The acoustics of snoring

Automatically detecting OSAHS patients based on transfer learning and model fusion

Objective. Snoring is the most typical symptom of obstructive sleep apnea hypopnea syndrome (OSAHS) that can be used to develop a non-invasive approach for automatically detecting OSAHS patients.Approach. In this work, a model based on transfer learning and model fusion was applied to classify simple snorers and OSAHS patients. Three kinds of basic models were constructed based on pretrained Visual Geometry Group-16 (VGG16), pretrained audio neural networks (PANN), and Mel-frequency cepstral coefficient (MFCC). The XGBoost was used to select features based on feature importance, the majority voting strategy was applied to fuse these basic models and leave-one-subject-out cross validation was used to evaluate the proposed model.Main results. The results show that the fused model embedded with top-5 VGG16 features, top-5 PANN features, and MFCC feature can correctly identify OSAHS patients (AHI > 5) with 100% accuracy.Significance. The proposed fused model provides a good classification performance with lower computational cost and higher robustness that makes detecting OSAHS patients at home possible.

Ultrasonic vocalisations during rapid eye movement sleep in the rat

Rats are known to use a 22-kHz ultrasonic vocalisation as a distress call to warn of danger to other members of their group. We monitored 22-kHz ultrasonic vocalisation emissions in rats (lean and obese) as part of a sleep deprivation study to detect the eventual presence of stress during the procedure. Unexpectedly, we detected ultrasonic vocalisation emission during rapid eye movement (REM) sleep, but not during non-REM (NREM) sleep, in all the rats. The event occurs during the expiratory phase and can take place singularly or as a train. No difference was detected in the number or duration of these events in lean versus obese rats, during the light versus the dark period, and after sleep deprivation. As far as we know, this is the first report showing that rats can vocalise during REM sleep.

SST: a snore shifted-window transformer method for potential obstructive sleep apnea patient diagnosis

Objective.Obstructive sleep apnea (OSA) is a high-incidence disease that is seriously harmful and potentially dangerous. The objective of this study was to develop a noncontact sleep audio signal-based method for diagnosing potential OSA patients, aiming to provide a more convenient diagnostic approach compared to the traditional polysomnography (PSG) testing.Approach.The study employed a shifted window transformer model to detect snoring audio signals from whole-night sleep audio. First, a snoring detection model was trained on large-scale audio datasets. Subsequently, the deep feature statistical metrics of the detected snore audio were used to train a random forest classifier for OSA patient diagnosis.Main results.Using a self-collected dataset of 305 potential OSA patients, the proposed snore shifted-window transformer method (SST) achieved an accuracy of 85.9%, a sensitivity of 85.3%, and a precision of 85.6% in OSA patient classification. These values surpassed the state-of-the-art method by 9.7%, 10.7%, and 7.9%, respectively.Significance.The experimental results demonstrated that SST significantly improved the noncontact audio-based OSA diagnosis performance. The study's findings suggest a promising self-diagnosis method for potential OSA patients, potentially reducing the need for invasive and inconvenient diagnostic procedures.

Regular snoring is associated with uncontrolled hypertension

Snoring may be a risk factor for cardiovascular disease independent of other co-morbidities. However, most prior studies have relied on subjective, self-report, snoring evaluation. This study assessed snoring prevalence objectively over multiple months using in-home monitoring technology, and its association with hypertension prevalence. In this study, 12,287 participants were monitored nightly for approximately six months using under-the-mattress sensor technology to estimate the average percentage of sleep time spent snoring per night and the estimated apnea-hypopnea index (eAHI). Blood pressure cuff measurements from multiple daytime assessments were averaged to define uncontrolled hypertension based on mean systolic blood pressure≥140 mmHg and/or a mean diastolic blood pressure ≥90 mmHg. Associations between snoring and uncontrolled hypertension were examined using logistic regressions controlled for age, body mass index, sex, and eAHI. Participants were middle-aged (mean ± SD; 50 ± 12 y) and most were male (88%). There were 2467 cases (20%) with uncontrolled hypertension. Approximately 29, 14 and 7% of the study population snored for an average of >10, 20, and 30% per night, respectively. A higher proportion of time spent snoring (75th vs. 5th; 12% vs. 0.04%) was associated with a ~1.9-fold increase (OR [95%CI]; 1.87 [1.63, 2.15]) in uncontrolled hypertension independent of sleep apnea. Multi-night objective snoring assessments and repeat daytime blood pressure recordings in a large global consumer sample, indicate that snoring is common and positively associated with hypertension. These findings highlight the potential clinical utility of simple, objective, and noninvasive methods to detect snoring and its potential adverse health consequences.

Obstructive sleep apnea diagnosis and beyond using portable monitors

Obstructive sleep apnea (OSA) is a chronic sleep and breathing disorder with significant health complications, including cardiovascular disease and neurocognitive impairments. To ensure timely treatment, there is a need for a portable, accurate and rapid method of diagnosing OSA. This review examines the use of various physiological signals used in the detection of respiratory events and evaluates their effectiveness in portable monitors (PM) relative to gold standard polysomnography. The primary objective is to explore the relationship between these physiological parameters and OSA, their application in calculating the apnea hypopnea index (AHI), the standard metric for OSA diagnosis, and the derivation of non-AHI metrics that offer additional diagnostic value. It is found that increasing the number of parameters in PMs does not necessarily improve OSA detection. Several factors can cause performance variations among different PMs, even if they extract similar signals. The review also highlights the potential of PMs to be used beyond OSA diagnosis. These devices possess parameters that can be utilized to obtain endotypic and other non-AHI metrics, enabling improved characterization of the disorder and personalized treatment strategies. Advancements in PM technology, coupled with thorough evaluation and validation of these devices, have the potential to revolutionize OSA diagnosis, personalized treatment, and ultimately improve health outcomes for patients with OSA. By identifying the key factors influencing performance and exploring the application of PMs beyond OSA diagnosis, this review aims to contribute to the ongoing development and utilization of portable, efficient, and effective diagnostic tools for OSA.

Physiological Determinants of Snore Loudness

Rationale: The physiological factors modulating the severity of snoring have not been adequately described. Airway collapse or obstruction is generally the leading determinant of snore sound generation; however, we suspect that ventilatory drive is of equal importance. Objective: To determine the relationship between airway obstruction and ventilatory drive on snore loudness. Methods: In 40 patients with suspected or diagnosed obstructive sleep apnea (1-98 events/hr), airflow was recorded via a pneumotachometer attached to an oronasal mask, ventilatory drive was recorded using calibrated intraesophageal diaphragm electromyography, and snore loudness was recorded using a calibrated microphone attached over the trachea. "Obstruction" was taken as the ratio of ventilation to ventilatory drive and termed flow:drive, i.e., actual ventilation as a percentage of intended ventilation. Lower values reflect increased flow resistance. Using 165,063 breaths, mixed model analysis (quadratic regression) quantified snore loudness as a function of obstruction, ventilatory drive, and the presence of extreme obstruction (i.e., apneic occlusion). Results: In the presence of obstruction (flow:drive = 50%, i.e., doubled resistance), snore loudness increased markedly with increased drive (+3.4 [95% confidence interval, 3.3-3.5] dB per standard deviation [SD] change in ventilatory drive). However, the effect of drive was profoundly attenuated without obstruction (at flow:drive = 100%: +0.23 [0.08-0.39] dB per SD change in drive). Similarly, snore loudness increased with increasing obstruction exclusively in the presence of increased drive (at drive = 200% of eupnea: +2.1 [2.0-2.2] dB per SD change in obstruction; at eupneic drive: +0.14 [-0.08 to 0.28] dB per SD change). Further, snore loudness decreased substantially with extreme obstruction, defined as flow:drive <20% (-9.9 [-3.3 to -6.6] dB vs. unobstructed eupneic breathing). Conclusions: This study highlights that ventilatory drive, and not simply pharyngeal obstruction, modulates snore loudness. This new framework for characterizing the severity of snoring helps better understand the physiology of snoring and is important for the development of technologies that use snore sounds to characterize sleep-disordered breathing.

