Validation of novel automatic ultra-wideband radar for sleep apnea detection

Combining a wireless radar sleep monitoring device with deep machine learning techniques to assess obstructive sleep apnea severity

STUDY OBJECTIVES

The gold standard for diagnosing obstructive sleep apnea (OSA) is polysomnography (PSG). However, PSG is a time-consuming method with clinical limitations. This study aimed to create a wireless radar framework to screen the likelihood of 2 levels of OSA severity (ie, moderate-to-severe and severe OSA) in accordance with clinical practice standards.

METHODS

We conducted a prospective, simultaneous study using a wireless radar system and PSG in a Northern Taiwan sleep center, involving 196 patients. The wireless radar sleep monitor, incorporating hybrid models such as deep neural decision trees, estimated the respiratory disturbance index relative to the total sleep time established by PSG (RDIPSG_TST), by analyzing continuous-wave signals indicative of breathing patterns. Analyses were performed to examine the correlation and agreement between the RDIPSG_TST and apnea-hypopnea index, results obtained through PSG. Cut-off thresholds for RDIPSG_TST were determined using Youden's index, and multiclass classification was performed, after which the results were compared.

RESULTS

A strong correlation (ρ = 0.91) and agreement (average difference of 0.59 events/h) between apnea-hypopnea index and RDIPSG_TST were identified. In terms of the agreement between the 2 devices, the average difference between PSG-based apnea-hypopnea index and radar-based RDIPSG_TST was 0.59 events/h, and 187 out of 196 cases (95.41%) fell within the 95% confidence interval of differences. A moderate-to-severe OSA model achieved an accuracy of 90.3% (cut-off threshold for RDIPSG_TST: 19.2 events/h). A severe OSA model achieved an accuracy of 92.4% (cut-off threshold for RDIPSG_TST: 28.86 events/h). The mean accuracy of multiclass classification performance using these cut-off thresholds was 83.7%.

CONCLUSIONS

The wireless-radar-based sleep monitoring device, with cut-off thresholds, can provide rapid OSA screening with acceptable accuracy and also alleviate the burden on PSG capacity. However, to independently apply this framework, the function of determining the radar-based total sleep time requires further optimizations and verification in future work.

CITATION

Lin S-Y, Tsai C-Y, Majumdar A, et al. Combining a wireless radar sleep monitoring device with deep machine learning techniques to assess obstructive sleep apnea severity. J Clin Sleep Med. 2024;20(8):1267-1277.

Technologies for sleep monitoring at home: wearables and nearables

Sleep is an essential part of our lives and daily sleep monitoring is crucial for maintaining good health and well-being. Traditionally, the gold standard method for sleep monitoring is polysomnography using various sensors attached to the body; however, it is limited with regards to long-term sleep monitoring in a home environment. Recent advancements in wearable and nearable technology have made it possible to monitor sleep at home. In this review paper, the technologies that are currently available for sleep stages and sleep disorder monitoring at home are reviewed using wearable and nearable devices. Wearables are devices that are worn on the body, while nearables are placed near the body. These devices can accurately monitor sleep stages and sleep disorder in a home environment. In this study, the benefits and limitations of each technology are discussed, along with their potential to improve sleep quality.

Diagnosis of obstructive sleep apnea using a bio-radar contact-free system compared with an established HST device in older adults

GOAL AND AIMS

To compare a bio-radar contact-free monitoring device in diagnosing obstructive sleep apnea (OSA) in older people with an established home sleep apnea testing system (HST).

FOCUS METHOD/TECHNOLOGY

A bio-radar contact-free monitoring device (OrbSense+).

REFERENCE METHOD/TECHNOLOGY

An established HST, Alice NightOne.

SAMPLE

Fifty-three out of 63 recruited subjects were included in the final analysis. Seventy-two percent were male (age 72 ± 9 years; body mass index 31.05 ± 5.56 kg/m2).

DESIGN

An observational, prospective study.

CORE ANALYTICS

Intraclass correlation coefficient (ICC), Bland-Altman analysis, and receiver operating characteristic analysis.

ADDITIONAL ANALYTICS AND EXPLORATORY ANALYSES

None.

