Obstructive Sleep Apnea Monitoring Research Articles

Development of an affordable microRNA electrochemical biosensor for identification and monitoring of obstructive sleep apnea and its associated comorbidities

Obstructive sleep apnea (OSA) is a growing and common disorder found in a large global population. Unfortunately, many tend to neglect this disorder without anticipating its chronic and serious health consequences. In this work we demonstrate a prototype portable, low-cost and facile sensing platform that can identify microRNA based molecular markers of OSA including monitoring its severity. An affordable commercial grade gold coated copper cladded laminate sheet was used for fabricating the electrochemical biosensor. The electrode surface was nanotextured to extend a dense and high surface area to significantly improve the sensitivity. A limit of detection of 0.7 nM could be obtained for mir-21 target with a very promising stability of more than 600 days at − 20 °C storage. Clinical utility of the fabricated sensor was established with a rsd of 7.3 % using RNA extracted from PBMC isolated blood samples of various (n = 12) OSA patients and healthy individuals (n = 7). The electrochemical sensing results were compared and satisfactorily validated with ΔCt values obtained from RT-PCR and AHI values from Polysomnography test. Clinical validation not only indicated potentials for an easy portable sensing technology but also a method to monitor patient’s severity of the disorder. These test results have been further supported by statistical analysis that enabled prediction of correlation of OSA with other common lifestyle disorders such as Obesity, liver disorder and diabetes. Overall, the proposed platform holds a strong potential as a reliable alternative to the existing OSA detection technology like Polysomnography that is complex and requires long data acquisition time.

SleepPPG-Net: A Deep Learning Algorithm for Robust Sleep Staging From Continuous Photoplethysmography.

Sleep staging is an essential component in the diagnosis of sleep disorders and management of sleep health. Sleep is traditionally measured in a clinical setting and requires a labor-intensive labeling process. We hypothesize that it is possible to perform automated robust 4-class sleep staging using the raw photoplethysmography (PPG) time series and modern advances in deep learning (DL). We used two publicly available sleep databases that included raw PPG recordings, totalling 2,374 patients and 23,055 hours of continuous data. We developed SleepPPG-Net, a DL model for 4-class sleep staging from the raw PPG time series. SleepPPG-Net was trained end-to-end and consists of a residual convolutional network for automatic feature extraction and a temporal convolutional network to capture long-range contextual information. We benchmarked the performance of SleepPPG-Net against models based on the best-reported state-of-the-art (SOTA) algorithms. When benchmarked on a held-out test set, SleepPPG-Net obtained a median Cohen's Kappa ( κ) score of 0.75 against 0.69 for the best SOTA approach. SleepPPG-Net showed good generalization performance to an external database, obtaining a κ score of 0.74 after transfer learning. Overall, SleepPPG-Net provides new SOTA performance. In addition, performance is high enough to open the path to the development of wearables that meet the requirements for usage in clinical applications such as the diagnosis and monitoring of obstructive sleep apnea.

Validating Discriminative Signatures for Obstructive Sleep Apnea in Exhaled Breath.

Rapid and reliable tools for the diagnosis and monitoring of obstructive sleep apnea (OSA) are currently lacking. Prior studies using a chemical analysis of exhaled breath have suggested the existence of an OSA-specific metabolic signature. Here, we validated this diagnostic approach and the proposed marker compounds, as well as their potential to reliably diagnose OSA. In this cross-sectional observational study, exhaled breath was analyzed using secondary electrospray ionization high-resolution mass spectrometry. The study cohort included untreated OSA patients, OSA patients treated with continuous positive airway pressure and healthy subjects. The robustness of previously reported OSA markers was validated based on detectability, significant differences between groups (Mann–Whitney U test) and classification performance. The breath analysis of 118 participants resulted in 42 previously reported markers that could be confirmed in this independent validation cohort. Nine markers were significantly increased in untreated OSA compared to treated OSA, with a subset of them being consistent with a previous validation study. An OSA prediction based on the confirmed OSA signature performed with an AUC of 0.80 (accuracy 77%, sensitivity 73% and specificity 80%). As several breath markers were clearly found to be repeatable and robust in this independent validation study, these results underscore the clinical potential of breath analysis for OSA diagnostics and monitoring.

