Snoring Patterns Research Articles

An audio-semantic multimodal model for automatic obstructive sleep Apnea-Hypopnea Syndrome classification via multi-feature analysis of snoring sounds.

Obstructive Sleep Apnea-Hypopnea Syndrome (OSAHS) is a common sleep-related breathing disorder that significantly impacts the daily lives of patients. Currently, the diagnosis of OSAHS relies on various physiological signal monitoring devices, requiring a comprehensive Polysomnography (PSG). However, this invasive diagnostic method faces challenges such as data fluctuation and high costs. To address these challenges, we propose a novel data-driven Audio-Semantic Multi-Modal model for OSAHS severity classification (i.e., ASMM-OSA) based on patient snoring sound characteristics. In light of the correlation between the acoustic attributes of a patient's snoring patterns and their episodes of breathing disorders, we utilize the patient's sleep audio recordings as an initial screening modality. We analyze the audio features of snoring sounds during the night for subjects suspected of having OSAHS. Audio features were augmented via PubMedBERT to enrich their diversity and detail and subsequently classified for OSAHS severity using XGBoost based on the number of sleep apnea events. Experimental results using the OSAHS dataset from a collaborative university hospital demonstrate that our ASMM-OSA audio-semantic multimodal model achieves a diagnostic level in automatically identifying sleep apnea events and classifying the four-class severity (normal, mild, moderate, and severe) of OSAHS. Our proposed model promises new perspectives for non-invasive OSAHS diagnosis, potentially reducing costs and enhancing patient quality of life.

Effect of High-Risk Obstructive Sleep Apnea on Clinical Outcomes in Adults with Coronavirus Disease 2019: A Multicenter, Prospective, Observational Clinical Trial.

Rationale: Coronavirus disease (COVID-19) is an ongoing pandemic, in which obesity, hypertension, and diabetes have been linked to poor outcomes. Obstructive sleep apnea (OSA) is associated with these conditions and may influence the prognosis of adults with COVID-19.Objectives: To determine the effect of OSA on clinical outcomes in patients with COVID-19.Methods: The current prospective observational study was conducted in three hospitals in Istanbul, Turkey from March 10 to June 22, 2020. The participants were categorized as high-risk or low-risk OSA according to the Berlin questionnaire that was administered in the out-patient clinic, in hospital, or shortly after discharge from hospital blinded to the clinical outcomes. A modified high-risk (mHR)–OSA score based on the snoring patterns (intensity and/or frequency), breathing pauses, and morning/daytime sleepiness, without taking obesity and hypertension into account, were used in the regression models.Results: The primary outcome was the clinical improvement defined as a decline of two categories from admission on a 7-category ordinal scale that ranges from 1 (discharged with normal activity) to 7 (death) on Days 7, 14, 21, and 28, respectively. Secondary outcomes included clinical worsening (an increase of 1 category), need for hospitalization, supplemental oxygen, and intensive care. In total, 320 eligible patients (median [interquartile range] age, 53.2 [41.3–63.0] yr; 45.9% female) were enrolled. In all, 121 (37.8%) were categorized as known (n = 3) or high-risk OSA (n = 118). According to the modified scoring, 70 (21.9%) had mHR-OSA. Among 242 patients requiring hospitalization, clinical improvement within 2 weeks occurred in 75.4% of the mHR-OSA group compared with 88.4% of the modified low-risk–OSA group (P = 0.014). In multivariate regression analyses, mHR-OSA (adjusted odds ratio [OR], 0.42; 95% confidence interval [CI], 0.19–0.92) and male sex (OR, 0.39; 95% CI, 0.17–0.86) predicted the delayed clinical improvement. In the entire study population (n = 320), including the nonhospitalized patients, mHR-OSA was associated with clinical worsening (adjusted hazard ratio, 1.55; 95% CI, 1.00–2.39) and with the need for supplemental oxygen (OR, 1.95; 95% CI, 1.06–3.59). Snoring patterns, especially louder snoring, significantly predicted delayed clinical improvement, worsening, need for hospitalization, supplemental oxygen, and intensive care.Conclusions: Adults with mHR-OSA in our COVID-19 cohort had poorer clinical outcomes than those with modified low-risk OSA independent of age, sex, and comorbidities. Clinical trial registered with www.clinicaltrials.gov (NCT04363333).

