosing COPD, is creating difficulties in reaching hospitals, especially in patients with disabilities or advanced disease and in children. To facilitate the diagnostic treatment and prevent these problems, it is far evaluated that using photoplethysmography (PPG) signal in the diagnosis of COPD disease would be beneficial in order to simplify and speed up the diagnosis process and make it more convenient for monitoring. A PPG signal includes numerous components, including volumetric changes in arterial blood that are related to heart activity, fluctuations in venous blood volume that modify the PPG signal, a direct current (DC) component that shows the optical properties of the tissues, and modest energy changes in the body. PPG has typically received the usage of a pulse oximeter, which illuminates the pores and skin and measures adjustments in mild absorption. PPG occurring with every heart rate is an easy signal to measure. PPG signal is modeled by machine learning to predict COPD.

Methods

During the studies, the PPG signal was cleaned of noise, and a brand-new PPG signal having three low-frequency bands of the PPG was obtained. Each of the four signals extracted 25 features. An aggregate of 100 features have been extracted. Additionally, weight, height, and age were also used as characteristics. In the feature selection process, we employed the Fisher method. The intention of using this method is to improve performance.

Results

This improved PPG prediction models have an accuracy rate of 0.95 performance value for all individuals. Classification algorithms used in feature selection algorithm has contributed to a performance increase.

Conclusion

According to the findings, PPG-based COPD prediction models are suitable for usage in practice.

Advances in Photoplethysmography for Personalized Cardiovascular Monitoring

Photoplethysmography (PPG) is garnering substantial interest due to low cost, noninvasiveness, and its potential for diagnosing cardiovascular diseases, such as cardiomyopathy, heart failure, and arrhythmia. The signals obtained through PPG can yield information based on simple analyses, such as heart rate. In contrast, when accompanied by the complex analysis of sophisticated signals, valuable information, such as blood pressure, sympathetic nervous system activity, and heart rate variability, can be obtained. For a complex analysis, a better understanding of the sources of noise, which create limitations in the application of PPG, is needed to get reliable information to assess cardiovascular health. Therefore, this Special Issue handles literature about noises and how they affect the waveform of the PPG caused by individual variations (e.g., skin tone, obesity, age, and gender), physiology (e.g., respiration, venous pulsation, body site of measurement, and body temperature), and external factors (e.g., motion artifact, ambient light, and applied pressure to the skin). It also covers the issues that still need to be considered in each situation.

Application of photoplethysmography signals for healthcare systems: An in-depth review

BACKGROUND AND OBJECTIVES

Photoplethysmography (PPG) is a device that measures the amount of light absorbed by the blood vessel, blood, and tissues, which can, in turn, translate into various measurements such as the variation in blood flow volume, heart rate variability, blood pressure, etc. Hence, PPG signals can produce a wide variety of biological information that can be useful for the detection and diagnosis of various health problems. In this review, we are interested in the possible health disorders that can be detected using PPG signals.

METHODS

We applied PRISMA guidelines to systematically search various journal databases and identified 43 PPG studies that fit the criteria of this review.

RESULTS

Twenty-five health issues were identified from these studies that were classified into six categories: cardiac, blood pressure, sleep health, mental health, diabetes, and miscellaneous. Various routes were employed in these PPG studies to perform the diagnosis: machine learning, deep learning, and statistical routes. The studies were reviewed and summarized.

CONCLUSIONS

We identified limitations such as poor standardization of sampling frequencies and lack of publicly available PPG databases. We urge that future work should consider creating more publicly available databases so that a wide spectrum of health problems can be covered. We also want to promote the use of PPG signals as a potential precision medicine tool in both ambulatory and hospital settings.

Wearable Photoplethysmography for Cardiovascular Monitoring

Smart wearables provide an opportunity to monitor health in daily life and are emerging as potential tools for detecting cardiovascular disease (CVD). Wearables such as fitness bands and smartwatches routinely monitor the photoplethysmogram signal, an optical measure of the arterial pulse wave that is strongly influenced by the heart and blood vessels. In this survey, we summarize the fundamentals of wearable photoplethysmography and its analysis, identify its potential clinical applications, and outline pressing directions for future research in order to realize its full potential for tackling CVD.

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.

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.

A novel multi-class imbalanced EEG signals classification based on the adaptive synthetic sampling (ADASYN) approach

BACKGROUND

Brain signals (EEG-Electroencephalography) are a gold standard frequently used in epilepsy prediction. It is crucial to predict epilepsy, which is common in the community. Early diagnosis is essential to reduce the treatment process of the disease and to keep the process healthier.

