A comparison of automated and manual sleep staging and respiratory event recognition in a portable sleep diagnostic device with in-lab sleep study

A comparison of caregiver-reported snoring and objective snoring in children from urban neighborhoods

OBJECTIVE

Sleep Disordered Breathing (SDB) is both prevalent and under-recognized in pediatric minority populations. Recognition of SDB is often triggered by symptoms of caregiver-reported snoring. However, the validity and utility of caregiver reports likely vary across populations. Our objective is to assess the association between caregiver-reported snoring and objectively recorded snoring in a low-income urban community and explore factors associated with agreement between objective and subjective snoring.

METHODS

169 6 to 12 year old participants underwent at-home sleep studies with a WatchPAT device as part of the Environmental Assessment of Sleep in Youth (EASY) cohort study. Differences in subjective snoring, objective snoring, and concordance between subjective and objective snoring based on socioeconomic and clinical characteristics were assessed.

RESULTS

The sample had a high proportion of non-white (78.9 %) and low income (39.6 %) children. Caregivers reported snoring for 20.7 % of the children and snoring was measured objectively for 21.9 %. Of those with objective snoring, only 29.7 % were identified as snorers by caregiver report (sensitivity: 0.30; specificity: 0.82). Primary Spanish language and co-sleeping were associated with increased caregiver reported snoring, and allergy was associated with increased objective snoring. Older child age and normal range BMI percentile were associated with higher concordance between caregiver and objective snoring.

CONCLUSIONS

Among a community-based, predominantly minority sample, caregiver-reported snoring resulted in under-estimation of prevalence of objectively assessed snoring. Reliance on caregiver report may poorly identify children with snoring or SDB in clinical practice.

A perspective on automated rapid eye movement sleep assessment

Rapid eye movement sleep is associated with distinct changes in various biomedical signals that can be easily captured during sleep, lending themselves to automated sleep staging using machine learning systems. Here, we provide a perspective on the critical characteristics of biomedical signals associated with rapid eye movement sleep and how they can be exploited for automated sleep assessment. We summarise key historical developments in automated sleep staging systems, having now achieved classification accuracy on par with human expert scorers and their role in the clinical setting. We also discuss rapid eye movement sleep assessment with consumer sleep trackers and its potential for unprecedented sleep assessment on a global scale. We conclude by providing a future outlook of computerised rapid eye movement sleep assessment and the role AI systems may play.

Don't hold PAT: watch for and correct oximetry artifact

This study evaluated the accuracy of the algorithmic oxygen saturation (SpO2) nadir detection of WatchPAT (Zoll/Itamar, Caesarea, Israel) compared with visual inspection in a real-world setting. SpO2 tracings for 209 consecutive adult WatchPAT recordings were reviewed for SpO2 artifact, with erroneous SpO2 data removed manually. Error rates for SpO2 minima were determined across all studies, and relationships between correct and erroneous studies examined. The overall error rate for SpO2 nadir was 22.5%. Erroneous studies had overall less time spent at SpO2 ≤ 88%, higher true SpO2 nadir, lower mean body mass index, and greater artifact time; however, these variables were not associated with the magnitude of discrepancy between manual and algorithmically derived SpO2 minima. These data demonstrate that SpO2 nadir determined by WatchPAT algorithms should not be considered universally accurate. Like other home sleep apnea tests, visual inspection and manual correction of the study data are often required to derive accurate clinical results.

CITATION

Plante DT, Rumble ME. Don't hold PAT: watch for and correct oximetry artifact. J Clin Sleep Med. 2023;19(12):2113-2116.

Characterization of sleep apnea among a sample of adults from Samoa

Sleep apnea is a public health concern around the world, but little research has been dedicated to examining this issue in low- and middle-income countries, including Samoa. Using data collected through the Soifua Manuia ("Good Health") study, which aimed to investigate the impact of the body mass index (BMI)-associated genetic variant rs373863828 in CREB3 Regulatory Factor ( CREBRF ) on metabolic traits in Samoan adults, we examined the sample prevalence and characteristics of sleep apnea using data collected with a validated home sleep apnea device (WatchPAT, Itamar). A total of 330 participants (sampled to overrepresent the obesity-risk allele of interest) had sleep data available. Participants (53.3% female) had a mean (SD) age of 52.0 (9.9) years and BMI of 35.5 (7.5) kg/m 2 and 36.3% of the sample had type 2 diabetes. Based on the 3% and 4% apnea hypopnea indices (AHI) and the 4% oxygen desaturation index (ODI), descriptive analyses revealed that many participants had potentially actionable sleep apnea defined as >5 events/hr (87.9%, 68.5%, and 71.2%, respectively) or clinically actionable sleep apnea defined as ≥15 events/hr (54.9%, 31.5%, and 34.5%, respectively). Sleep apnea was more severe in men; for example, clinically actionable sleep apnea (≥15) based on the AHI 3% definition was observed in 61.7% of men and 48.9% of women. Correction for non-representational sampling related to the CREBRF obesity-risk allele resulted in only slightly lower estimates. Across the AHI 3%, AHI 4%, and ODI 4%, multiple linear regression revealed associations between a greater number of events/hr and higher age, male sex, higher body mass index, higher abdominal-hip circumference ratio, and geographic region of residence. Our study identified a much higher frequency of sleep apnea in Samoa compared with published data from other studies, but similar predictors. Continued research addressing generalizability of these findings, as well as a specific focus on diagnosis and affordable and equitable access to treatment, is needed to alleviate the burden of sleep apnea in Samoa and around the world.