Self-reported Snoring Patterns Predict Stroke Events in High-Risk Patients With OSA: Post Hoc Analyses of the SAVE Study

The relation of snoring to risks of stroke and other major cardiovascular (CV) events is uncertain. We aimed to determine associations of snoring patterns and major CV events in relation to OSA among participants of the international Sleep Apnea cardiovascular Endpoints (SAVE) trial. Post hoc analyses of the SAVE trial, which involved 2,687 patients with coexisting moderate-to-severe OSA and established coronary or cerebral CV disease, who were randomly allocated to CPAP treatment plus usual care or usual care alone, and followed-up for a median 3.5 years. Associations of self-reported snoring patterns (frequency and loudness) and breathing pauses collected on the Berlin questionnaire at baseline and multiple times during follow-up, and adjudicated composites of CV outcomes (primary, CV death, nonfatal myocardial infarction, nonfatal stroke, and hospitalization for unstable angina, heart failure, or transient ischemic attack; and separately of cardiac and cerebral events), were evaluated in time-dependent Cox proportional hazards models adjusted for various confounders including the apnea-hypopnea index. Increase (per category) of snoring frequency (adjusted hazard ratio [HR], 1.10; 95%CI, 1.02-1.20; P= .015), loudness (HR, 1.16; 95%CI, 1.06-1.27; P= .001), and breathing pauses (HR, 1.16; 95%CI, 1.08-1.25; P< .001) at any time point during follow-up were each associated with the primary composite CV outcome. These associations were driven by significant associations for cerebral rather than cardiac events, and positive interactions between the three snoring patterns for cerebral events. There was no significant interaction between CPAP treatment and snoring variables for cerebral events. Snoring in patients with OSA with established CV disease is associated with greater risks of cerebral but not cardiac events, independent of CPAP treatment and frequency of apnea and hypopnea events. ClinicalTrials.gov; No.: NCT00738179; URL: www.clinicaltrials.gov.

Removing of Snoring Segments from Tracheal Breathing Sounds using a Wavelet-based Algorithm.

Tracheal sounds represent information about the upper airway and respiratory airflow, however, they can be contaminated by the snoring sounds. The sound of snoring has spectral content in a wide range that overlaps with that of breathing sounds during sleep. For assessing respiratory airflow using tracheal breathing sound, it is essential to remove the effect of snoring. In this paper, an automatic and unsupervised wavelet-based snoring removal algorithm is presented. Simultaneously with full-night polysomnography, the tracheal sound signals of 9 subjects with different levels of airway obstruction were recorded by a microphone placed over the trachea during sleep. The segments of tracheal sounds that were contaminated by snoring were manually identified through listening to the recordings. The selected segments were automatically categorized based on including discrete or continuous snoring pattern. Segments with discrete snoring were analyzed by an iterative wave-based filtering optimized to separate large spectral components related to snoring from smaller ones corresponded to breathing. Those with continuous snoring were first segmented into shorter segments. Then, each short segments were similarly analyzed along with a segment of normal breathing extracted from the recordings during wakefulness. The algorithm was evaluated by visual inspection of the denoised sound energy and comparison of the spectral densities before and after removing snores, where the overall rate of detectability of snoring was less than 2%.Clinical Relevance- The algorithm provides a way of separating snoring pattern from the tracheal breathing sounds. Therefore, each of them can be analyzed separately to assess respiratory airflow and the pathophysiology of the upper airway during sleep.

Snoring patterns during home polysomnography. A proposal for a new classification.

Snoring is a very common disorder, but, at present, there is no universally accepted classification for the condition. The main aim of this paper is to introduce a home sleep monitoring-based classification of common snoring patterns in simple snorers and in patients with obstructive sleep apnea-hypopnea syndrome (OSAHS). In total, 561 consecutive patients with a history of snoring, either simple or associated with apnea, were enrolled in this home sleep monitoring study. Analysis of the polysomnographic traces and the snoring sensor allowed the main patterns of snoring and their characteristics to be determined. Four patterns of snoring were identified. In a spectrum of increasing severity (mild, moderate or severe), snoring can be episodic, positional, continuous, or alternating, whereas in obstructive sleep apnea syndrome, the snoring events only occur between successive respiratory obstructive events. In mild snoring, the episodic pattern is the most frequent, whereas in moderate and severe snoring, the continuous snoring pattern occurs in most cases. The proposed classification of snoring patterns would be beneficial for providing a realistic disturbance index, for the selection and evaluation of the outcomes of surgical techniques.