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.

Snoring might be a warning sign for metabolic syndrome in nonobese Korean women

Metabolic syndrome (MetS) is an underlying cause of various diseases and is strongly associated with mortality. In particular, it has been steadily increasing along with changes in diet and lifestyle habits. The close relationship between sleep apnea and MetS is well established. In addition, these two diseases share a common factor of obesity and have a high prevalence among obese individuals. Nevertheless, the association can vary depending on factors, such as race and sex, and research on the relatively low obesity rates among East Asians is lacking. This study aimed to investigate the association between snoring and MetS in nonobese Koreans. A total of 2478 participants (827 men and 1651 women) were enrolled in the Korean National Health and Nutrition Examination Survey from 2019 to 2020. We used the National Cholesterol Education Program Adult Treatment Panel III criteria for MetS and a snoring questionnaire. Logistic regression analysis was used to measure the association between MetS and various confounding factors according to age and sex in participants with body mass index (BMI) < 23 kg/m2. MetS was significantly higher in participants with snoring than in those without snoring (26.9% vs. 19.6%; p = 0.007). In multivariate logistic regression analysis, age (odds ratio [OR] 1.070, 95% confidence interval [CI] 1.059-1.082, p < .001), sex (OR 1.531, 95% CI 1.139-2.058, p = 0.005), and snoring (OR 1.442, 95% CI 1.050-1.979, p = 0.024) were significantly associated with MetS in patients with a BMI < 23 kg/m2. Finally, regression analysis showed that snoring was significantly associated with MetS in women with a BMI of less than 23 kg/m2, especially with younger ages (40-49 years, OR 4.449, 95% CI 1.088 to 18.197, p = 0.038). Snoring was closely associated with MetS in women aged 40-50 years with a BMI of less than 23 kg/m2 compared to other participants. However, the association was not found in women aged 60 and over. Therefore, sufficient consideration should be given to the possibility of MetS when snoring is present in nonobese middle-aged Asian women.

AHI estimation of OSAHS patients based on snoring classification and fusion model

Obstructive sleep apnea-hypopnea syndrome (OSAHS) is a chronic and common sleep-breathing disease that could negatively influence lives of patients and cause serious concomitant diseases. Polysomnography(PSG) is the gold standard for diagnosing OSAHS, but it is expensive and requires overnight hospitalization. Snoring is a typical symptom of OSAHS. This study proposes an effective OSAHS screening method based on snoring sound analysis. Snores were labeled as OSAHS related snoring sounds and simple snoring sounds according to real-time PSG records. Three models were used, including acoustic features combined with XGBoost, Mel-spectrum combined with convolution neural network (CNN), and Mel-spectrum combined with residual neural network (ResNet). Further, the three models were fused by soft voting to detect these two types of snoring sounds. The subject's apnea-hypopnea index (AHI) was estimated according to these recognized snoring sounds. The accuracy and recall of the proposed fusion model achieved 83.44% and 85.27% respectively, and the predicted AHI has a Pearson correlation coefficient of 0.913 (R2 = 0.834, p < 0.001) with PSG. The results demonstrate the validity of predicting AHI based on analysis of snoring sound and show great potential for monitoring OSAHS at home.

Smart Devices Are Poised to Revolutionize the Usefulness of Respiratory Sounds

The association between breathing sounds and respiratory health or disease has been exceptionally useful in the practice of medicine since the advent of the stethoscope. Remote patient monitoring technology and artificial intelligence offer the potential to develop practical means of assessing respiratory function or dysfunction through continuous assessment of breathing sounds when patients are at home, at work, or even asleep. Automated reports such as cough counts or the percentage of the breathing cycles containing wheezes can be delivered to a practitioner via secure electronic means or returned to the clinical office at the first opportunity. This has not previously been possible. The four respiratory sounds that most lend themselves to this technology are wheezes, to detect breakthrough asthma at night and even occupational asthma when a patient is at work; snoring as an indicator of OSA or adequacy of CPAP settings; cough in which long-term recording can objectively assess treatment adequacy; and crackles, which, although subtle and often overlooked, can contain important clinical information when appearing in a home recording. In recent years, a flurry of publications in the engineering literature described construction, usage, and testing outcomes of such devices. Little of this has appeared in the medical literature. The potential value of this technology for pulmonary medicine is compelling. We expect that these tiny, smart devices soon will allow us to address clinical questions that occur away from the clinic.

Reliability of parental reporting of child snoring in children referred for obstructive sleep apnea

Despite the high number of studies based on subjective reports of snoring, self-reported snoring has hardly been validated at all. As there is no "gold-standard" for objective snoring measurements, studies must evaluate whether the presence of snoring based on parental judgement is linked to objective measurements of nasal and/or pharyngeal obstruction in children referred for obstructive sleep apnea. A total of 146 children (median age 11 years) underwent polysomnography (with snoring recording using nasal cannula signal), acoustic rhinometry and pharyngometry, while their parents filled out the Spruyt-Gozal questionnaire assessing both frequency and loudness of subjective snoring. Three categories were further differentiated (null, low and high) for both frequency and loudness. The apnea-hypopnea index was significantly different in the three groups for both frequency (p = 0.04) and loudness (p = 0.01) of subjective snoring. Children in the low or high groups (frequency or loudness), compared with those in the null group, experienced a decline in both pharyngeal (sitting and supine positions) and nasopharyngeal (supine position) volumes (frequency, pharynx sitting: p = 0.03; supine: 0.005 and nasopharynx: p = 0.002; loudness, p = 0.03; p = 0.007 and p = 0.03; three group comparisons). Objective snoring frequency during the night obtained with cannula was weakly related to loudness of subjective snoring but not to subjective snoring frequency during the week, and was biased by nasal obstruction. In conclusion, our study showed that parental assessment of snoring is related to a reduction in both pharyngeal and nasopharyngeal volumes in snorers, arguing for the adequacy of their evaluation of both snoring frequency and loudness.

Dependable algorithm for visualizing snoring duration through acoustic analysis: A pilot study

Snoring is a nuisance for the bed partners of people who snore and is also associated with chronic diseases. Estimating the snoring duration from a whole-night sleep period is challenging. The authors present a dependable algorithm for visualizing snoring durations through acoustic analysis. Both instruments (Sony digital recorder and smartphone's SnoreClock app) were placed within 30 cm from the examinee's head during the sleep period. Subsequently, spectrograms were plotted based on audio files recorded from Sony recorders. The authors thereby developed an algorithm to validate snoring durations through visualization of typical snoring segments. In total, 37 snoring recordings obtained from 6 individuals were analyzed. The mean age of the participants was 44.6 ± 9.9 years. Every recorded file was tailored to a regular 600-second segment and plotted. Visualization revealed that the typical features of the clustered snores in the amplitude domains were near-isometric spikes (most had an ascending-descending trend). The recorded snores exhibited 1 or more visibly fixed frequency bands. Intervals were noted between the snoring clusters and were incorporated into the whole-night snoring calculation. The correlative coefficients of snoring rates from digitally recorded files examined between Examiners A and B were higher (0.865, P < .001) than those with SnoreClock app and Examiners (0.757, P < .001; 0.787, P < .001, respectively). A dependable algorithm with high reproducibility was developed for visualizing snoring durations.