CORE OUTCOMES

Both 45 (84.91%) were diagnosed with OSA by Alice NightOne (average respiratory event index = 21.23 events/h) and by OrbSense+ (average respiratory event index = 25.98 events/h). Respiratory event index and oxygen desaturation index obtained by Alice NightOne and OrbSense+ were highly correlated, with ICC of 0.93 and 0.88, respectively. The Bland-Altman plot comparing the means showed good agreement between the 2 diagnostic techniques. With more than 5 respiratory events per hour as the standard for OSA diagnosis, OrbSense+ had a sensitivity of 100% and a specificity of 100% in diagnosis of OSA (P < .0001). With more than 15 respiratory events per hour as the standard for OSA diagnosis, OrbSense+ was found to have a sensitivity of 100% and a specificity of 86.96% in diagnosis of OSA (P < .0001).

IMPORTANT ADDITIONAL OUTCOMES

None.

CORE CONCLUSION

The bio-radar sleep monitoring device is a reasonably accurate home sleep apnea test for use in older patients.

Mattress-Based Non-Influencing Sleep Apnea Monitoring System

A mattress-type non-influencing sleep apnea monitoring system was designed to detect sleep apnea-hypopnea syndrome (SAHS). The pressure signals generated during sleep on the mattress were collected, and ballistocardiogram (BCG) and respiratory signals were extracted from the original signals. In the experiment, wavelet transform (WT) was used to reduce noise and decompose and reconstruct the signal to eliminate the influence of interference noise, which can directly and accurately separate the BCG signal and respiratory signal. In feature extraction, based on the five features commonly used in SAHS, an innovative respiratory waveform similarity feature was proposed in this work for the first time. In the SAHS detection, the binomial logistic regression was used to determine the sleep apnea symptoms in the signal segment. Simulation and experimental results showed that the device, algorithm, and system designed in this work were effective methods to detect, diagnose, and assist the diagnosis of SAHS.

Validity of non-contact methods for diagnosis of Obstructive Sleep Apnea: a systematic review and meta-analysis

STUDY OBJECTIVE

Obstructive Sleep Apnea (OSA) is associated with increased perioperative cardiac, respiratory and neurological complications. Pre-operative OSA risk assessment is currently done through screening questionnaires with high sensitivity but poor specificity. The objective of this study was to evaluate the validity and diagnostic accuracy of portable, non-contact devices in the diagnosis of OSA as compared with polysomnography.

DESIGN

This study is a systematic review of English observational cohort studies with meta-analysis and risk of bias assessment.

SETTING

Pre-operative, including in the hospital and clinic setting.

PATIENTS

Adult patients undergoing sleep apnea assessment using polysomnography and an experimental non-contact tool.

INTERVENTIONS

A novel non-contact device, which does not utilize any monitor that makes direct contact with the patient's body, in conjunction with polysomnography.

MEASUREMENTS

Primary outcomes included pooled sensitivity and specificity of the experimental device in the diagnosis of obstructive sleep apnea, in comparison to gold-standard polysomnography.

RESULTS

Twenty-eight of 4929 screened studies were included in the meta-analysis. A total of 2653 patients were included with the majority being patients referred to a sleep clinic (88.8%). Average age was 49.7(SD±6.1) years, female sex (31%), average body mass index of 29.5(SD±3.2) kg/m², average apnea-hypopnea index (AHI) of 24.7(SD±5.6) events/h, and pooled OSA prevalence of 72%. Non-contact technology used was mainly video, sound, or bio-motion analysis. Pooled sensitivity and specificity of non-contact methods in moderate to severe OSA diagnosis (AHI > 15) was 0.871 (95% CI 0.841,0.896, I² 0%) and 0.8 (95% CI 0.719,0.862), respectively (AUC 0.902). Risk of bias assessment showed an overall low risk of bias across all domains except for applicability concerns (none were conducted in the perioperative setting).

CONCLUSION

Available data indicate contactless methods have high pooled sensitivity and specificity for OSA diagnosis with moderate to high level of evidence. Future research is needed to evaluate these tools in the perioperative setting.

Portable evaluation of obstructive sleep apnea in adults: A systematic review

Obstructive sleep apnea (OSA) is a significant healthcare burden affecting approximately one billion people worldwide. The prevalence of OSA is rising with the ongoing obesity epidemic, a key risk factor for its development. While in-laboratory polysomnography (PSG) is the gold standard for diagnosing OSA, it has significant drawbacks that prevent widespread use. Portable devices with different levels of monitoring are available to allow remote assessment for OSA. To better inform clinical practice and research, this comprehensive systematic review evaluated diagnostic performances, study cost and patients' experience of different levels of portable sleep studies (type 2, 3, and 4), as well as wearable devices and non-contact systems, in adults. Despite varying study designs and devices used, portable diagnostic tests are found to be sufficient for initial screening of patients at risk of OSA. Future studies are needed to evaluate cost effectiveness with the incorporation of portable diagnostic tests into the diagnostic pathway for OSA, as well as their application in patients with chronic respiratory diseases and other comorbidities that may affect test performance.