METHODS

In this study, a five-classes dataset was used: EEG signals from different individuals, healthy EEG signals from tumor document, EEG signal with epilepsy, EEG signal with eyes closed, and EEG signal with eyes open. Four different methods have been proposed to classify five classes of EEG signals. In the first approach, the EEG signal was first divided into four different bands (beta, alpha, theta, and delta), and then 25 time-domain features were extracted from each band, and the main EEG signal and these extracted features were combined to obtain 125-time domain features (feature extraction). Using the Random Forests classifier, EEG activities were classified into five classes. In the second approach, each One-Against-One (OVO) approach with 125 attributes was split into ten parts, pairwise, and then each piece was classified with the Random Forests classifier. The majority voting scheme was used to combine decisions from the ten classifiers. In the third proposed method, each One-Against-All (OVA) approach with 125 attributes was divided into five parts, and then each piece was classified with the Random Forests classifier. The majority voting scheme was used to combine decisions from the five classifiers. In the fourth proposed approach, each One-Against-All (OVA) approach with 125 attributes was divided into five parts. Since each piece obtained had an imbalanced data distribution, an adaptive synthetic (ADASYN) sampling approach was used to stabilize each piece. Then, each balanced piece was classified with the Random Forests classifier. To combine the decisions obtanied from each classifier, the majority voting scheme has been used.

RESULTS

The first approach achieved 71.90% classification success in classifying five-class EEG signals. The second approach achieved a classification success of 91.08% in classifying five-class EEG signals. The third method achieved 89% success, while the fourth proposed approach achieved 91.72% success. The results obtained show that the proposed fourth approach (the combination of the ADASYN sampling approach and Random Forest Classifier) achieved the best success in classifying five class EEG signals. This proposed method could be used in the detection of epilepsy events in the EEG signals.

Sources of Inaccuracy in Photoplethysmography for Continuous Cardiovascular Monitoring

Photoplethysmography (PPG) is a low-cost, noninvasive optical technique that uses change in light transmission with changes in blood volume within tissue to provide information for cardiovascular health and fitness. As remote health and wearable medical devices become more prevalent, PPG devices are being developed as part of wearable systems to monitor parameters such as heart rate (HR) that do not require complex analysis of the PPG waveform. However, complex analyses of the PPG waveform yield valuable clinical information, such as: blood pressure, respiratory information, sympathetic nervous system activity, and heart rate variability. Systems aiming to derive such complex parameters do not always account for realistic sources of noise, as testing is performed within controlled parameter spaces. A wearable monitoring tool to be used beyond fitness and heart rate must account for noise sources originating from individual patient variations (e.g., skin tone, obesity, age, and gender), physiology (e.g., respiration, venous pulsation, body site of measurement, and body temperature), and external perturbations of the device itself (e.g., motion artifact, ambient light, and applied pressure to the skin). Here, we present a comprehensive review of the literature that aims to summarize these noise sources for future PPG device development for use in health monitoring.

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.

Proof of principle study: diagnostic accuracy of a novel algorithm for the estimation of sleep stages and disease severity in patients with sleep-disordered breathing based on actigraphy and respiratory inductance plethysmography

PURPOSE

In this proof of principle study, we evaluated the diagnostic accuracy of the novel Nox BodySleep^TM 1.0 algorithm (Nox Medical, Iceland) for the estimation of disease severity and sleep stages based on features extracted from actigraphy and respiratory inductance plethysmography (RIP) belts. Validation was performed against in-lab polysomnography (PSG) in patients with sleep-disordered breathing (SDB).

METHODS

Patients received PSG according to AASM. Sleep stages were manually scored using the AASM criteria and the recording was evaluated by the novel algorithm. The results were analyzed by descriptive statistics methods (IBM SPSS Statistics 25.0).

RESULTS

We found a strong Pearson correlation (r=0.91) with a bias of 0.2/h for AHI estimation as well as a good correlation (r=0.81) and an overestimation of 14 min for total sleep time (TST). Sleep efficiency (SE) was also valued with a good Pearson correlation (r=0.73) and an overestimation of 2.1%. Wake epochs were estimated with a sensitivity of 0.65 and a specificity of 0.59 while REM and non-REM (NREM) phases were evaluated a sensitivity of 0.72 and 0.74, respectively. Specificity was 0.74 for NREM and 0.68 for REM. Additionally, a Cohen's kappa of 0.62 was found for this 3-class classification problem.

CONCLUSION

The algorithm shows a moderate diagnostic accuracy for the estimation of sleep. In addition, the algorithm determines the AHI with good agreement with the manual scoring and it shows good diagnostic accuracy in estimating wake-sleep transition. The presented algorithm seems to be an appropriate tool to increase the diagnostic accuracy of portable monitoring. The validated diagnostic algorithm promises a more appropriate and cost-effective method if integrated in out-of-center (OOC) testing of patients with suspicion for SDB.