Association between snoring frequency and male serum testosterone: Findings from the 2015-2016 National Health and Nutrition Examination Survey

BACKGROUND

This study aimed to assess the association between snoring frequency and male serum testosterone levels.

METHODS

We analyzed data from the 2015 to 2016 National Health and Nutrition Examination Survey. Snoring frequency was relied on self-report, and was divided into never, rarely (1-2 nights a week), occasionally (3-4 nights a week), or frequently (5 or more nights a week) groups. Multivariable analysis controlling for age, race, waist circumference, total cholesterol, diabetes, and hypertension was used to evaluate the association between snoring frequency and male serum testosterone. Furthermore, we performed the subgroup analyses stratified by age and waist circumference.

RESULTS

Our analysis included 1900 participants. In the fully adjusted model, only frequent snoring was inversely associated with male serum testosterone (β -0.053, 95% CI -0.101 to -0.006, P = 0.028); According to the subgroup analysis stratified by age, only in 40-59 years group, frequent snoring was inversely associated with male serum testosterone in the fully adjusted model (β -0.113, 95% CI -0.196 to -0.031, P = 0.007). As for the subgroup analysis stratified by waist circumference, our results showed only in the waist circumference ≥102 cm group (abdominal obesity), frequent snoring was inversely associated with male serum testosterone (β -0.133, 95% CI -0.216 to -0.05, P = 0.002).

CONCLUSIONS

Frequent snoring (5 or more nights a week) is inversely associated with male serum testosterone levels, especially in those aged 40-59 years and those with abdominal obesity.

Association of Obstructive Sleep Apnea-Hypopnea Syndrome with hearing loss: A systematic review and meta-analysis

Objective

This study seeks to investigate the relationship between Obstructive Sleep Apnea-Hypopnea Syndrome (OSAHS) and hearing impairment by meta-analysis.

Methods

Cochrane Library, PubMed, Embase, Web of Science and other databases are searched from their establishment to July 1st, 2022. Literature on the relationship between OSAHS and hearing loss is collected, and two researchers independently perform screening, data extraction and quality evaluation on the included literature. Meta-analysis is performed using RevMan 5.4.1 software. According to the heterogeneity between studies, a random-effects model or fixed-effects model is used for meta-analysis.

Results

A total of 10 articles are included, with 7,867 subjects, 1,832 in the OSAHS group and 6,035 in the control group. The meta-analysis shows that the incidence of hearing impairment in the OSAHS group is higher than in the control group (OR = 1.38; 95% CI 1.18–1.62, Z = 4.09, P < 0.001), and the average hearing threshold of OSAHS patients is higher than that of the control group (MD = 5.89; 95% CI 1.87–9.91, Z = 2.87, P = 0.004). After stratifying the included studies according to hearing frequency, the meta-analysis shows that the OSAHS group has a higher threshold of 0.25, and the response amplitudes at frequencies 2, 4, 6, and 8 kHz are all higher than those of the control group.

Conclusion

Compared with the control group, the OSAHS group has a higher incidence of hearing loss, mainly high-frequency hearing loss. Thus, OSAHS is closely associated with and a risk factor for hearing loss.

Predicting upper airway collapse sites found in drug-induced sleep endoscopy from clinical data and snoring sounds in patients with obstructive sleep apnea: a prospective clinical study

STUDY OBJECTIVES

The primary aim was to predict upper airway collapse sites found in drug-induced sleep endoscopy (DISE) from demographic, anthropometric, clinical examination, sleep study, and snoring sound parameters in patients with obstructive sleep apnea (OSA). The secondary aim was to identify the above-mentioned parameters that are associated with complete concentric collapse of the soft palate.

METHODS

All patients with OSA who underwent DISE and simultaneous snoring sound recording were enrolled in this study. Demographic, anthropometric, clinical examination (viz., modified Mallampati classification and Friedman tonsil classification), and sleep study parameters were extracted from the polysomnography and DISE reports. Snoring sound parameters during DISE were calculated.

RESULTS

One hundred and nineteen patients with OSA (79.8% men; age = 48.1 ± 12.4 years) were included. Increased body mass index was found to be associated with higher probability of oropharyngeal collapse (P < .01; odds ratio = 1.29). Patients with a high Friedman tonsil score were less likely to have tongue base collapse (P < .01; odd ratio = 0.12) and epiglottic collapse (P = .01; odds ratio = 0.20) than those with a low score. A longer duration of snoring events (P = .05; odds ratio = 2.99) was associated with a higher probability of complete concentric collapse of the soft palate.

CONCLUSIONS

Within the current patient profile and approach, given that only a limited number of predictors were identified, it does not seem feasible to predict upper airway collapse sites found in DISE from demographic, anthropometric, clinical examination, sleep study, and snoring sound parameters in patients with OSA.

CITATION

Huang Z, Bosschieter PFN, Aarab G, et al. Predicting upper airway collapse sites found in drug-induced sleep endoscopy from clinical data and snoring sounds in obstructive sleep apnea patients: a prospective clinical study. J Clin Sleep Med. 2022;18(9):2119-2131.

Determining the Site of Upper Airway Narrowing in Snorers Using a Noninvasive Technique

Background

In this study, we aimed to determine the site of obstruction if surgical treatment is considered. Flexible nasopharyngoscopy is an invasive procedure currently used for the assessment of snoring and the level of obstruction. Here, we examine the role of Somnoscreen™ plus, a noninvasive cardiorespiratory polysomnographic device, in identifying the site of obstruction in patients presenting with snoring.

Methodology

This cross-sectional study was conducted in the Sleep Research Center at King Abdulaziz University Hospital. Polysomnography was conducted using Somnoscreen™ plus. All participants underwent flexible nasopharyngoscopy after polysomnography.

Results

Nasopharyngoscopy revealed that the most common site of obstruction was the nose and the soft palate (35.4%), followed by the soft palate alone (25%). Somnoscreen revealed that the site of obstruction was the nose and the soft palate in 18 (37.5%) patients and the nose alone in 16 (33.3%) patients. However, distal obstructions were not detected using Somnoscreen. The concordance of nasopharyngoscopy and Somnoscreen was 52.9%. However, it showed a discrepancy in identifying distal obstructions, which Somnoscreen™ plus failed to detect.

Conclusions

Somnoscreen appears to be sensitive for identifying proximal airway obstructions. The audio signal recordings can potentially be used as a tool to detect the site of airway obstruction in snoring; however, further studies are needed.