Perioperative management of Obstructive Sleep Apnoea: Present themes and future directions

PURPOSE OF REVIEW

Obstructive sleep apnoea (OSA) is an increasingly common pathology that all those involved in perioperative care will come across. Patients with the condition present a challenge at many stages along the perioperative journey, not least because many patients living with OSA are unaware of their diagnosis.Key interventions can be made pre, intra-, and postoperatively to improve outcomes. Knowledge of screening tools, diagnostic tests, and the raft of treatment options are important for anyone caring for these patients.

RECENT FINDINGS

Recent literature has highlighted the increasing complexity of surgical patients and significant underdiagnosis of OSA in this patient population. Work has demonstrated how and why patients with OSA are at a higher perioperative risk and that effective positive airways pressure (PAP) therapy can reduce these risks, alongside evidencing how best to optimise adherence to therapy, a key issue in OSA.

SUMMARY

OSA, and particularly undiagnosed OSA, presents a huge problem in the perioperative period. Perioperative PAP reduces the risk of postoperative complications but adherence remains an issue. Bespoke perioperative pathways should be developed to identify and optimise high risk patients, although at present evidence on how best to achieve this is lacking.

Peripheral arterial tonometry versus polysomnography in suspected obstructive sleep apnoea

BACKGROUND

Polysomnography (PSG) is the gold standard for the diagnosis of obstructive sleep apnoea (OSA). Home sleep apnoea testing with peripheral arterial tonometry (PAT) is a recommended diagnostic alternative for patients with an increased risk for OSA. In a large clinical cohort, we investigated concordance and predictors for discordance in diagnosing OSA using PAT and PSG, and three-year cardiovascular risk in patients with discordant OSA diagnosis.

METHODS

Retrospective monocentric cohort study. Patients with a PAT AHI ≥ 5/h followed by an in-hospital PSG within three months were included. All patients with a PAT AHI ≥ 5/h but a PSG AHI < 5/h were classified as discordant. Patients with PAT and PSG AHI ≥ 5/h were classified as concordant. To ascertain cardiovascular risk, major adverse cardiovascular events (MACE) were analyzed in discordant patients and sex, age, body mass index (BMI) and cardiovascular disease-matched concordant patients over a follow-up time of 3.1 ± 0.06 years.

RESULTS

A total of 940 patients, 66% male with an average age of 55 ± 0.4 years and BMI of 31 ± 0.2 kg/m² were included. Agreement in OSA diagnosis was observed in 80% of patients (55% in mild and 86% in moderate and severe OSA). Factors significantly associated with a discordant diagnosis were female sex, younger age and lower BMI, but not comorbidities. There was no significant difference in MACE (p = 0.920) between discordant patients (n = 155) and matched concordant patients (n = 274) with or without therapy.

CONCLUSIONS

Concordance between PAT and PSG diagnosis of sleep apnoea is good, particularly in moderate and severe OSA. Predictors for discordant results between PAT and PSG were age, sex and BMI. MACE risk is similar in those with OSA diagnosed by PAT or PSG.

Validity study of a multiscaled fusion network using single-lead electrocardiogram signals for obstructive sleep apnea diagnosis

STUDY OBJECTIVES

We evaluated the validity of a squeeze-and-excitation and multiscaled fusion network (SE-MSCNN) using single-lead electrocardiogram (ECG) signals for obstructive sleep apnea detection and classification.

METHODS

Overnight polysomnographic data from 436 participants at the Sleep Center of the First Affiliated Hospital of Sun Yat-sen University were used to generate a new FAH-ECG dataset comprising 260, 88, and 88 single-lead ECG signal recordings for training, validation, and testing, respectively. The SE-MSCNN was employed for detection of apnea-hypopnea events from the acquired ECG segments. Sensitivity, specificity, accuracy, and F1 scores were assigned to assess algorithm performance. We also used the SE-MSCNN to estimate the apnea-hypopnea index, classify obstructive sleep apnea severity, and compare the agreement between 2 sleep technicians.

RESULTS

The SE-MSCNN's accuracy, sensitivity, specificity, and F1 score on the FAH-ECG dataset were 86.6%, 83.3%, 89.1%, and 0.843, respectively. Although slightly inferior to previously reported results using public datasets, it is superior to state-of-the-art open-source models. Furthermore, the SE-MSCNN had good agreement with manual scoring, such that the Spearman's correlations for the apnea-hypopnea index between the SE-MSCNN and 2 technicians were 0.93 and 0.94, respectively. Cohen's kappa scores in classifying the SE-MSCNN and the 2 sleep technicians were 0.72 and 0.78, respectively.