Sleep-wake stage detection with single channel ECG and hybrid machine learning model in patients with obstructive sleep apnea

Sleep staging is an important step in the diagnosis of obstructive sleep apnea (OSA) and this step is performed by a physician who visually scores the electroencephalography, electrooculography and electromyography signals taken by the polysomnography (PSG) device. The PSG records must be taken by a technician in a hospital environment, this may suggest a drawback. This study aims to develop a new method based on hybrid machine learning with single-channel ECG for sleep-wake detection, which is an alternative to the sleep staging procedure used in hospitals today. For this purpose, the heart rate variability signal was derived using electrocardiography (ECG) signals of 10 OSA patients. Then, QRS components in different frequency bands were obtained from the ECG signal by digital filtering. In this way, nine more signals were obtained in total. 25 features from each of the 9 signals, a total of 225 features have been extracted. Fisher feature selection algorithm and principal component analysis were used to reduce the number of features. Finally, features were classified with decision tree, support vector machines, k-nearest neighborhood algorithm and ensemble classifiers. In addition, the proposed model has been checked with the leave one out method. At the end of the study, it was shown that sleep-wake detection can be performed with 81.35% accuracy with only three features and 87.12% accuracy with 10 features. The sensitivity and specificity values for the 3 features were 0.85 and 0.77, and for 10 features the sensitivity and specificity values were 0.90 and 0.85 respectively. These results suggested that the proposed model could be used to detect sleep-wake stages during the OSA diagnostic process.

A review on current trends in automatic sleep staging through bio-signal recordings and future challenges

Sleep staging is a vital process conducted in order to analyze polysomnographic data. To facilitate prompt interpretation of these recordings, many automatic sleep staging methods have been proposed. These methods rely on bio-signal recordings, which include electroencephalography, electrocardiography, electromyography, electrooculography, respiratory, pulse oximetry and others. However, advanced, uncomplicated and swift sleep-staging-evaluation is still needed in order to improve the existing polysomnographic data interpretation. The present review focuses on automatic sleep staging methods through bio-signal recording including current and future challenges.

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.

Sleep stage classification from heart-rate variability using long short-term memory neural networks

Automated sleep stage classification using heart rate variability (HRV) may provide an ergonomic and low-cost alternative to gold standard polysomnography, creating possibilities for unobtrusive home-based sleep monitoring. Current methods however are limited in their ability to take into account long-term sleep architectural patterns. A long short-term memory (LSTM) network is proposed as a solution to model long-term cardiac sleep architecture information and validated on a comprehensive data set (292 participants, 584 nights, 541.214 annotated 30 s sleep segments) comprising a wide range of ages and pathological profiles, annotated according to the Rechtschaffen and Kales (R&K) annotation standard. It is shown that the model outperforms state-of-the-art approaches which were often limited to non-temporal or short-term recurrent classifiers. The model achieves a Cohen's k of 0.61 ± 0.15 and accuracy of 77.00 ± 8.90% across the entire database. Further analysis revealed that the performance for individuals aged 50 years and older may decline. These results demonstrate the merit of deep temporal modelling using a diverse data set and advance the state-of-the-art for HRV-based sleep stage classification. Further research is warranted into individuals over the age of 50 as performance tends to worsen in this sub-population.

In obstructive sleep apnea patients, automatic determination of respiratory arrests by photoplethysmography signal and heart rate variability

Obstructive sleep apnea is a disease that occurs in connection to pauses in respiration during sleep. Detection of the disease is achieved using a polysomnography device, which is the gold standard in diagnosis. Diagnosis is made by the steps of sleep staging and respiration scoring. Respiration scoring is performed with at least four signals. Technical knowledge is required for attaching the electrodes. Additionally, the electrodes are disturbing to an extent that will delay the patient's sleep. It is needed to have systems as alternatives for polysomnography devices that will bring a solution to these issues. This study proposes a new approach for the process of respiration scoring which is one of the diagnostic steps for the disease. A machine-learning-based apnea detection algorithm was developed for the process of respiration scoring. The study used Photoplethysmography (PPG) signal and Heart Rate Variability (HRV) that is derived from this signal. The PPG records obtained from the patient and control groups were cleaned out using a digital filter. Then, the HRV parameter was derived from the PPG signal. Later, 46 features were derived from the PPG signal and 40 features were derived from the HRV. The derived features were classified with reduced machine-learning techniques using the F-score feature-selection algorithm. The evaluation was made in a multifaceted manner. Besides, Principal Component Analysis was performed to reduce system input (features). According to the results, if a real-time embedded system is designed, the system can operate with 16 PPG feature 95%, four PPG feature 93.81% accuracy rate. These success rates are highly sufficient for the system to work. Considering all these values, it is possible to realize a practical respiration scoring system. With this study, it was agreed upon that PPG signal may be used in the diagnosis of this disease by processing it with machine learning and signal processing techniques.