Multi-task feature fusion network for Obstructive Sleep Apnea detection using single-lead ECG signal

Efficient daily monitoring of Obstructive Sleep Apnea (OSA) and timely implementation of treatment is one of the important measures to ensure human health and sleep quality. Unfortunately, as the clinical gold standard, polysomnography (PSG) is complex to detect and cannot be popularized on a large scale. In recent years, OSA detection methods for single-lead electrocardiogram (ECG) signal based on deep learning have emerged. However, the detection performance of these deep learning methods based on a single learning task is often unsatisfactory. In order to solve this problem, we propose an OSA detection method based on one-dimensional multi-task feature fusion convolutional neural network (1D-MTFFNet). First of all, the borderline synthetic minority oversampling technique (Borderline-SMOTE) is used to alleviate the problem of data imbalance. Secondly, a multi-task learning method based on the combination of unsupervised feature learning and supervised feature learning is proposed to improve the feature extraction performance of the network. Finally, feature fusion between multiple tasks and between different levels is achieved by channel shuffling. We use the Apnea-ECG database of PhysioNet to conduct experiments. In terms of segment detection results, the proposed method achieves an accuracy of 91.13%, and the sensitivity and specificity reach 90.32% and 91.63% respectively. In terms of individual screening, the accuracy of the proposed method reached 100%. The overall performance is at the level of the most advanced methods.

A Minimalist Method Toward Severity Assessment and Progression Monitoring of Obstructive Sleep Apnea on the Edge

Artificial Intelligence-enabled applications on edge devices have the potential to revolutionize disease detection and monitoring in future smart health (sHealth) systems. In this study, we investigated a minimalist approach for the severity classification, severity estimation, and progression monitoring of obstructive sleep apnea (OSA) in a home environment using wearables. We used the recursive feature elimination technique to select the best feature set of 70 features from a total of 200 features extracted from polysomnogram. We used a multi-layer perceptron model to investigate the performance of OSA severity classification with all the ranked features to a subset of features available from either Electroencephalography or Heart Rate Variability (HRV) and time duration of SpO2 level. The results indicate that using only computationally inexpensive features from HRV and SpO2, an area under the curve of 0.91 and an accuracy of 83.97% can be achieved for the severity classification of OSA. For estimation of the apnea-hypopnea index, the accuracy of RMSE = 4.6 and R-squared value = 0.71 have been achieved in the test set using only ranked HRV and SpO2 features. The Wilcoxon-signed-rank test indicates a significant change (p < 0.05) in the selected feature values for a progression in the disease over 2.5 years. The method has the potential for integration with edge computing for deployment on everyday wearables. This may facilitate the preliminary severity estimation, monitoring, and management of OSA patients and reduce associated healthcare costs as well as the prevalence of untreated OSA.

Sleep Diagnostics for Home Monitoring of Sleep Apnea Patients.

Objectives: Sleep time information is essential for monitoring of obstructive sleep apnea (OSA), as the severity assessment depends on the number of breathing disturbances per hour of sleep. However, clinical procedures for sleep monitoring rely on numerous uncomfortable sensors, which could affect sleeping patterns. Therefore, an automated method to identify sleep intervals from unobtrusive data is required. However, most unobtrusive sensors suffer from data loss and sensitivity to movement artifacts. Thus, current sleep detection methods are inadequate, as these require long intervals of good quality. Moreover, sleep monitoring of OSA patients is often less reliable due to heart rate disturbances, movement and sleep fragmentation. The primary aim was to develop a sleep-wake classifier for sleep time estimation of suspected OSA patients, based on single short-term segments of their cardiac and respiratory signals. The secondary aim was to define metrics to detect OSA patients directly from their predicted sleep-wake pattern and prioritize them for clinical diagnosis.Methods: This study used a dataset of 183 suspected OSA patients, of which 36 test subjects. First, a convolutional neural network was designed for sleep-wake classification based on healthier patients (AHI < 10). It employed single 30 s epochs of electrocardiograms and respiratory inductance plethysmograms. Sleep information and Total Sleep Time (TST) was derived for all patients using the short-term segments. Next, OSA patients were detected based on the average confidence of sleep predictions and the percentage of sleep-wake transitions in the predicted sleep architecture.Results: Sleep-wake classification on healthy, mild and moderate patients resulted in moderate κ scores of 0.51, 0.49, and 0.48, respectively. However, TST estimates decreased in accuracy with increasing AHI. Nevertheless, severe patients were detected with a sensitivity of 78% and specificity of 89%, and prioritized for clinical diagnosis. As such, their inaccurate TST estimate becomes irrelevant. Excluding detected OSA patients resulted in an overall estimated TST with a mean bias error of 21.9 (± 55.7) min and Pearson correlation of 0.74 to the reference.Conclusion: The presented framework offered a realistic tool for unobtrusive sleep monitoring of suspected OSA patients. Moreover, it enabled fast prioritization of severe patients for clinical diagnosis.

An intelligent detection and therapeutic device to support sleep apnea in infants

Among the numerous sleep-disorders breathing patterns encountered by babies, such as intermittent respiration, premature apnea, obstructive sleep apnea wa sconsidered a major cause of concern. Upper airway structure, pulmonary system mechanics, etc. are only a few reasons why the babies are vulnerable to obstructive sleep disorder. An imbalance in the viscoelastic properties of the pharynx, dilators and pressure can lead to airway collapse. Low level of oxygen in blood or hypoxemia is considered a characteristic in infants with severe Obstructive Sleep Apnea (OSA). Invasive treatments like nasopharyngeal tubes, continuous positive airway pressure (CPAP), or tracheostomy are found to be helpful in most cases where infants experience sleep apnea. This paper suggests an appropriate method for long-term monitoring of obstructive sleep apnea in infants and, if any abnormalities are observed, the tool provides continuous airway pressure treatment until the abnormality is stabilized. Resilient propagation algorithm is utilised to train the datasets and produce a relevant output.