CONCLUSIONS

In this study, we validated the use of the SE-MSCNN in a clinical environment, and despite some limitations the network appeared to meet the performance standards for generalizability. Therefore, updating algorithms based on single-lead ECG signals can facilitate the development of novel wearable devices for efficient obstructive sleep apnea screening.

CITATION

Yue H, Li P, Li Y, et al. Validity study of a multiscaled fusion network using single-lead electrocardiogram signals for obstructive sleep apnea diagnosis. J Clin Sleep Med. 2023;19(6):1017-1025.

Clinical impact of manual scoring of peripheral arterial tonometry in patients with sleep apnea

PURPOSE

The objective was to analyze the clinical implications of manual scoring of sleep studies using peripheral arterial tonometry (PAT) and to compare the manual and automated scoring algorithms.

METHODS

Patients with suspected sleep-disordered breathing underwent sleep studies using PAT. The recordings were analyzed using a validated automated computer-based scoring and a novel manual scoring algorithm. The two methods were compared regarding sleep stages and respiratory events.

RESULTS

Recordings of 130 patients were compared. The sleep stages and time were not significantly different between the scoring methods. PAT-derived apnea-hypopnea index (pAHI) was on average 8.4 events/h lower in the manually scored data (27.5±17.4/h vs.19.1±15.2/h, p<0.001). The OSA severity classification decreased in 66 (51%) of 130 recordings. A similar effect was found for the PAT-derived respiratory disturbance index with a reduction from 31.2±16.5/h to 21.7±14.4/h (p<0.001), for automated and manual scoring, respectively. A lower pAHI for manual scoring was found in all body positions and sleep stages and was independent of gender and body mass index. The absolute difference of pAHI increased with sleep apnea severity, while the relative difference decreased. Pearson's correlation coefficient between pAHI and oxygen desaturation index (ODI) significantly improved from 0.89 to 0.94 with manual scoring (p<0.001).

CONCLUSIONS

Manual scoring results in a lower pAHI while improving the correlation to ODI. With manual scoring, the OSA category decreases in a clinically relevant proportion of patients. Sleep stages and time do not change significantly with manual scoring. In the authors' opinion, manual oversight is recommended if clinical decisions are likely to change.

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.

ERS technical standards for using type III devices (limited channel studies) in the diagnosis of sleep disordered breathing in adults and children

For more than three decades, type III devices have been used in the diagnosis of sleep disordered breathing in supervised as well as unsupervised settings. They have satisfactory positive and negative predictive values for detecting obstructive and central sleep apnoea in populations with moderately high pre-test probability of symptoms associated with these events. However, standardisation of commercially available type III devices has never been undertaken and the technical specifications can vary widely. None have been subjected to the same rigorous processes as most other diagnostic modalities in the medical field. Although type III devices do not include acquisition of electroencephalographic signals overnight, the minimum number of physical sensors required to allow for respiratory event scoring using standards outlined by the American Academy of Sleep Medicine remains debatable. This technical standard summarises data on type III studies published since 2007 from multiple perspectives in both adult and paediatric sleep practice. Most importantly, it aims to provide a framework for considering current type III device limitations in the diagnosis of sleep disordered breathing while raising research- and practice-related questions aimed at improving our use of these devices in the present and future.

Obstructive sleep apnoea and perioperative medicine: a growing concern

Obstructive sleep apnoea represents a sizable public health and economic burden. Owing to rising obesity rates, the prevalence of obstructive sleep apnoea is increasing, and it is a condition that is significantly underdiagnosed. Exacerbated by the COVID-19 pandemic, the backlog of elective surgeries is also sizable and growing. A combination of these factors means that many patients due to have surgery will have obstructive sleep apnoea, either diagnosed or otherwise.

Patients with obstructive sleep apnoea have a significantly increased risk of operative complications, but the evidence base for optimum perioperative management of these patients is limited. This article reviews sleep apnoea, its prevalence and its impact on operative management and perioperative outcomes for patients. The evidence base for screening and treating undiagnosed obstructive sleep apnoea is also comprehensively assessed. Finally, a pathway to manage patients with possible undiagnosed obstructive sleep apnoea is proposed, and areas for further research identified.

Ketogenic dietary lifestyle intervention effects on sleep, cognition, and behavior in mild cognitive impairment: Study design

Introduction

Sleep and diet are modifiable risk factors for Alzheimer's disease (AD) that may be salient areas for the development of preventive intervention strategies against dementia in people with mild cognitive impairment (MCI). Sleep disturbances account for up to 15% of the population attributable risk for AD. Diet influences sleep quality, such that diets high in sugars, fat, and processed food affect sleep quality and cognition in older adults. The combination of poor sleep and diet health may increase risk for dementia in people with MCI, yet it is unknown how intervening on diet may influence sleep health.