Classification of snoring sound based on a recurrent neural network

Snoring is a sleep disorder that may have adverse effects on an individual's health and social activities. Polysomnography is the most common way to diagnose snoring but involves considerable time and cost. Many recent studies have attempted to classify snoring and non-snoring. However, since the length, frequency, and period of snoring episodes (SE) differ according to the individual being measured, it is very difficult to develop a general reference point to classify snoring. Therefore, in order to classify different snoring patterns and noise for different individuals, a learning-based snoring classification algorithm is essential. To this end, this study proposes a classification method based on a recurrent neural network (RNN) that can classify SEs and non-snoring episodes (NSEs) by learning the features of an individual's SEs and NSEs, measured in daily life based on the subjects’ sleep recordings using smartphone. The method proposed in this study can be largely divided into segmentation, feature extraction, and classification. The performance of this study was evaluated through statistical parameters. Despite the fact that the proposed RNN-based classifiers were trained using a relative small dataset, they exhibited an extremely high accuracy of 98.9%.

Clinical Practice Guideline on Management of Sleep Disorders in the Elderly.

Clinical Practice Guideline on Management of Sleep Disorders in the Elderly.

Evaluation of acoustic characteristics of snoring sounds obtained during drug-induced sleep endoscopy.

Snoring sounds are discussed to contain acoustic information about their geneses. Nocturnal snoring can easily be recorded acoustically but it is difficult to visually verify its genesis. Contrary, snoring patterns induced by drug-induced sleep endoscopy (DISE) can be visually differentiated. The aim of the study was to classify patterns of obstructions and vibration during DISE and to evaluate acoustic characteristics between these different patterns of snoring. DISE was performed in 41 male patients with sleep-disordered breathing. The recorded video sequences (n = 108) were classified visually at a mute mode in different patterns of snoring (velar, velar obstructive, tonsillar, post-apnoeic). The sound tracks of these subgroups were analysed and compared with regard to the parameters sound pressure level, loudness, sharpness, roughness, fluctuations strength and centre frequency. Obstructive snoring patterns revealed a higher loudness than non-obstructive patterns (>25sone). Velar snoring showed more roughness (>150cAsper) than tonsillar and post-apnoeic snoring and revealed the lowest centre frequency (<3000Hz) of all patterns. Tonsillar snoring presented the highest sharpness (>1.6acum) whereas post-apnoeic snoring revealed the largest fluctuation strength (>50cVacil). Different snoring patterns induced by DISE can be classified visually, and an approach to differentiate them acoustically by means of psychoacoustic analyses is demonstrated. On the basis of these results, nocturnal snoring might also be differentiated by psychoacoustic algorithms which could be implemented in acoustic polygraphic screening devices in the future.

Evaluation of Upper Airway in Obstructive Sleep Apnea: Synchronized Imaging and Acoustic Analyses

Objectives: Snore signals are produced by soft tissue vibration in the upper airway (UA). To date, there is no gold standard to localize UA narrowing sites in patients with obstructive sleep apnea syndrome (OSAS). In this study, we use a “vocal tract model” to investigate the association between snore acoustic characteristics and UA collapse. Dynamic magnetic resonance imaging (dMRI) was used to provide UA anatomy information. Methods: We report data from 44 polysomnography (PSG)-confirmed snoring episodes. Dynamics of UA and acoustic manifestations of snore events during natural sleep were recorded with synchronized dMRI and fiber-optic microphone recording. After the deletion of background dMRI noises, the spectrum envelope was reconstructed by applying a vocal tract model to characterize the snoring patterns. The temporal change of spectrum envelope was analyzed using Gabor transformation to correlate with UA dynamics. Results: The snore events were categorized into 28 none, 7 typical (velopharyngeal), and 9 mixed (velopharyngeal and hypopharyngeal) obstructions. The snore’s dominant frequency of envelop spectrum can differentiate none from typical UA obstructions (82.3±16.4Hz vs 101.9±9.1 Hz, p&lt;0.01); and can differentiate mixed from typical obstructions (131.9±19.8 Hz vs.101.9±9.1 Hz, p &lt; 0.05) Conclusions: The dynamics of acoustic patterns derived from the envelope of Gabor spectrogram are unique and characteristics in different types of obstruction with the advantage of low-cost and easy availability. Therefore, the dynamics of acoustic patterns warrants further investigation to identify the structural changes of the obstruction sites in OSAS patients.

Snoring, inflammatory markers, adipokines and metabolic syndrome in apparently healthy Chinese.