Development of an automated system for obstructive sleep apnea treatment based on machine learning and breath effort monitoring

Obstructive sleep apnea (OSA) is characterized by repeated airway obstructions during sleep and affects about 35% of the population. Untreated OSA is associated with increased mortality and severe comorbidities. This fact, combined with the poor long-term compliance to the standard therapy, has led to an increased interest in alternative treatment options such as the electrical stimulation (ES) of the genioglossus muscle. In this work, we propose an automated non-invasive system for real-time monitoring of obstructive sleep apnea and treatment through ES of the genioglossus muscle. The closed-loop system includes a sensor to monitor breath effort from respiratory movement, a Transcutaneous Electrical Nerve Stimulation (TENS) device, and a program that analyzes the signal of the sensor and controls the whole system. The breath effort signal is first processed and then fed to a machine learning (ML) algorithm, which is a pattern recognition network. The whole analysis runs on a personal computer and used data from an open database of 12 patients in order to train the ML network and evaluate its performance. The breath effort signals were obtained from thoracic and abdominal inductance plethysmography recordings. OSA events were classified with an average true detection rate 81% ± 8% and 77% ± 11% for thoracic (VTH) and abdominal (VAB) sensor signals, respectively. The overall classification accuracies were on average 73% ± 5% for VTH and 74% ± 9% for VAB. An improvement is observed when both signals are considered (82% ± 7%).

SAS score: Targeting high-specificity for efficient population-wide monitoring of obstructive sleep apnea.

ProposalThis paper investigates a novel screening tool for Obstructive Sleep Apnea Syndrome (OSAS), which aims at efficient population-wide monitoring. To this end, we introduce SASscore which provides better OSAS prediction specificity while maintaining a high sensitivity.MethodsWe process a cohort of 2595 patients from 4 sleep laboratories in Western Romania, by recording over 100 sleep, breathing, and anthropometric measurements per patient; using this data, we compare our SASscore with state of the art scores STOP-Bang and NoSAS through area under curve (AUC), sensitivity, specificity, negative predictive value (NPV), and positive predictive value (PPV). We also evaluate the performance of SASscore by considering different Apnea–Hypopnea Index (AHI) diagnosis cut-off points and show that custom refinements are possible by changing the score’s threshold.ResultsSASscore takes decimal values within the interval (2, 7) and varies linearly with AHI; it is based on standardized measures for BMI, neck circumference, systolic blood pressure and Epworth score. By applying the STOP-Bang and NoSAS questionnaires, as well as the SASscore on the patient cohort, we respectively obtain the AUC values of 0.69 (95% CI 0.66-0.73, p < 0.001), 0.66 (95% CI 0.63-0.68, p < 0.001), and 0.73 (95% CI 0.71-0.75, p < 0.001), with sensitivities values of 0.968, 0.901, 0.829, and specificity values of 0.149, 0.294, 0.359, respectively. Additionally, we cross-validate our score with a second independent cohort of 231 patients confirming the high specificity and good sensitivity of our score. When raising SASscore’s diagnosis cut-off point from 3 to 3.7, both sensitivity and specificity become roughly 0.6.ConclusionsIn comparison with the existing scores, SASscore is a more appropriate screening tool for monitoring large populations, due to its improved specificity. Our score can be tailored to increase either sensitivity or specificity, while balancing the AUC value.

An automatic rules extraction approach to support OSA events detection in an mHealth system.

Detection and real time monitoring of obstructive sleep apnea (OSA) episodes are very important tasks in healthcare. To suitably face them, this paper proposes an easy-to-use, cheap mobile-based approach relying on three steps. First, single-channel ECG data from a patient are collected by a wearable sensor and are recorded on a mobile device. Second, the automatic extraction of knowledge about that patient takes place offline, and a set of IF…THEN rules containing heart-rate variability (HRV) parameters is achieved. Third, these rules are used in our real-time mobile monitoring system: the same wearable sensor collects the single-channel ECG data and sends them to the same mobile device, which now processes those data online to compute HRV-related parameter values. If these values activate one of the rules found for that patient, an alarm is immediately produced. This approach has been tested on a literature database with 35 OSA patients. A comparison against five well-known classifiers has been carried out.

Digital monitoring of obstructive sleep apnea using snoring sound and arterial oxygen saturation.

Digital monitoring of obstructive sleep apnea using snoring sound and arterial oxygen saturation.