Methods

The MCI Sleep Study assesses longitudinal changes in objective and subjective measures of sleep between two investigational diet groups in the Brain Energy for Amyloid Transformation in Alzheimer's Disease study: the modified Mediterranean ketogenic diet (MMKD) and the American Heart Association diet. Objective sleep assessments include an in-home sleep study using the WatchPAT Central Plus (Itamar Medical, Ltd) at baseline and the end of the 4-month diet intervention. Subjective sleep questionnaires include the Epworth Sleepiness Scale and Pittsburgh Sleep Quality Index. The MCI Sleep Study outcome measures include longitudinal change in cognitive performance, mood, behavior, and quality of life.

Results

Study recruitment is currently ongoing. We hypothesize the low-carb MMKD diet to have a beneficial impact on sleep health in individuals with MCI. Pre- and post-diet changes in sleep metrics across diet groups will be examined using mixed effects analysis of variance models.

Discussion

Early assessment of chronic sleep and diet behaviors may be vital in understanding when interventions are necessary and the lifestyle modifications that should accompany future AD prevention and therapy recommendations.

Home sleep apnea testing with peripheral arterial tonometry to assess outcome in upper airway stimulation

STUDY OBJECTIVES

To determine whether home sleep apnea testing with peripheral arterial tonometry (HSAT-PAT) can be used in upper airway stimulation to evaluate therapy success.

METHODS

Data analysis from 50 consecutive patients receiving upper airway stimulation was performed. Baseline values were measured by polysomnography and HSAT-PAT. Follow-up was performed during and after titration (3-6 months) by polysomnography and HSAT-PAT and after 1 year by HSAT-PAT only. Primary outcome measures were reduction in the apnea-hypopnea index and oxygen desaturation index. In addition, an analysis of night-to-night variability for HSAT-PAT was performed.

RESULTS

All 50 patients completed their posttitration visit (3-6 months) and 41 patients completed the 1-year follow-up. In HSAT-PAT after 1 year, the mean apnea-hypopnea index (desaturation 3%) was reduced from 29.5 ± 17.1 events/h to 19.9 ± 13.1 events/h (P < .01) and the oxygen desaturation index (desaturation 4%) was reduced from 17.8 ± 12.6 events/h to 10.2 ± 8.3 events/h (P < .01). Therapy adherence after 1 year was high (6.6 ± 1.9 hours per night) and led to improvement in daytime sleepiness, meaning a reduction in the Epworth Sleepiness Scale score from 12.8 ± 5.4 to 5.9 ± 4.0 (P < .01). Analysis of night-to-night variability showed similar apnea-hypopnea index values between the 2 nights.

CONCLUSIONS

Upper airway stimulation was able to reduce the apnea-hypopnea index and oxygen desaturation index after 1 year, as assessed by full-night efficacy studies with HSAT-PAT. In addition, improvements in self-reported outcome parameters were observed. The importance of publishing the scoring criteria is highlighted and whether data are based on full-night efficacy studies or a selected period of time from a sleep study. This is a prerequisite for comparing data with other trials in the emerging field of upper airway stimulation.

CITATION

Hinder D, Schams SC, Knaus C, Tschopp K. Home sleep apnea testing with peripheral arterial tonometry to assess outcome in upper airway stimulation. J Clin Sleep Med. 2022;18(9):2197-2205.

Diagnostic accuracy of home sleep apnea testing using peripheral arterial tonometry for sleep apnea: A systematic review and meta-analysis

This study aimed to evaluate the diagnostic accuracy of home sleep apnea testing using peripheral arterial tonometry for sleep apnea as an alternative to polysomnography. We conducted a systematic review and meta-analysis of observational studies, randomized controlled trials, and diagnostic case-control studies examining the diagnostic accuracy of peripheral arterial tonometry by searching the CENTRAL, MEDLINE, EMBASE, ICTRP and ClinicalTrials.gov databases on 5 October 2021. We assessed the risk of bias of the included studies using the Quality Assessment of Diagnostic Accuracy Studies-2 tool. A bivariate random-effects model was generated to derive the summary point estimates of sensitivity and specificity with 95% confidence intervals at different apnea-hypopnea index cutoffs. This meta-analysis included 13 studies (1227 participants, median prevalence of sleep apnea with apnea-hypopnea index ≥ 5 events per hr: 85%). The risk of bias in the included studies was low to moderate. The pooled sensitivity and specificity estimates were 96% (95% confidence interval: 93%-97%) and 44% (95% confidence interval: 32%-56%) at apnea-hypopnea index ≥ 5 events per hr, 88% (85%-91%) and 74% (63%-83%) at apnea-hypopnea index ≧ 15 events per hr, and 80% (66%-89%) and 90% (83%-95%) at apnea-hypopnea index ≧ 30 events per hr, respectively. Peripheral arterial tonometry resulted in a significant number of false negatives and false positives at any apnea-hypopnea index cutoff when applied to the median prevalence setting of the included studies. The inadequate sensitivity and specificity of peripheral arterial tonometry render it an unsuitable alternative to polysomnography for detecting sleep apnea for apnea-hypopnea index ≧ 5, 15 and 30 events per hr.