A Nationally Representative Survey Assessing Restorative Sleep in US Adults

Restorative sleep is a commonly used term but a poorly defined construct. Few studies have assessed restorative sleep in nationally representative samples. We convened a panel of 7 expert physicians and researchers to evaluate and enhance available measures of restorative sleep. We then developed the revised Restorative Sleep Questionnaire (REST-Q), which comprises 9 items assessing feelings resulting from the prior sleep episode, each with 5-point Likert response scales. Finally, we assessed the prevalence of high, somewhat, and low REST-Q scores in a nationally representative sample of US adults (n= 1,055) and examined the relationship of REST-Q scores with other sleep and demographic characteristics. Pairwise correlations were performed between the REST-Q scores and other self-reported sleep measures. Weighted logistic regression analyses were conducted to compare scores on the REST-Q with demographic variables. The prevalence of higher REST-Q scores (4 or 5 on the Likert scale) was 28.1% in the nationally representative sample. REST-Q scores positively correlated with sleep quality (r=0.61) and sleep duration (r=0.32), and negatively correlated with both difficulty falling asleep (r=-0.40) and falling back asleep after waking (r=-0.41). Higher restorative sleep scores (indicating more feelings of restoration upon waking) were more common among those who were: ≥60 years of age (OR=4.20, 95%CI: 1.92-9.17); widowed (OR=2.35, 95%CI:1.01-5.42), and retired (OR=2.02, 95%CI:1.30-3.14). Higher restorative sleep scores were less frequent among those who were not working (OR=0.36, 95%CI: 0.10-1.00) and living in a household with two or more persons (OR=0.51,95%CI:0.29-0.87). Our findings suggest that the REST-Q may be useful for assessing restorative sleep.

Towards Sleep Study Automation: Detection Evaluation of Respiratory-Related Events

The diagnosis of sleep disordered breathing depends on the detection of several respiratory-related events: apneas, hypopneas, snores, or respiratory event-related arousals from sleep studies. While a number of automatic detection methods have been proposed, reproducibility of these methods has been an issue, in part due to the absence of a generally accepted protocol for evaluating their results. With sleep measurements this is usually treated as a classification problem and the accompanying issue of localization is not treated as similarly critical. To address these problems we present a detection evaluation protocol that is able to qualitatively assess the match between two annotations of respiratory-related events. This protocol relies on measuring the relative temporal overlap between two annotations in order to find an alignment that maximizes their F1-score at the sequence level. This protocol can be used in applications which require a precise estimate of the number of events, total event duration, and a joint estimate of event number and duration. We assess its application using a data set that contains over 10,000 manually annotated snore events from 9 subjects, and show that when using the American Academy of Sleep Medicine Manual standard, two sleep technologists can achieve an F1-score of 0.88 when identifying the presence of snore events. In addition, we drafted rules for marking snore boundaries and showed that one sleep technologist can achieve F1-score of 0.94 at the same tasks. Finally, we compared our protocol against the protocol that is used to evaluate sleep spindle detection and highlighted the differences.

Comparison of Drug-Induced Sleep Endoscopy and Natural Sleep Endoscopy in the Assessment of Upper Airway Pathophysiology During Sleep: Protocol and Study Design

Study Objectives: Obstructive sleep apnea (OSA) is increasingly recognized as a complex and heterogenous disorder. As a result, a "one-size-fits-all" management approach should be avoided. Therefore, evaluation of pathophysiological endotyping in OSA patients is emphasized, with upper airway collapse during sleep as one of the main features. To assess the site(s) and pattern(s) of upper airway collapse, natural sleep endoscopy (NSE) is defined as the gold standard. As NSE is labor-intensive and time-consuming, it is not feasible in routine practice. Instead, drug-induced sleep endoscopy (DISE) is the most frequently used technique and can be considered as the clinical standard. Flow shape and snoring analysis are non-invasive measurement techniques, yet are still evolving. Although DISE is used as the clinical alternative to assess upper airway collapse, associations between DISE and NSE observations, and associated flow and snoring signals, have not been quantified satisfactorily. In the current project we aim to compare upper airway collapse identified in patients with OSA using endoscopic techniques as well as flow shape analysis and analysis of tracheal snoring sounds between natural and drug-induced sleep. Methods: This study is a blinded prospective comparative multicenter cohort study. The study population will consist of adult patients with a recent diagnosis of OSA. Eligible patients will undergo a polysomnography (PSG) with NSE overnight and a DISE within 3 months. During DISE the upper airway is assessed under sedation by an experienced ear, nose, throat (ENT) surgeon using a flexible fiberoptic endoscope in the operating theater. In contrast to DISE, NSE is performed during natural sleep using a pediatric bronchoscope. During research DISE and NSE, the standard set-up is expanded with additional PSG measurements, including gold standard flow and analysis of tracheal snoring sounds. Conclusions: This project will be one of the first studies to formally compare collapse patterns during natural and drug-induced sleep. Moreover, this will be, to the authors' best knowledge, the first comparative research in airflow shape and tracheal snoring sounds analysis between DISE and NSE. These novel and non-invasive diagnostic methods studying upper airway mechanics during sleep will be simultaneously validated against DISE and NSE. Clinical Trial Registration: www.ClinicalTrials.gov, identifier: NCT04729478.

Sleep Measurements in Women

Sleep in women and men have been studied in several studies with higher prevalence of sleep complaints in women compared with men. Several factors can affect sleep and could be argued to contribute to sex and gender differences in general sleep. There are no differences in guidelines when measuring sleep in women but several sleep assessment tools have been validated or compared between sexes. Because there is still a lack of knowledge on sleep measurements in women, the present review aimed to produce an overview of the current knowledge of objective and subjective sleep measurements in women.

Prediction of the obstruction sites in the upper airway in sleep-disordered breathing based on snoring sound parameters: a systematic review

BACKGROUND

Identification of the obstruction site in the upper airway may help in treatment selection for patients with sleep-disordered breathing. Because of limitations of existing techniques, there is a continuous search for more feasible methods. Snoring sound parameters were hypothesized to be potential predictors of the obstruction site. Therefore, this review aims to i) investigate the association between snoring sound parameters and the obstruction sites; and ii) analyze the methodology of reported prediction models of the obstruction sites.

METHODS

The literature search was conducted in PubMed, Embase.com, CENTRAL, Web of Science, and Scopus in collaboration with a medical librarian. Studies were eligible if they investigated the associations between snoring sound parameters and the obstruction sites, and/or reported prediction models of the obstruction sites based on snoring sound.

RESULTS

Of the 1016 retrieved references, 28 eligible studies were included. It was found that the characteristic frequency components generated from lower-level obstructions of the upper airway were higher than those generated from upper-level obstructions. Prediction models were built mainly based on snoring sound parameters in frequency domain. The reported accuracies ranged from 60.4% to 92.2%.

CONCLUSIONS

Available evidence points toward associations between the snoring sound parameters in the frequency domain and the obstruction sites in the upper airway. It is promising to build a prediction model of the obstruction sites based on snoring sound parameters and participant characteristics, but so far snoring sound analysis does not seem to be a viable diagnostic modality for treatment selection.

IoT snoring sound detector prototype as a model of future participatory healthcare

BACKGROUND

Traditional healthcare is centred around providing in-hospital services using hospital owned medical instruments. The COVID-19 pandemic has shown that this approach lacks flexibility to insure follow-up and treatment of common medical problems. In an alternative setting adapted to this problem, participatory healthcare can be considered centred around data provided by patients owning and operating medical data collection equipment in their homes.

OBJECTIVE

In order to trigger such a shift reliable and price attractive devices need to become available. Snoring, as a human sound production during sleep, can reflect sleeping behaviour and indicate sleep problems as an element of the overall health condition of a person.

METHODS

The use of off-the-shelf hardware from Internet of Things platforms and standard audio components allows the development of such devices. A prototype of a snoring sound detector with this purpose is developed.

RESULTS

The device, controlled by the patient and with specific snoring recording and analysing functions is demonstrated as a model for future participatory healthcare.

CONCLUSIONS

Design of monitoring devices following this model could allow market introduction of new equipment for participatory healthcare, bringing a care complementary to traditional healthcare to the reach of patients, and could result in benefits from enhanced patient participation.