Automated Detection of Sleep Apnea-Hypopnea Events Based on 60 GHz Frequency-Modulated Continuous-Wave Radar Using Convolutional Recurrent Neural Networks: A Preliminary Report of a Prospective Cohort Study

Radar is a promising non-contact sensor for overnight polysomnography (PSG), the gold standard for diagnosing obstructive sleep apnea (OSA). This preliminary study aimed to demonstrate the feasibility of the automated detection of apnea-hypopnea events for OSA diagnosis based on 60 GHz frequency-modulated continuous-wave radar using convolutional recurrent neural networks. The dataset comprised 44 participants from an ongoing OSA cohort, recruited from July 2021 to April 2022, who underwent overnight PSG with a radar sensor. All PSG recordings, including sleep and wakefulness, were included in the dataset. Model development and evaluation were based on a five-fold cross-validation. The area under the receiver operating characteristic curve for the classification of 1-min segments ranged from 0.796 to 0.859. Depending on OSA severity, the sensitivities for apnea-hypopnea events were 49.0-67.6%, and the number of false-positive detections per participant was 23.4-52.8. The estimated apnea-hypopnea index showed strong correlations (Pearson correlation coefficient = 0.805-0.949) and good to excellent agreement (intraclass correlation coefficient = 0.776-0.929) with the ground truth. There was substantial agreement between the estimated and ground truth OSA severity (kappa statistics = 0.648-0.736). The results demonstrate the potential of radar as a standalone screening tool for OSA.

Noncontact Longitudinal Respiratory Rate Measurements in Healthy Adults Using Radar-Based Sleep Monitor (Somnofy): Validation Study

BACKGROUND

Respiratory rate (RR) is arguably the most important vital sign to detect clinical deterioration. Change in RR can also, for example, be associated with the onset of different diseases, opioid overdoses, intense workouts, or mood. However, unlike for most other vital parameters, an easy and accurate measuring method is lacking.

OBJECTIVE

This study aims to validate the radar-based sleep monitor, Somnofy, for measuring RRs and investigate whether events affecting RR can be detected from personalized baselines calculated from nightly averages.

METHODS

First, RRs from Somnofy for 37 healthy adults during full nights of sleep were extensively validated against respiratory inductance plethysmography. Then, the night-to-night consistency of a proposed filtered average RR was analyzed for 6 healthy participants in a pilot study in which they used Somnofy at home for 3 months.

RESULTS

Somnofy measured RR 84% of the time, with mean absolute error of 0.18 (SD 0.05) respirations per minute, and Bland-Altman 95% limits of agreement adjusted for repeated measurements ranged from -0.99 to 0.85. The accuracy and coverage were substantially higher in deep and light sleep than in rapid eye movement sleep and wake. The results were independent of age, sex, and BMI, but dependent on supine sleeping position for some radar orientations. For nightly filtered averages, the 95% limits of agreement ranged from -0.07 to -0.04 respirations per minute. In the longitudinal part of the study, the nightly average was consistent from night to night, and all substantial deviations coincided with self-reported illnesses.

CONCLUSIONS

RRs from Somnofy were more accurate than those from any other alternative method suitable for longitudinal measurements. Moreover, the nightly averages were consistent from night to night. Thus, several factors affecting RR should be detectable as anomalies from personalized baselines, enabling a range of applications. More studies are necessary to investigate its potential in children and older adults or in a clinical setting.

Sleep Position Detection with a Wireless Audio-Motion Sensor—A Validation Study

It is well documented that body position significantly affects breathing indices during sleep in patients with obstructive sleep apnea. They usually worsen while changing from a non-supine to a supine position. Therefore, body position should be an accurately measured and credible parameter in all types of sleep studies. The aim of this study was to specify the accuracy of a neck-based monitoring device (Clebre, Olsztyn, Poland) mounted at the suprasternal notch, in determining a supine and non-supine sleeping position, as well as specific body positions during sleep, in comparison to polysomnography (PSG). A sleep study (PSG along with a neck-based audio-motion sensor) was performed on 89 consecutive patients. The accuracy in determining supine and non-supine positions was 96.9%±3.9% and 97.0%±3.6%, respectively. For lateral positions, the accuracy was 98.6%±2% and 97.4%±4.5% for the right and left side, respectively. The prone position was detected with an accuracy of 97.3%±5.6%. The study showed a high accuracy in detecting supine, as well as other gross positions, during sleep based on a sensor attached to the suprasternal notch, compared to the PSG study. We feel that the suprasternal notch is a promising area for placing wireless sleep study devices.