Transoral awake state neuromuscular electrical stimulation therapy for mild obstructive sleep apnea

Introduction

Obstructive sleep apnea (OSA) is a common disorder with major neurocognitive and cardiovascular sequelae. The treatment of symptomatic patients with mild OSA remains controversial given that adherence to positive airway pressure (PAP) has historically been suboptimal. With this notion in mind, we assessed a daily transoral neuromuscular electrical stimulation (NMES) device for individuals with mild OSA.

Methods

The sample represents a subset of participants with a baseline AHI 5–14.9 events/hour, drawn from a parent study which also included participants with primary snoring. Outcome measures for the current study included changes in apnea-hypopnea index (AHI), Epworth Sleepiness Scale (ESS), Pittsburgh Sleep Quality Index (PSQI) and snoring levels before and after use of the NMES. 

Results

Among 65 participants (68% men) with median age of 49 years (range 24 to 79) and median BMI of 27.7 kg/m2 (range 20 to 34), the NMES device was used daily for 6 weeks. We observed a significant improvement in the AHI from 10.2 to 6.8 events/hour among all participants and from 10.4 to 5.0 events/h among responders. Statistically significant improvements in the ESS, PSQI, objectively measured snoring, and bed partner-reported snoring were observed. Adherence among all participants was 85%.

Discussion

This NMES device has the benefit of being a treatment modality of daytime therapy which confers a high level of tolerability and patient acceptance. It alleviates the need for an in situ device during sleep and leads to improvements in OSA severity, snoring, and subjective sleep metrics, potentially crucial in mild OSA. Further studies are needed to define which individuals may benefit most from the device across the wider spectrum of OSA severity and assess long-term therapeutic outcomes.

Trial registration

ClinicalTrials.gov Identifier: NCT03829956.

A multicentric validation study of a novel home sleep apnea test based on peripheral arterial tonometry

STUDY OBJECTIVES

This paper reports on the multicentric validation of a novel FDA-cleared home sleep apnea test based on peripheral arterial tonometry (PAT HSAT).

METHODS

One hundred sixty-seven participants suspected of having obstructive sleep apnea (OSA) were included in a multicentric cohort. All patients underwent simultaneous polysomnography (PSG) and PAT HSAT, and all PSG data were independently double scored using both the recommended 1A rule for hypopnea, requiring a 3% desaturation or arousal (3% Rule), and the acceptable 1B rule for hypopnea, requiring a 4% desaturation (4% Rule). The double-scoring of PSG enabled a comparison of the agreement between PAT HSAT and PSG to the inter-rater agreement of PSG. Clinical endpoint parameters were selected to evaluate the device's ability to determine the OSA severity category. Finally, a correction for near-boundary apnea-hypopnea index values was proposed to adequately handle the inter-rater variability of the PSG benchmark.

RESULTS

For both the 3% and the 4% Rules, most endpoint parameters showed a close agreement with PSG. The 4-way OSA severity categorization accuracy of PAT HSAT was strong, but nevertheless lower than the inter-rater agreement of PSG (70% vs 77% for the 3% Rule and 78% vs 81% for the 4% Rule).

CONCLUSIONS

This paper reported on a multitude of robust endpoint parameters, in particular OSA severity categorization accuracies, while also benchmarking clinical performances against double-scored PSG. This study demonstrated strong agreement of PAT HSAT with PSG. The results of this study also suggest that different brands of PAT HSAT may have distinct clinical performance characteristics.

Correlations between home sleep apnea tests and polysomnography outcomes do not fully reflect the diagnostic accuracy of these tests

STUDY OBJECTIVES

The clinical performance of home sleep apnea tests (HSATs) can be described by their (diagnostic) accuracy, defined as the percentage agreement with the obstructive sleep apnea severity category (normal, mild, moderate, and severe) based on polysomnography. Rather than reporting on accuracy, there has been a strong reliance in the literature to report correlation coefficients between the apnea-hypopnea index of HSATs and polysomnography to support claims of diagnostic performance. This is surprising, as it has been well described that correlation coefficients are inadequate to evaluate equivalence between 2 parameters. The aim of this study was to systematically investigate the magnitude of the discrepancies between correlation coefficients and diagnostic accuracy reported in or retrievable from HSAT validation studies.

METHODS

We compared the discrepancy between accuracy and apnea-hypopnea index correlation coefficients of all validation papers that met the inclusion criteria. A total of 20 papers were retained, representing a participant pool of 1,652.

RESULTS

The weighted average apnea-hypopnea index correlation across all 20 papers was 0.82 and the weighted average accuracy was 0.61, highlighting a discrepancy of 0.21 and an overall misdiagnosis rate of 39%.

CONCLUSIONS

The results of our study confirm the need for increased scientific rigor in selecting primary performance endpoints to support clinical performance claims of HSATs.

