Snoring Sound Characteristics are Associated with Common Carotid Artery Profiles in Patients with Obstructive Sleep Apnea

Distinguishing severe sleep apnea from habitual snoring using a neck-wearable piezoelectric sensor and deep learning: A pilot study

This study explores the development of a deep learning model using a neck-wearable piezoelectric sensor to accurately distinguish severe sleep apnea syndrome (SAS) from habitual snoring, addressing the underdiagnosis of SAS in adults. From 2018 to 2020, 60 adult habitual snorers underwent polysomnography while wearing a neck piezoelectric sensor that recorded snoring vibrations (70-250 Hz) and carotid artery pulsations (0.01-1.5 Hz). The initial dataset comprised 1167 silence, 1304 snoring, and 399 noise samples from 20 participants. Using a hybrid deep learning model comprising a one-dimensional convolutional neural network and gated-recurrent unit, the model identified snoring and apnea/hypopnea events, with sleep phases detected via pulse wave variability criteria. The model's efficacy in predicting severe SAS was assessed in the remaining 40 participants, achieving snoring detection rates of 0.88, 0.86, and 0.92, with respective loss rates of 0.39, 0.90, and 0.23. Classification accuracy for severe SAS improved from 0.85 for total sleep time to 0.90 for partial sleep time, excluding the first sleep phase, demonstrating precision of 0.84, recall of 1.00, and an F1 score of 0.91. This innovative approach of combining a hybrid deep learning model with a neck-wearable piezoelectric sensor suggests a promising route for early and precise differentiation of severe SAS from habitual snoring, aiding guiding further standard diagnostic evaluations and timely patient management. Future studies should focus on expanding the sample size, diversifying the patient population, and external validations in real-world settings to enhance the robustness and applicability of the findings.

Vibro-Acoustic Platelet Activation: An Additive Mechanism of Prothrombosis with Applicability to Snoring and Obstructive Sleep Apnea

Introduction: Obstructive sleep apnea (OSA) and loud snoring are conditions with increased cardiovascular risk and notably an association with stroke. Central in stroke are thrombosis and thromboembolism, all related to and initiaing with platelet activation. Platelet activation in OSA has been felt to be driven by biochemical and inflammatory means, including intermittent catecholamine exposure and transient hypoxia. We hypothesized that snore-associated acoustic vibration (SAAV) is an activator of platelets that synergizes with catecholamines and hypoxia to further amplify platelet activation. Methods: Gel-filtered human platelets were exposed to snoring utilizing a designed vibro-acoustic exposure device, varying the time and intensity of exposure and frequency content. Platelet activation was assessed via thrombin generation using the Platelet Activity State assay and scanning electron microscopy. Comparative activation induced by epinephrine and hypoxia were assessed individually as well as additively with SAAV, as well as the inhibitory effect of aspirin. Results: We demonstrate that snore-associated acoustic vibration is an independent activator of platelets, which is dependent upon the dose of exposure, i.e., intensity x time. In snoring, acoustic vibrations associated with low-frequency sound content (200 Hz) are more activating than those associated with high frequencies (900 Hz) (53.05% vs. 22.08%, p = 0.001). Furthermore, SAAV is additive to both catecholamines and hypoxia-mediated activation, inducing synergistic activation. Finally, aspirin, a known inhibitor of platelet activation, has no significant effect in limiting SAAV platelet activation. Conclusion: Snore-associated acoustic vibration is a mechanical means of platelet activation, which may drive prothrombosis and thrombotic risk clinically observed in loud snoring and OSA.

Obstructive Sleep Apnea and Auditory Dysfunction—Does Snoring Sound Play a Role?