Association of Snoring Characteristics with Predominant Site of Collapse of Upper Airway in Obstructive Sleep Apnoea Patients

STUDY OBJECTIVES

Acoustic analysis of isolated events and snoring by previous researchers suggests a correlation between individual acoustic features and individual site of collapse events. In this study, we hypothesised that multi-parameter evaluation of snore sounds during natural sleep would provide a robust prediction of the predominant site of airway collapse.

METHODS

The audio signals of 58 OSA patients were recorded simultaneously with full night polysomnography. The site of collapse was determined by manual analysis of the shape of the airflow signal during hypopnoea events and corresponding audio signal segments containing snore were manually extracted and processed. Machine learning algorithms were developed to automatically annotate the site of collapse of each hypopnoea event into three classes (lateral wall, palate and tongue-base). The predominant site of collapse for a sleep period was determined from the individual hypopnoea annotations and compared to the manually determined annotations. This was a retrospective study that used cross-validation to estimate performance.

RESULTS

Cluster analysis showed that the data fits well in two clusters with a mean silhouette coefficient of 0.79 and an accuracy of 68% for classifying tongue/non-tongue collapse. A classification model using linear discriminants achieved an overall accuracy of 81% for discriminating tongue/non-tongue predominant site of collapse and accuracy of 64% for all site of collapse classes.

CONCLUSIONS

Our results reveal that the snore signal during hypopnoea can provide information regarding the predominant site of collapse in the upper airway. Therefore, the audio signal recorded during sleep could potentially be used as a new tool in identifying the predominant site of collapse and consequently improving the treatment selection and outcome.

Audio source separation to reduce sleeping partner sounds: a simulation study

Objective.When recording a subject in an at-home environment for sleep evaluation or for other breathing disorder diagnoses using non-contact microphones, the breathing recordings (audio signals) can be distorted by sounds such as TV, outside noise, or air-conditioners. If two people are sleeping together, both may produce breathing/snoring sounds that need to be separated. In this study, we present signal processing and source separation algorithms for the enhancement of individual breathing/snoring audio signals in a simulated environment.Approach.We developed a computer simulation of mixed signals derived from genuine nocturnal recordings of 110 subjects. Two main source separation approaches were tested: (1) changing the basis vectors for the mixtures in the time domain (principal and independent component analysis, PCA/ICA) and (2) converting the mixtures to their time-frequency representations (degenerate un-mixing estimation technique, DUET). In addition to these source separation techniques, a beamforming approach was tested.Main results.The separation results with a reverberation time of 0.15 s and zero SNR between signals showed good performance (mean source to interference ratio (SIR): DUET = 12.831 dB, ICA = 3.388 dB, PCA = 4.452 dB), and for beamforming (SIR = -0.304 dB). To evaluate our source separation results, we propose two new measures: an evaluation measure based on a spectral similarity score (mel-SID) between the target source and its estimation (after separation) and a breathing energy ratio measure (BER). The results with the new proposed measures yielded comparable conclusions (mel-SID: DUET = 1.320, ICA = 2.732, PCA = 1.927, and beamforming = 2.590, BER: DUET = 10.241 dB, ICA = 0.270 dB, PCA = -2.847 dB, and beamforming = -1.151 dB), but better differentiated the differences between the performance of the algorithms. The DUET is superior on all measures. Its main advantage is that it only uses two microphones for separation.Significance. The separated audio signal can thus contribute to a more informed diagnosis of sleep-related and non-sleep-related diseases. The Institutional Review Committee of Soroka University Medical Center approved this study protocol (protocol number 10141) and all methods were performed in accordance with the relevant guidelines and regulations.

An OSAHS evaluation method based on multi-features acoustic analysis of snoring sounds

Snoring is the most direct symptom of obstructive sleep apnea hypopnea syndrome (OSAHS) and implies a lot of information about OSAHS symptoms. This paper aimed to identify OSAHS patients by analyzing acoustic features derived from overnight snoring sounds. Mel-frequency cepstral coefficients, 800 Hz power ratio, spectral entropy and other 10 acoustic features were extracted from snores, and Top-6 features were selected from the extracted 10 acoustic features by a feature selection algorithm based on random forest, then 5 kinds of machine learning models were applied to validate the effectiveness of Top-6 features on identifying OSAHS patients. The results showed that when the classification performance and computing efficiency were taken into account, the combination of logistic regression model and Top-6 features performed best and could successfully distinguish OSAHS patients from simple snorers. The proposed method provides a higher accuracy for evaluating OSAHS with lower computational complexity. The method has great potential prospect for the development of a portable sleep snore monitoring device.

The acoustical and perceptual features of snore-related sounds in patients with obstructive sleep apnea sleeping with the dynamic mandibular advancement system MATRx plus®

PURPOSE

The effect of snoring on the bed partner can be studied through the evaluation of in situ sound records by the bed partner or unspecialized raters as a proxy of real-life snoring perception. The aim was to characterize perceptual snore events through acoustical features in patients with obstructive sleep apnea (OSA) with an advanced mandibular position.

METHODS

Thirty-minute sound samples of 29 patients with OSA were retrieved from overnight, in-home recordings of a study to validate the MATRx plus® dynamic mandibular advancement system. Three unspecialized raters identified sound events and classified them as noise, snore, or breathing. The raters provided ratings for classification certainty and annoyance. Data were analyzed with respect to respiratory phases, and annoyance.

RESULTS

When subdividing perceptual events based on respiratory phase, the logarithm-transformed Mean Power, Spectral Centroid, and Snore Factor differed significantly between event types, although not substantially for the spectral centroid. The variability within event type was high and distributions suggested the presence of subpopulations. The general linear model (GLM) showed a significant patient effect. Inspiration segments occurred in 65% of snore events, expiration segments in 54%. The annoyance correlated with the logarithm of mean power (r = 0.48) and the Snore Factor (0.46).

CONCLUSION

Perceptual sound events identified by non-experts contain a non-negligible mixture of expiration and inspiration phases making the characterization through acoustical features complex. The present study reveals that subpopulations may exist, and patient-specific features need to be introduced.

Can Machine Learning Assist Locating the Excitation of Snore Sound? A Review

In the past three decades, snoring (affecting more than 30 % adults of the UK population) has been increasingly studied in the transdisciplinary research community involving medicine and engineering. Early work demonstrated that, the snore sound can carry important information about the status of the upper airway, which facilitates the development of non-invasive acoustic based approaches for diagnosing and screening of obstructive sleep apnoea and other sleep disorders. Nonetheless, there are more demands from clinical practice on finding methods to localise the snore sound's excitation rather than only detecting sleep disorders. In order to further the relevant studies and attract more attention, we provide a comprehensive review on the state-of-the-art techniques from machine learning to automatically classify snore sounds. First, we introduce the background and definition of the problem. Second, we illustrate the current work in detail and explain potential applications. Finally, we discuss the limitations and challenges in the snore sound classification task. Overall, our review provides a comprehensive guidance for researchers to contribute to this area.

Validation of snoring detection using a smartphone app

Purpose

Snoring is closely related to obstructive sleep apnea in adults. The increasing abundance and availability of smartphone technology has facilitated the examination and monitoring of snoring at home through snoring apps. However, the accuracy of snoring detection by snoring apps is unclear. This study explored the snoring detection accuracy of Snore Clock—a paid snoring detection app for smartphones.