CITATION

Massie F, Van Pee B, Bergmann J. Correlations between home sleep apnea tests and polysomnography outcomes do not fully reflect the diagnostic accuracy of these tests. J Clin Sleep Med. 2022;18(3):871-876.

Obstructive Sleep Apnea Detection Based on Sleep Sounds via Deep Learning

PURPOSE

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

METHODS

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

RESULTS

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

CONCLUSION

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

Sleep position, patient comfort, and technical performance with two established procedures for home sleep testing

Purpose

In patients with a high pre-test probability of suffering from obstructive sleep apnea (OSA), (cardio)-respiratory polygraphy (RP; level 3) is commonly used for home sleep testing (HST); however, testing based on peripheral arterial tonometry (PAT) is increasingly recognized as an alternative method. The aim of the study was to compare sleep position, patients’ comfort, and technical failure rates of HST with RP and PAT in patients with suspected OSA.

Methods

Sleep position, patients’ comfort, and technical failure rates of RP and PAT were compared in 56 patients receiving two nights of HST with either RP or PAT in a randomized fashion.

Results

Time in supine position with PAT was significantly lower (173.7±88 min) compared to RP (181.7±103.7 min; p < 0.001), although the absolute mean difference was not clinically significant. Patients reported to sleep better, feeling less disturbed when falling asleep, losing less sensors, and fewer nightly awakenings with PAT, but experienced more pain at the side of the finger probe. Forty-five out of 56 patients (80%) rated PAT as being the superior sleep test and 49 out of 56 (88%) would prefer PAT for further investigations (p<0.001). PAT testing was associated with less technical failures.

Conclusion

The results demonstrate that HST with PAT leads to less time in supine sleep positioning, which may be clinically relevant in selected patients. Moreover, PAT is associated with less technical failures and is perceived with less discomfort during testing and a reduced number of nocturnal awakenings in patient self-reports.

Peripheral arterial tonometry-PAT technology

PAT Technology is a plethysmographic based measurement method which facilitates the accurate recording of the pulsatile volume changes of the arteries of peripheral vascular beds at the distal end of the fingers over sustained periods of time. It represents a departure from previously available plethysmographic methods, in so far as it applies a uniform pressure field which completely envelopes the measured part of a digit, including its distal-most tip. Applying near diastolic blood pressure levels of pressure within the PAT probe optimizes the dynamic range of the signal, prevents confounding veno-arteriolar reflex vasoconstriction at the measurement site, reduces respiratory and movement artifacts and thus facilitates accurate long term measurement. The vascular bed of the distal phalanx of the finger is a major site of sympathetic nervous system mediated vasoconstrictor activity, and the PAT response to sympathetic changes provides a platform for accurate and robust measurement in a number of sleep and sleep related clinical areas, foremost as a patient friendly and extensively validated home sleep testing device.

Detection of obstructive sleep apnea using Belun Sleep Platform wearable with neural network-based algorithm and its combined use with STOP-Bang questionnaire

Many wearables allow physiological data acquisition in sleep and enable clinicians to assess sleep outside of sleep labs. Belun Sleep Platform (BSP) is a novel neural network-based home sleep apnea testing system utilizing a wearable ring device to detect obstructive sleep apnea (OSA). The objective of the study is to assess the performance of BSP for the evaluation of OSA. Subjects who take heart rate-affecting medications and those with non-arrhythmic comorbidities were included in this cohort. Polysomnography (PSG) studies were performed simultaneously with the Belun Ring in individuals who were referred to the sleep lab for an overnight sleep study. The sleep studies were manually scored using the American Academy of Sleep Medicine Scoring Manual (version 2.4) with 4% desaturation hypopnea criteria. A total of 78 subjects were recruited. Of these, 45% had AHI < 5; 18% had AHI 5-15; 19% had AHI 15-30; 18% had AHI ≥ 30. The Belun apnea-hypopnea index (bAHI) correlated well with the PSG-AHI (r = 0.888, P < 0.001). The Belun total sleep time (bTST) and PSG-TST had a high correlation coefficient (r = 0.967, P < 0.001). The accuracy, sensitivity, specificity in categorizing AHI ≥ 15 were 0.808 [95% CI, 0.703-0.888], 0.931 [95% CI, 0.772-0.992], and 0.735 [95% CI, 0.589-0.850], respectively. The use of beta-blocker/calcium-receptor antagonist and the presence of comorbidities did not negatively affect the sensitivity and specificity of BSP in predicting OSA. A diagnostic algorithm combining STOP-Bang cutoff of 5 and bAHI cutoff of 15 events/h demonstrated an accuracy, sensitivity, specificity of 0.938 [95% CI, 0.828-0.987], 0.944 [95% CI, 0.727-0.999], and 0.933 [95% CI, 0.779-0.992], respectively, for the diagnosis of moderate to severe OSA. BSP is a promising testing tool for OSA assessment and can potentially be incorporated into clinical practices for the identification of OSA. Trial registration: ClinicalTrial.org NCT03997916 https://clinicaltrials.gov/ct2/show/NCT03997916?term=belun+ring&draw=2&rank=1.