Classification of Respiratory States Using Spectrogram with Convolutional Neural Network

This paper proposes an approach to the classification of respiration states based on a neural network model by visualizing respiratory signals using a spectrogram. The analysis and processing of human biosignals are still considered some of the most crucial and fundamental research areas in both signal processing and medical applications. Recently, learning-based algorithms in signal and image processing for medical applications have shown significant improvement from both quantitative and qualitative perspectives. Human respiration is still considered an important factor for diagnosis, and it plays a key role in preventing fatal diseases in practice. This paper chiefly deals with a contactless-based approach for the acquisition of respiration data using an ultra-wideband (UWB) radar sensor because it is simple and easy for use in an experimental setup and shows high accuracy in distance estimation. This paper proposes the classification of respiratory states by using a feature visualization scheme, a spectrogram, and a neural network model. The proposed method shows competitive and promising results in the classification of respiratory states. The experimental results also show that the method provides better accuracy (precision: 0.86 and specificity: 0.90) than conventional methods that use expensive equipment for respiration measurement.

Apnea Detection in Polysomnographic Recordings Using Machine Learning Techniques

Sleep disorders are diagnosed in sleep laboratories by polysomnography, a multi-parameter examination that monitors biological signals during sleep. The subsequent evaluation of the obtained records is very time-consuming. The goal of this study was to create an automatic system for evaluation of the airflow and SpO2 channels of polysomnography records, through the use of machine learning techniques and a large database, for apnea and desaturation detection (which is unusual in other studies). To that end, a convolutional neural network (CNN) was designed using hyperparameter optimization. It was then trained and tested for apnea and desaturation. The proposed CNN was compared with the commonly used k-nearest neighbors (k-NN) method. The classifiers were designed based on nasal airflow and blood oxygen saturation signals. The final neural network accuracy for apnea detection reached 84%, and that for desaturation detection was 74%, while the k-NN classifier reached accuracies of 83% and 64% for apnea detection and desaturation detection, respectively.

Measuring Sleep, Wakefulness, and Circadian Functions in Neurologic Disorders

Neurologic disorders impact the ability of the brain to regulate sleep, wake, and circadian functions, including state generation, components of state (such as rapid eye movement sleep muscle atonia, state transitions) and electroencephalographic microarchitecture. At its most extreme, extensive brain damage may even prevent differentiation of sleep stages from wakefulness (eg, status dissociatus). Given that comorbid sleep-wake-circadian disorders are common and can adversely impact the occurrence, evolution, and management of underlying neurologic conditions, new technologies for long-term monitoring of neurologic patients may potentially usher in new diagnostic strategies and optimization of clinical management.

Distinguishing sleep from wake with a radar sensor: a contact-free real-time sleep monitor

This work aimed to evaluate whether a radar sensor can distinguish sleep from wakefulness in real time. The sensor detects body movements without direct physical contact with the subject and can be embedded in the roof of a hospital room for completely unobtrusive monitoring. We conducted simultaneous recordings with polysomnography, actigraphy, and radar on two groups: healthy young adults (n = 12, four nights per participant) and patients referred to a sleep examination (n = 28, one night per participant). We developed models for sleep/wake classification based on principles commonly used by actigraphy, including real-time models, and tested them on both datasets. We estimated a set of commonly reported sleep parameters from these data, including total-sleep-time, sleep-onset-latency, sleep-efficiency, and wake-after-sleep-onset, and evaluated the inter-method reliability of these estimates. Classification results were on-par with, or exceeding, those often seen for actigraphy. For real-time models in healthy young adults, accuracies were above 92%, sensitivities above 95%, specificities above 83%, and all Cohen's kappa values were above 0.81 compared to polysomnography. For patients referred to a sleep examination, accuracies were above 81%, sensitivities about 89%, specificities above 53%, and Cohen's kappa values above 0.44. Sleep variable estimates showed no significant intermethod bias, but the limits of agreement were quite wide for the group of patients referred to a sleep examination. Our results indicate that the radar has the potential to offer the benefits of contact-free real-time monitoring of sleep, both for in-patients and for ambulatory home monitoring.