Methods

Snoring rates were detected by smartphones that had been installed with the paid app Snore Clock. The app provides information on the following variables: sleep duration, snoring duration, snoring loudness (in dB), maximum snoring loudness (in dB), and snoring duration rate (%). In brief, we first reviewed the snoring rates detected by Snore Clock; thereafter, an ear, nose, and throat specialist reviewed the actual snoring rates by using the playback of the app recordings.

Results

In total, the 201 snoring records of 11 patients were analyzed. Snoring rates measured by Snore Clock and those measured manually were closely correlated (r = 0.907). The mean snoring detection accuracy rate of Snore Clock was 95%, with a positive predictive value, negative predictive value, sensitivity, and specificity of 65% ± 35%, 97% ± 4%, 78% ± 25%, and 97% ± 4%, respectively. However, the higher the snoring rates, the higher were the false-negative rates for the app.

Conclusion

Snore Clock is compatible with various brands of smartphones and has a high predictive value for snoring. Based on the strong correlation between Snore Clock and manual approaches for snoring detection, these findings have validated that Snore Clock has the capacity for at-home snoring detection.

Audio-based snore detection using deep neural networks

BACKGROUND AND OBJECTIVE

Snoring is a prevalent phenomenon. It may be benign, but can also be a symptom of obstructive sleep apnea (OSA) a prevalent sleep disorder. Accurate detection of snoring may help with screening and diagnosis of OSA.

METHODS

We introduce a snore detection algorithm based on the combination of a convolutional neural network (CNN) and a recurrent neural network (RNN). We obtained audio recordings of 38 subjects referred to a clinical center for a sleep study. All subjects were recorded by a total of 5 microphones placed at strategic positions around the bed. The CNN was used to extract features from the sound spectrogram, while the RNN was used to process the sequential CNN output and to classify the audio events to snore and non-snore events. We also addressed the impact of microphone placement on the performance of the algorithm.

RESULTS

The algorithm achieved an accuracy of 95.3 ± 0.5%, a sensitivity of 92.2 ± 0.9%, and a specificity of 97.7 ± 0.4% over all microphones in snore detection on our data set including 18412 sound events. The best accuracy (95.9%) was observed from the microphone placed about 70 cm above the subject's head and the worst (94.4%) was observed from the microphone placed about 130 cm above the subject's head.

CONCLUSION

Our results suggest that our method detects snore events from audio recordings with high accuracy and that microphone placement does not have a major impact on detection performance.

Estimating a Sleep Apnea Hypopnea Index Based on the ERB Correlation Dimension of Snore Sounds

This paper proposes a new perspective of analyzing non-linear acoustic characteristics of the snore sounds. According to the ERB (Equivalent Rectangular Bandwidth) scale used in psychoacoustics, the ERB correlation dimension (ECD) of the snore sound was computed to feature different severity levels of sleep apnea hypopnea syndrome (SAHS). For the training group of 93 subjects, snore episodes were manually segmented and the ECD parameters of the snores were extracted, which established the gaussian mixture models (GMM). The nocturnal snore sound of the testing group of another 120 subjects was tested to detect SAHS snores, thus estimating the apnea hypopnea index (AHI), which is called AHIECD. Compared to the AHIPSG value of the gold standard polysomnography (PSG) diagnosis, the estimated AHIECD achieved an accuracy of 87.5% in diagnosis the SAHS severity levels. The results suggest that the ECD vectors can be effective parameters for screening SAHS.

Methods for Adventitious Respiratory Sound Analyzing Applications Based on Smartphones: A Survey

Detection and classification of adventitious acoustic lung sounds plays an important role in diagnosing, monitoring, controlling and, caring the patients with lung diseases. Such systems can be presented as different platforms like medical devices, standalone software or smartphone application. Ubiquity of smartphones and widespread use of the corresponding applications make such a device an attractive platform for hosting the detection and classification systems for adventitious lung sounds. In this paper, the smartphone-based systems for automatic detection and classification of the adventitious lung sounds are surveyed. Such adventitious sounds include cough, wheeze, crackle and, snore. Relevant sounds related to abnormal respiratory activities are considered as well. The methods are shortly described and the analyzing algorithms are explained. The analysis includes detection and/or classification of the sound events. A summary of the main surveyed methods together with the classification parameters and used features for the sake of comparison is given. Existing challenges, open issues and future trends will be discussed as well.

Nocturnal awakenings of Brazilian immigrants in Massachusetts

OBJECTIVE

The purpose of this study was to assess the relationship between the quantity of jobs and nocturnal awakenings of Brazilians living in Massachusetts.

MATERIAL AND METHODS

We sampled of 48 documented Brazilians around the age of 45.5 years old. 52.1% of them were women. Data gathering occurred for three weeks, using the Pittsburgh Sleep Quality Index. Participants also wore wrist actigraph and filled sleep/wake diary for a week.

RESULTS

The sleep quality of immigrants with one job (mean=8.58, SD=4.16) is better when compared to immigrants with 2-3 jobs (mean=12.7, SD=3.57) according to the PSQI scores. Immigrants with 2-3 jobs reported dissatisfaction on three components of the scale: sleep duration, sleep efficiency and sleep quality.

DISCUSSION

There is a positive relationship between the quantity of jobs and nocturnal awakenings and between nocturnal awakenings and complaints related to sleep apnea among Brazilians in Massachusetts. The assessment of systemic morbidities associated with sleep pattern changes should be considered in future research.

An automated snoring sound classification method based on local dual octal pattern and iterative hybrid feature selector

In this research, a novel snoring sound classification (SSC) method is presented by proposing a new feature generation function to yield a high classification rate. The proposed feature extractor is named as Local Dual Octal Pattern (LDOP). A novel LDOP based SSC method is presented to solve the low success rate problems for Munich-Passau Snore Sound Corpus (MPSSC) dataset. Multilevel discrete wavelet transform (DWT) decomposition and the LDOP based feature generation, informative features selection with ReliefF and iterative neighborhood component analysis (RFINCA), and classification using k nearest neighbors (kNN) are fundamental phases of the proposed SSC method. Seven leveled DWT transform, and LDOP are used together to generate low, medium, and high levels features. This feature generation network extracts 4096 features in total. RFINCA selects 95 the most discriminative and informative ones of these 4096 features. In the classification phase, kNN with leave one out cross-validation (LOOCV) is used. 95.53% classification accuracy and 94.65% unweighted average recall (UAR) have been achieved using this method. The proposed LDOP based SSC method reaches 22% better result than the best of the other state-of-the-art machine learning and deep learning-based methods. These results clearly denote the success of the proposed SSC method.

Polysomnographic characteristics and acoustic analysis of catathrenia (nocturnal groaning)

OBJECTIVE

Catathrenia is a sleep disorder characterized by nocturnal groaning sounds emitted during prolonged expiration. As a rare condition, its polysomnographic findings were inconsistent. We aimed to present polysomnographic characteristics of catathrenia patients and perform acoustic analysis of groaning sounds.

APPROACH

Twenty-three patients (eight males and 15 females) diagnosed with catathrenia by video-polysomnography were included. They underwent clinical evaluation and physical examination, and answered a questionnaire. Acoustic analyses (oscillograms and spectrograms) of catathrenia and snoring signals were performed by Praat 6.1.09. Sounds were classified according to Yanagihara criteria.