Phenotyping REM OSA by means of peripheral arterial tone-based home sleep apnea testing and polysomnography: A critical assessment of the sensitivity and specificity of both methods

The clinical relevance of rapid eye movement sleep-related obstructive sleep apnea (REM OSA) is supported by its associated adverse health outcomes and impact on optimal treatment strategies. To date, no assessment of REM OSA phenotyping performance has been conducted for any type of sleep testing technology. The objective of this study was to assess this for polysomnography and peripheral arterial tone-based home sleep apnea testing (PAT HSAT). In a dataset comprising 261 participants, the sensitivity and specificity of the agreement on REM OSA phenotyping was assessed for two independent scorings of polysomnography and a synchronously administered PAT HSAT. The sensitivity and specificity of REM OSA phenotyping were 0.87 and 0.89, respectively, for the polysomnography inter-scorer comparison, and 0.68 and 0.97 for the PAT HSAT on a single-night basis, using the conventional minimum required rapid eye movement sleep time of 30 min. Polysomnography-based REM OSA phenotyping was found to be sensitive and specific even for a single-night testing protocol. Peripheral arterial tone-based REM OSA phenotyping showed a lower sensitivity but a slightly higher specificity compared to polysomnography. In order to increase performance and conclusiveness of peripheral arterial tone-based REM OSA phenotyping, a multi-night protocol of 2-5 nights could be considered. Finally, the minimum required rapid eye movement sleep time could be lowered from the conventional 30 min to 15 min without significantly lowering REM OSA phenotyping sensitivity and specificity, while increasing the level of phenotyping conclusiveness.

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

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

The Future of Sleep Measurements: A Review and Perspective

This article provides an overview of the current use, limitations, and future directions of the variety of subjective and objective sleep assessments available. This article argues for various ways and sources of collecting, combining, and using data to enlighten clinical practice and the sleep research of the future. It highlights the prospects of digital management platforms to store and present the data, and the importance of codesign when developing such platforms and other new instruments. It also discusses the abundance of opportunities that data science and machine learning open for the analysis of data.

Performance of peripheral arterial tonometry-based testing for the diagnosis of obstructive sleep apnea in a large sleep clinic cohort

STUDY OBJECTIVES

Peripheral arterial tonometry (PAT)-based technology represents a validated portable monitoring modality for the diagnosis of OSA. We assessed the diagnostic accuracy of PAT-based technology in a large point-of-care cohort of patients studied with concurrent polysomnography (PSG).

METHODS

During study enrollment, all participants suspected to have OSA and tested by in-laboratory PSG underwent concurrent PAT device recordings.

RESULTS

Five hundred concomitant PSG and WatchPat tests were analyzed. Median (interquartile range) PSG AHI was 18 (8-37) events/h and PAT AHI_3% was 25 (12-46) events/h. Average bias was + 4 events/h. Diagnostic concordance was found in 42%, 41%, and 83% of mild, moderate, and severe OSA, respectively (accuracy = 53%). Among patients with PAT diagnoses of moderate or severe OSA, 5% did not have OSA and 19% had mild OSA; in those with mild OSA, PSG showed moderate or severe disease in 20% and no OSA in 30% of patients (accuracy = 69%). On average, using a 3% desaturation threshold, WatchPat overestimated disease prevalence and severity (mean + 4 events/h) and the 4% threshold underestimated disease prevalence and severity by -6 events/h.

CONCLUSIONS

Although there was an overall tendency to overestimate the severity of OSA, a significant percentage of patients had clinically relevant misclassifications. As such, we recommend that patients without OSA or with mild disease assessed by PAT undergo repeat in-laboratory PSG. Optimized clinical pathways are urgently needed to minimize therapeutic decisions instituted in the presence of diagnostic uncertainty.

Elevation of CD40/CD40L Inflammatory Pathway Molecules in Carotid Plaques from Moderate-and-Severe Obstructive Sleep Apnea Patients

A chronic inflammatory process characteristic of obstructive sleep apnea promotes vascular endothelial dysfunction and atherogenesis. This process can lead to destabilization and rupture of cardiovascular plaques, which clinically manifests as an acute coronary syndrome or stroke. The aim of this study was to investigate the inflammatory pathway leading to plaque destabilization in non-to-mild and moderate-to-severe groups of OSA patients. This prospective study involved enrollment of patients scheduled for endarterectomy. A sleep study was performed prior to surgery. Immunohistochemistry was performed on atherosclerotic plaques from carotid arteries obtained during standard open endarterectomy to determine levels of CD40, CD40L receptors, MCP-1, and MMP-9. The 46 patients included 14 controls, 13 with mild, 11 with moderate, and 8 with severe OSA. Increased expression of CD40, CD40L receptors, MCP-1, and MMP-9 were found to be proportionate with OSA severity. However, significant differences among groups were observed only for MCP-1 (p = 0.014). Increased expression of inflammatory markers (CD40, CD40L, MCP-1, MMP-9) is associated with increasing OSA severity. This suggests the CD40-CD4-L inflammatory pathway may contribute to plaque instability and rupture in OSA patients.