The objective of the study was to investigate the relationship between obstructive sleep apnea (OSA) and auditory dysfunction, and to clarify the role of snoring sounds in contributing to auditory dysfunction. A comprehensive assessment of OSA and the auditory system was performed, including overnight polysomnography, detection of the intra-ear canal snoring sound energy (SSE), pure tone average (PTA), tinnitus pitch matching, the tinnitus handicap inventory (THI), and the Epworth sleepiness scale (ESS). The patients were identified as having tinnitus if their THI score was higher than zero or their tinnitus pitches were matched to specific frequencies. The median age, body mass index, and apnea–hypopnea index score were 41 years, 26.4 kg/m², and 29.9 events/h, respectively. Among the 50 participants, 46 (92%) had a normal PTA, and only 4 (8%) patients had mild hearing loss. There was no significant difference in PTA among OSA severities (p = 0.52). Among the 50 participants, 33 patients (66%) were identified as having tinnitus. In the tinnitus group (n = 33), the ESS score (p = 0.01) and intra-ear canal SSE of 851–1500 Hz (p = 0.04) were significantly higher than those in the non-tinnitus group (n = 17). OSA patients with a higher ESS score had a higher risk of tinnitus (odds ratio 1.22 [95% CI: 1.01–1.46]). OSA-related auditory dysfunction emerged in tinnitus rather than in hearing impairment. OSA patients with daytime sleepiness had a higher risk of tinnitus. High-frequency SSE can jeopardize cochlea and is a potential mechanism contributing to tinnitus. Detection of snoring sounds through an intra-ear canal device may be more precise in assessing acoustic trauma from snoring sounds to vulnerable auditory system and thus warrants further research.

Association of Metabolic Syndrome With Long-Term Cardiovascular Risks and All-Cause Mortality in Elderly Patients With Obstructive Sleep Apnea

Background

Evidence suggests that an increased risk of major adverse cardiac events (MACE) and all-cause mortality is associated with obstructive sleep apnea (OSA), particularly in the elderly. Metabolic syndrome (MetS) increases cardiovascular risk in the general population; however, less is known about its influence in patients with OSA. We aimed to assess whether MetS affected the risk of MACE and all-cause mortality in elderly patients with OSA.

Methods

From January 2015 to October 2017, 1,157 patients with OSA, aged ≥60 years, no myocardial infarction (MI), and hospitalization for unstable angina or heart failure were enrolled at baseline and were followed up prospectively. OSA is defined as an apnea-hypopnea index of ≥5 events per hour, as recorded by polysomnography. Patients were classified on the basis of the presence of MetS, according to the definition of the National Cholesterol Education Program (NCEP). Incidence rates were expressed as cumulative incidence. Cox proportional hazards analysis was used to estimate the risk of all events. The primary outcomes were MACE, which included cardiovascular death, MI, and hospitalization for unstable angina or heart failure. Secondary outcomes were all-cause mortality, components of MACE, and a composite of all events.

Results

MetS was present in 703 out of 1,157 (60.8%) elderly patients with OSA. During the median follow-up of 42 months, 119 (10.3%) patients experienced MACE. MetS conferred a cumulative incidence of MACE in elderly patients with OSA (log-rank, P < 0.001). In addition, there was a trend for MACE incidence risk to gradually increase in individuals with ≥3 MetS components (P = 0.045). Multivariate analysis showed that MetS was associated with an incidence risk for MACE [adjusted hazard ratio (aHR), 1.86; 95% confidence interval (CI), 1.17–2.96; P = 0.009], a composite of all events (aHR, 1.54; 95% CI, 1.03–2.32; P = 0.036), and hospitalization for unstable angina (aHR, 2.01; 95% CI, 1.04–3.90; P = 0.039). No significant differences in the risk of all-cause mortality and other components of MACE between patients with and without MetS (P > 0.05). Subgroup analysis demonstrated that males (aHR, 2.23; 95% CI, 1.28–3.91, P = 0.05), individuals aged <70 years (aHR, 2.36; 95% CI, 1.27–4.39, P = 0.006), overweight and obese individuals (aHR, 2.32; 95% CI, 1.34–4.01, P = 0.003), and those with moderate-severe OSA (aHR, 1.81;95% CI: 1.05–3.12, P = 0.032) and concomitant MetS were at a higher risk for MACE.

Conclusion

MetS is common in elderly patients with OSA in the absence of MI, hospitalization for unstable angina or heart failure. Further, it confers an independent, increased risk of MACE, a composite of all events, and hospitalization for unstable angina. Overweight and obese males, aged <70 years with moderate-severe OSA combined with MetS presented a significantly higher MACE risk.

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.