MAIN RESULTS

The average age of catathrenia patients was 29.6 ± 10.0 years, with a body mass index of 22.3 ± 5.1 kg m^-2. A total of 3728 groaning episodes were documented. Catathrenia events of 16 patients (70%) were rapid eye movement (REM)-predominant. The average duration of groaning was 11.4 ± 4.6 s, ranging from 1.3 to 74.9 s. All signals of groaning were rhythmic or semi-rhythmic, classified as type I and type II, respectively, with formants and harmonics. Snoring events were observed in nine patients. Snoring mainly occurred in the non-REM stage, with a duration of less than 1.5 s. Signals of snoring were chaotic, classified as type III, without harmonics.

SIGNIFICANCE

Catathrenia occurred in all sleep stages but mainly in REM. Durations of groaning varied greatly across patients. Acoustic characteristics of catathrenia were typical. Groaning had rhythmic or semi-rhythmic waveform, formants and harmonics, indicating vocal origin, while snoring had chaotic waveform.

Use of mandibular advancement devices for the treatment of primary snoring with or without obstructive sleep apnea (OSA): A systematic review

The aim of this review was to systematically evaluate the available scientific evidence on the benefit of mandibular advancement devices (MADs) in the treatment of primary snoring (PS). From 905 initially identified articles, 18 were selected. Papers that provided indirect information regarding obstructive sleep apnea syndrome (OSAS) and/or sleep breathing disorders (SBD) were included. Information was obtained on monoblock and duoblock appliances from the selected studies. The devices were most commonly able to achieve 50%-70% of the maximum mandibular protrusion. The frequently used outcome measurements were the apnea-hypopnea index, Epworth sleepiness scale, and oxygen desaturation index, which all yielded positive post-treatment results. The most common side effects were temporomandibular joint pain and excessive salivation, which improved with time. Our findings indicated that the use of MADs, even with varying designs, improved outcomes in all the reported patient populations (PS, OSAS, and SBD). Despite the lack of studies on PS, the available evidence supports the use of MADs for treatment of PS. Snoring should be treated from a preventive and psychosocial perspective to avoid progression to more severe diseases that could have a significant medical and economic impact.

Influence of age and gender on sleep bruxism and snoring in non-apneic snoring patients: A polysomnographic study

The present study aimed to assess the influence of gender and age on snoring and sleep bruxism in non-apneic snoring patients. Adult participants with clinical suspicion of snoring and with no other significant medical history were recruited. Single-night video polysomnography was performed to detect snoring and sleep bruxism. Finally, 137 snoring non-apneic participants were included. Statistical analysis of gender groups showed that the total snore index and snore train were significantly higher in men than in women. Men also presented severe bruxism, with significantly more frequent episodes and higher bruxism episodes index scores. The correlation analysis showed the presence of significant linear relationships in the supine sleep position between age and snore index, snore index in non-rapid eye movement 2 (N2) sleep stage, and snore train. The analysis of groups separated according to the criterion of third age quartile showed that the average, maximum and minimum audio volume in the non-supine sleep position was significantly higher in the older group. The analysis of groups separated according to the criterion of median age showed that the bruxism episode index and bruxism phasic episodes were significantly higher in the younger group. Thus, it can be concluded that both age and gender influence snoring and sleep bruxism. Snoring and sleep bruxism seem to be more intensive in men. Older patients seem to snore more in N2 sleep and the supine sleep position and present lower bruxism episodes, especially the phasic type. The results of the present study indicate the need for further research on this topic to establish the possible relationship between snoring and sleep bruxism.

Acoustic analyses of snoring sounds using a smartphone in patients undergoing septoplasty and turbinoplasty

PURPOSE

Several studies have been performed using recently developed smartphone-based acoustic analysis techniques. We investigated the effects of septoplasty and turbinoplasty in patients with nasal septal deviation and turbinate hypertrophy accompanied by snoring by recording the sounds of snoring using a smartphone and performing acoustic analysis.

METHODS

A total of 15 male patients who underwent septoplasty with turbinoplasty for snoring and nasal obstruction were included in this prospective study. Preoperatively and 2 months after surgery, their bed partners or caregivers were instructed to record the snoring sounds. The intensity (dB), formant frequencies (F₁, F₂, F₃, and F₄), spectrogram pattern, and visual analog scale (VAS) score were analyzed for each subject.

RESULTS

Overall snoring sounds improved after surgery in 12/15 (80%) patients, and there was significant improvement in the intensity of snoring sounds after surgery (from 64.17 ± 12.18 dB to 55.62 ± 9.11 dB, p = 0.018). There was a significant difference in the F₁ formant frequency before and after surgery (p = 0.031), but there were no significant differences in F₂, F₃, or F₄. The change in F₁ indicated that patients changed from mouth breathing to normal breathing. The degree of subjective snoring sounds improved significantly after surgery (VAS: from 5.40 ± 1.55 to 3.80 ± 1.26, p = 0.003).

CONCLUSION

Our results confirm that snoring is reduced when nasal congestion is improved, and they demonstrate that smartphone-based acoustic analysis of snoring sounds can be useful for diagnosis.

Snoring time versus snoring intensity: Which parameter correlates better with severity of obstructive sleep apnea syndrome?

Objective:

The relationship between the severity of obstructive sleep apnea syndrome (OSAS) and both snoring intensity and rate measured objectively has not been sufficiently investigated. The aim of this study was to evaluate the relationship between severity of OSAS and snoring parameters including snoring intensity and rate.

Patients and Methods:

A total of 150 records of individuals who complained of snoring were analyzed. Patients were classified into four groups according to apnea–hypopnea index (AHI). Polygraphy recordings including the snoring intensity and the snoring rate (defined as the percentage of snoring time during the total sleep time) and the clinical data were compared and analyzed.

Results:

AHI was significantly correlated, respectively, with snoring rate (r = 0.341; P < 0.0001) and maximal intensity of snoring (r = 0.362; P < 0.0001). However, no correlation was found between the average intensity of snoring and AHI (P = 0.33). When assessing each respiratory event individually, snoring rate was more correlated with hypopnea index (r = 0.424; P < 0.0001) than with AI (r = 0.233; P = 0.004). The snoring rate (%) in the severe OSAS group (31.79 ± 19.3) was significantly higher than that in the mild OSAS group (18.02 ± 17; P = 0.001) and the control group (17 ± 16.57; P = 0.011). Similarly, the maximal intensity of snoring (db) in the severe OSAS group (90.45 ± 13.79) was higher than that in the mild OSAS group (86.46 ± 15.07; P = 0.006) and the control group (84.75 ± 6.65; P < 0.001).

Conclusion:

The snoring rate and maximal intensity of snoring correlate better with the severity of OSAS than average snoring intensity.

Diagnosis and treatment of isolated snoring-open questions and areas for future research

STUDY OBJECTIVES

Snoring is a common phenomenon which is generated by vibration of soft tissue of the upper airway during sleep. Due to the high incidence of isolated snoring and the substantial burden for the patient and the bed partner, a thorough examination and appropriate therapy are required. Many recommendations for the treatment of isolated snoring are either not evidence-based or are derived from recommendations for the management of obstructive sleep apnea. Therefore, the aim of this study is the identification and description of open questions in the diagnosis and treatment of isolated snoring and the illustration of areas for further research.

METHODS

In the context of the development of the new version of the German guideline "Diagnosis and treatment of isolated snoring in adults," a multidisciplinary team of experts performed a systematic literature search on the relevant medical data and rated the current evidence regarding the key diagnostic and therapeutic measures for snoring.

RESULTS

The systematic literature review identified 2293 articles. As a major inclusion criterion, only studies on primary snoring based on objective sleep medical assessment were selected. After screening and evaluation, 33 full-text articles remained for further analysis. Based on these articles, open questions and areas for future research were identified for this review.