Night-to-night variability in obstructive sleep apnea using peripheral arterial tonometry: a case for multiple night testing

STUDY OBJECTIVES

Night-to-night variability of obstructive sleep apnea severity (OSA) is considerable and may depend on the diagnostic modality used. We investigated the night-to-night variability using peripheral arterial tonometry (PAT).

METHODS

Home sleep apnea testing was performed in 51 patients during three consecutive nights using PAT. Patients referred to our sleep clinic were screened and prospectively recruited for this study. All recordings were automatically and manually scored according to the PAT scoring guidelines.

RESULTS

No systematic differences in pAHI were found between the nights. The night-to-night variability was comparable between manually and automatically scored data. PAT-derived apnea-hypopnea index (pAHI) varied in 35% of patients more than 10/h between the nights. The OSA severity of 24% of patients was misclassified when using one night compared to the average of all nights. On average, pAHI varied by 57% from night-to-night. The variability of pAHI could partially be explained by the variability of time spent in the supine position with more time supine leading to a higher pAHI. On measuring a subsequent night, 12-14% of patients spontaneously fulfilled the commonly accepted criteria for treatment success without any intervention.

CONCLUSIONS

With repeated recordings of PAT, we found no first night effect. However, there is considerable night-to-night variability similar to values found for polysomnography, which can partially be explained by the variability of time spent in the supine position. OSA severity was frequently misclassified due to the night-to-night variability. Our findings make a strong case for multiple testing in the diagnostic work-up of OSA patients.

Evaluation and Management of Adults with Obstructive Sleep Apnea Syndrome

Obstructive sleep apnea syndrome (OSAS) is a common and underdiagnosed medical condition characterized by recurrent sleep-dependent pauses and reductions in airflow. While a narrow, collapsible oropharynx plays a central role in the pathophysiology of OSAS, there are other equally important nonanatomic factors including sleep-stage dependent muscle tone, arousal threshold, and loop gain that drive obstructive apneas and hypopneas. Through mechanisms of intermittent hypoxemia, arousal-related sleep fragmentation, and intrathoracic pressure changes, OSAS impacts multiple organ systems. Risk factors for OSAS include obesity, male sex, age, specific craniofacial features, and ethnicity. The prevalence of OSAS is rising due to increasing obesity rates and improved sensitivity in the tools used for diagnosis. Validated questionnaires have an important but limited role in the identification of patients that would benefit from formal testing for OSA. While an in-laboratory polysomnography remains the gold standard for diagnosis, the widespread availability and accuracy of home sleep apnea testing modalities increase access and ease of OSAS diagnosis for many patients. In adults, the most common treatment involves the application of positive airway pressure (PAP), but compliance continues to be a challenge. Alternative treatments including mandibular advancement device, hypoglossal nerve stimulator, positional therapies, and surgical options coupled with weight loss and exercise offer possibilities of an individualized personal approach to OSAS. Treatment of symptomatic patients with OSAS has been found to be beneficial with regard to sleep-related quality of life, sleepiness, and motor vehicle accidents. The benefit of treating asymptomatic OSA patients, particularly with regard to cardiovascular outcomes, is controversial and more data are needed.

Improving the performance of peripheral arterial tonometry-based testing for the diagnosis of obstructive sleep apnea

Outside sleep laboratory settings, peripheral arterial tonometry (PAT, eg, WatchPat) represents a validated modality for diagnosing obstructive sleep apnea (OSA). We have shown before that the accuracy of home sleep apnea testing by WatchPat 200 devices in diagnosing OSA is suboptimal (50%-70%). In order to improve its diagnostic performance, we built several models that predict the main functional parameter of polysomnography (PSG), Apnea Hypopnea Index (AHI). Participants were recruited in our Sleep Center and underwent concurrent in-laboratory PSG and PAT recordings. Statistical models were then developed to predict AHI by using robust functional parameters from PAT-based testing, in concert with available demographic and anthropometric data, and their performance was confirmed in a random validation subgroup of the cohort. Five hundred synchronous PSG and WatchPat sets were analyzed. Mean diagnostic accuracy of PAT was improved to 67%, 81% and 85% in mild, moderate-severe or no OSA, respectively, by several models that included participants' age, gender, neck circumference, body mass index and the number of 4% desaturations/hour. WatchPat had an overall accuracy of 85.7% and a positive predictive value of 87.3% in diagnosing OSA (by predicted AHI above 5). In this large cohort of patients with high pretest probability of OSA, we built several models based on 4% oxygen desaturations, neck circumference, body mass index and several other variables. These simple models can be used at the point-of-care, in order to improve the diagnostic accuracy of the PAT-based testing, thus ameliorating the high rates of misclassification for OSA presence or disease severity.