Evaluation of a non-contact ultra-wideband bio-radar sleep monitoring device for screening of sleep breathing disease

PURPOSE

Ultra-wideband bio-radar (UWB) is a new non-contact technology that can be used to screen for obstructive sleep apnea (OSA). However, little information is available regarding its reliability. This study aimed to evaluate the effectiveness of UWB and to determine if UWB could provide a novel and reliable method for the primary screening of sleep-related breathing disorders.

METHOD

Subjects with suspected OSA from the sleep center of the First Hospital of the China Medical University were assessed over the period of September 2018 to April 2019 for enrollment in the study. Three detection methods were simultaneously used, including the STOP-Bang questionnaire (SBQ), UWB, and standard polysomnography (PSG). The data were analyzed using a fourfold table, receiver operating characteristic curves, Spearman rank correlation coefficients, Bland-Altman plots, and epoch-by-epoch analysis.

RESULT

Of 67 patients, 56 were men, mean age was 43 ± 11 years, mean body mass index was 27.8 ± 4.8 kg/m², and mean SBQ score was 4.8 ± 1.6. The apnea-hypopnea index (AHI) (r = 0.82, p < 0.01) and minimum arterial oxygen saturation (r = 0.80, p < 0.01) of the UWB were positively correlated with those obtained from the PSG. UWB performed better than SBQ, as indicated by the larger area under the curve (0.85 vs. 0.632). The sensitivity and specificity of the UWB-AHI were good (100%, 70%, respectively).

CONCLUSIONS

UWB performs well in the screening of OSA and can provide reliable outcomes for the screening of OSA at the primary level.

Radar-based sleep stage classification in children undergoing polysomnography: a pilot-study

STUDY OBJECTIVES

Unobtrusive monitoring of sleep and sleep disorders in children presents challenges. We investigated the possibility of using Ultra-Wide band (UWB) radar to measure sleep in children.

METHODS

Thirty-two children scheduled to undergo a clinical polysomnography participated; their ages ranged from 2 months to 14 years. During the polysomnography, the children's body movements and breathing rate were measured by an UWB-radar. A total of 38 features were calculated from the motion signals and breathing rate obtained from the raw radar signals. Adaptive boosting was used as machine learning classifier to estimate sleep stages, with polysomnography as gold standard method for comparison.

RESULTS

Data of all participants combined, this study achieved a Cohen's Kappa coefficient of 0.67 and an overall accuracy of 89.8% for wake and sleep classification, a Kappa of 0.47 and an accuracy of 72.9% for wake, rapid-eye-movement (REM) sleep, and non-REM sleep classification, and a Kappa of 0.43 and an accuracy of 58.0% for wake, REM sleep, light sleep and deep sleep classification.

CONCLUSION

Although the current performance is not sufficient for clinical use yet, UWB radar is a promising method for non-contact sleep analysis in children.

Toward standardizing the clinical testing protocols of point-of-care devices for obstructive sleep apnea diagnosis

PURPOSE

In recent years, point-of-care (POC) devices, especially smart wearables, have been introduced to provide a cost-effective, comfortable, and accessible alternative to polysomnography (PSG)-the current gold standard-for the monitoring, screening, and diagnosis of obstructive sleep apnea (OSA). Thorough validation and human subject testing are essential steps in the translation of these device technologies to the market. However, every device development group tests their device in their own way. No standard guidelines exist for assessing the performance of these POC devices. The purpose of this paper is to critically distill the key aspects of the various protocols reported in the literature and present a protocol that unifies the best practices for testing wearable and other POC devices for OSA.

METHODS

A limited review and graphical descriptive analytics of literature-including journal articles, web sources, and clinical manuscripts by authoritative agencies in sleep medicine-are performed to glean the testing and validation methods employed for POC devices, specifically for OSA.

RESULTS

The analysis suggests that the extent of heterogeneity of the demographics, the performance metrics, subject survey, hypotheses, and statistical analyses need to be carefully considered in a systematic protocol for testing POC devices for OSA.

CONCLUSION

We provide a systematic method and list specific recommendations to extensively assess various performance criteria for human subject testing of POC devices. A rating scale of 1-3 is provided to encourage studies to put a focus on addressing the key elements of a testing protocol.