CONCLUSION

Several major gaps in the literature on the diagnosis and treatment of isolated snoring were identified. For the majority of diagnostic and therapeutic measures for snoring, high-level scientific evidence is still lacking.

Vibration pattern recognition using a compressed histogram of oriented gradients for snoring source analysis

BACKGROUND

Snoring source analysis is essential for an appropriate surgical decision for both simple snorers and obstructive sleep apnea/hypopnea syndrome (OSAHS) patients.

OBJECTIVE

As snoring sounds carry significant information about tissue vibrations within the upper airway, a new feature entitled compressed histogram of oriented gradients (CHOG) is proposed to recognize vibration patterns of the snoring source acoustically by compressing histogram of oriented gradients (HOG) descriptors via the multilinear principal component analysis (MPCA) algorithm.

METHODS

Each vibration pattern corresponds to a sole or combinatorial vibration among the four upper airway soft tissues of soft palate, lateral pharyngeal wall, tongue base, and epiglottis. 1037 snoring events from noncontact sound recordings of 76 simple snorers or OSAHS patients during drug-induced sleep endoscopy (DISE) were evaluated.

RESULTS

With a support vector machine (SVM) as the classifier, the proposed CHOG achieved a recognition accuracy of 89.8% for the seven observable vibration patterns of the snoring source categorized in our most recent work.

CONCLUSION

The CHOG outperforms other single features widely used for acoustic analysis of sole vibration site.

The Associations of Gender, Menopause, Age, and Asthma with REM-Predominant Obstructive Sleep Apnea: A Prospective Observational Study

PURPOSE

The study sought to assess demographics, clinical features, comorbidities, and polysomnographic features of a large cohort of clinic-based patients with rapid eye movement-predominant obstructive sleep apnea (REM-predominant-OSA) in both genders, while assessing the relationship between REM-predominant OSA in one hand and menopausal status and age on the other.

METHODS

This prospective observational study was conducted between January 2003 and December 2017. REM-predominant OSA diagnostic criteria included an AHI of ≥5/h, with REM-AHI/non-REM-AHI of >2, a non-REM-AHI of <15/h, and a minimum of 15 min of REM sleep. Patients who had an AHI>5 events/h and did not meet the criteria for REM-predominant OSA were included in the non-stage-specific OSA group (NSS).

RESULTS

The study consisted of 1346 men and 823 women (total=2169). REM-predominant OSA was diagnosed in 17% (n=369). The prevalence of REM-predominant OSA in women was 25% compared with 12% in men. Several independent associations of REM-predominant OSA were identified in the whole group, including age (OR: 0.97 [0.95-0.98], p<0.01), female sex (OR: 6.95 [4.86-9.93], p>0.01), REM sleep duration (min) (OR: 1.02 [1.02-1.03], < 0.01), and time with SpO2 <90% (mins) (OR: 0.97 [0.95-0.99], < 0.01), hypertension (OR:0.67 [0.45-0.99], 0.04) and asthma (OR: 2.19 [1.56-3.07], < 0.01). The prevalence of REM-predominant OSA in premenopausal and postmenopausal women was 35% and 18.6% (p< 0.01), respectively. Among women, age was an independent correlate (OR: 0.97 [0.94-0.99], p=0.03; however, menopausal status was not.

CONCLUSION

REM-predominant OSA is prevalent among clinic-based patients with OSA. A younger age and female sex were independent correlates of REM-predominant OSA. Among women, a younger age but not menopausal status was a correlate of REM-predominant OSA. Asthma was independently associated with REM-predominant OSA.

A Deep Learning Model for Snoring Detection and Vibration Notification Using a Smart Wearable Gadget

Snoring, a form of sleep-disordered breathing, interferes with sleep quality and quantity, both for the person who snores and often for the person who sleeps with the snorer. Poor sleep caused by snoring can create significant physical, mental, and economic problems. A simple and natural solution for snoring is to sleep on the side, instead of sleeping on the back. In this project, a deep learning model for snoring detection is developed and the model is transferred to an embedded system—referred to as the listener module—to automatically detect snoring. A novel wearable gadget is developed to apply a vibration notification on the upper arm until the snorer sleeps on the side. The gadget is rechargeable, and it is wirelessly connected to the listener module using low energy Bluetooth. A smartphone app—connected to the listener module using home Wi-Fi—is developed to log the snoring events with timestamps, and the data can be transferred to a physician for treating and monitoring diseases such as sleep apnea. The snoring detection deep learning model has an accuracy of 96%. A prototype system consisting of the listener module, the wearable gadget, and a smartphone app has been developed and tested successfully.

Snoring - An Acoustic Definition

Objective- The distinction of snoring and loud breathing is often subjective and lies in the ear of the beholder. The aim of this study is to identify and assess acoustic features with a high suitability to distinguish these two classes of sound, in order to facilitate an objective definition of snoring based on acoustic parameters. Methods- A corpus of snore and breath sounds from 23 subjects has been used that were classified by 25 human raters. Using the openSMILE feature extractor, 6 373 acoustic features have been evaluated for their selectivity comparing SVM classification, logistic regression, and the recall of each single feature. Results- Most selective single features were several statistical functionals of the first and second mel frequency spectrum-generated perceptual linear predictive (PLP) cepstral coefficient with an unweighted average recall (UAR) of up to 93.8%. The best performing feature sets were low level descriptors (LLDs), derivatives and statistical functionals based on fast Fourier transformation (FFT), with a UAR of 93.0%, and on the summed mel frequency spectrum-generated PLP cepstral coefficients, with a UAR of 92.2% using SVM classification. Compared to SVM classification, logistic regression did not show considerable differences in classification performance. Conclusion- It could be shown that snoring and loud breathing can be distinguished by robust acoustic features. The findings might serve as a guidance to find a consensus for an objective definition of snoring compared to loud breathing.

Accelerometer based Active Snore Detection for Behavioral Modification

Habitual snoring has been known to increase the risk for serious health problems in addition to affecting the quality of others' sleep. Several recent consumer products aim to automatically detect snoring events and wake the snorer to elicit a posture change. In this paper, we present a study comparing two of the methods, electromyography vs. accelerometry, proposed for automated snoring detection and incorporation of these into a wearable system. The study includes (a) the testing of various sensor configurations and placements to obtain optimal electromyography and accelerometry signals, (b) a review of the accuracy of a variety of snore detection algorithms from previously attained biological signals, and (3) design of an embedded device with integrated sensors and haptic feedback capability. Our preliminary results indicate superiority of accelerometry over electromyography. Further research opportunities to prove the concept and improve the design are then detailed for future work.

Apnea and Hypopnea Events Classification Using Amplitude Spectrum Trend Feature of Snores

Research on snores for Obstructive Sleep Apnea Syndrome (OSAS) diagnosis is a new trend in recent years. In this paper, we proposed a snore-based apnea and hypopnea events classification approach. Firstly, we define the snores after the apnea event and during the hypopnea event as apnea-event-snore (AES) and hypopnea-event-snore (HES), respectively. Then, we design a new feature from the trend of the amplitude spectrum of snores. The newly proposed feature can be viewed as an improvement of the Mel-frequency cepstral coefficient (MFCC) feature, which is well-known for speech recognition. The extracted features were fed to principle component analysis (PCA) for dimension reduction and support vector machine (SVM) for apnea and hypopnea events classification. The experimental results demonstrate the efficiency of the proposed algorithm in using snores to classify apnea and hypopnea events.