ObjectiveChronic low-grade inflammation and adipokines dysregulation are linked to mechanisms underscoring the pathogenesis of obesity-related metabolic disorders. Little is known about roles of these cytokines on the association between snoring and metabolic syndrome (MetS). We aimed to investigate whether a cluster of cytokines are related to snoring frequency and its association with MetS in apparently healthy Chinese.MethodsCurrent analyses used a population-based sample including 1059 Shanghai residents aged 35–54 years. Self-reported snoring frequency was classified as never, occasionally and regularly. Fasting plasma glucose, lipid profile, insulin, C-reactive protein, interleukin-6, interleukin-18, lipopolysaccharide binding protein, high-molecular-weight adiponectin and leptin were measured. MetS was defined by the updated National Cholesterol Education Program Adult Treatment Panel III criteria for Asian-Americans.ResultsOverweight/obese subjects had significantly higher prevalence of regular snorers than their normal-weight counterparts (34.8% vs. 11.5%, P<0.001). Regular snoring was associated with unfavorable profile of inflammatory markers and adipokines. However, those associations were abolished after adjustment for body mass index (BMI) or waist circumference. The MetS risk (multivariate-adjusted odds ratio 5.41, 95% confidence interval 3.72–7.88) was substantially higher in regular snorers compared with non-snorers. Controlling for BMI remarkably attenuated the association (2.03, 1.26–3.26), while adjusting for inflammatory markers and adipokines showed little effects.ConclusionFrequent snoring was associated with an elevated MetS risk independent of lifestyle factors, adiposity, inflammatory markers and adipokines in apparently healthy Chinese. Whether snoring pattern is an economic and no-invasive indicator for screening high-risk persons needs to be addressed prospectively.

The impact of the microphone position on the frequency analysis of snoring sounds

Frequency analysis of snoring sounds has been reported as a diagnostic tool to differentiate between different sources of snoring. Several studies have been published presenting diverging results of the frequency analyses of snoring sounds. Depending on the position of the used microphones, the results of the frequency analysis of snoring sounds vary. The present study investigated the influence of different microphone positions on the outcome of the frequency analysis of snoring sounds. Nocturnal snoring was recorded simultaneously at six positions (air-coupled: 30 cm middle, 100 cm middle, 30 cm lateral to both sides of the patients' head; body contact: neck and parasternal) in five patients. The used microphones had a flat frequency response and a similar frequency range (10/40 Hz-18 kHz). Frequency analysis was performed by fast Fourier transformation and frequency bands as well as peak intensities (Peaks 1-5) were detected. Air-coupled microphones presented a wider frequency range (60 Hz-10 kHz) compared to contact microphones. The contact microphone at cervical position presented a cut off at frequencies above 300 Hz, whereas the contact microphone at parasternal position revealed a cut off above 100 Hz. On an exemplary base, the study demonstrates that frequencies above 1,000 Hz do appear in complex snoring patterns, and it is emphasised that high frequencies are imported for the interpretation of snoring sounds with respect to the identification of the source of snoring. Contact microphones might be used in screening devices, but for a natural analysis of snoring sounds the use of air-coupled microphones is indispensable.

The Development of a Nonintrusive Home-Based Physiologic Signal Measurement System

This paper describes the development of a nonintrusive health-monitoring house system that has been developed for monitoring patients' health status. The system functions unobtrusively and leaves patients free to conduct daily activities. Installed sensors and devices in the house monitor biosignals such as bedside electrocardiogram (ECG), snoring, weight, and movement pattern. The network in the house was constructed using asymmetric digital subscriber line (ADSL) and Bluetooth technologies and it is capable of transmitting monitored signals to the remote hospital server through the home server. The system is found to be effective in monitoring patients' daily activity and health status in a nonconstraining manner.

Ein einfaches Verfahren zur quantitativen und zeitcodierten Erfassung von Schnarchgeräuschen bei Apnoikern und Schnarchern

A simple technique for time-encoded recording of snoring sounds is presented. An electronic circuit connected to a stereo cassette recorder via cord remote control will start the recorder when the sound pressure of the snoring sound surpasses a preset level. The snoring sound is recorded on one track of the cassette recorder. The other track is used for the time code. Every 120 seconds the tape recorder is switched on by the electronic circuit and a short high level signal is recorded. The time interval between two time coding signals equals the snoring time. Analysis of the time coding signals is performed by an A/D converter installed in a Personal Computer. The converter amd accompanying software are used to calculate the duration of the intervals between the coding signals. The results are displayed graphically where sleeping time is plotted against snoring time (Fig.2). The length of each bar equals the snoring time in seconds for each 120 second interval. Snoring periods can be recognised at a glance and the snoring pattern can be evaluated. Three cases studies are presented demonstrating the performance of the technique. A 39-year-old female with nonpathological snoring (Fig.2), a 45-year-old male with heavy and regular snoring (Fig. 3) and a 36-year-old male with a full-blown Pickwickian Syndrome (Fig. 4). This patient's response to nasal cPAP is demonstrated in Fig. 5.