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

PURPOSE: 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). MATERIALS AND METHODS: 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. RESULTS: 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. CONCLUSIONS: 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.

A New Feature with the Potential to Detect the Severity of Obstructive Sleep Apnoea via Snoring Sound Analysis.

The severity of obstructive sleep apnoea (OSA) is diagnosed with polysomnography (PSG), during which patients are monitored by over 20 physiological sensors overnight. These sensors often bother patients and may affect patients' sleep and OSA. This study aimed to investigate a method for analyzing patient snore sounds to detect the severity of OSA. Using a microphone placed at the patient's bedside, the snoring and breathing sounds of 22 participants were recorded while they simultaneously underwent PSG. We examined some features from the snoring and breathing sounds and examined the correlation between these features and the snore-specific apnoea-hypopnea index (ssAHI), defined as the number of apnoea and hypopnea events during the hour before a snore episode. Statistical analyses revealed that the ssAHI was positively correlated with the Mel frequency cepstral coefficients (MFCC) and volume information (VI). Based on clustering results, mild snore sound episodes and snore sound episodes from mild OSA patients were mainly classified into cluster 1. The results of clustering severe snore sound episodes and snore sound episodes from severe OSA patients were mainly classified into cluster 2. The features of snoring sounds that we identified have the potential to detect the severity of OSA.

Snore-GANs: Improving Automatic Snore Sound Classification With Synthesized Data.

One of the frontier issues that severely hamper the development of automatic snore sound classification (ASSC) associates to the lack of sufficient supervised training data. To cope with this problem, we propose a novel data augmentation approach based on semi-supervised conditional generative adversarial networks (scGANs), which aims to automatically learn a mapping strategy from a random noise space to original data distribution. The proposed approach has the capability of well synthesizing "realistic" high-dimensional data, while requiring no additional annotation process. To handle the mode collapse problem of GANs, we further introduce an ensemble strategy to enhance the diversity of the generated data. The systematic experiments conducted on a widely used Munich-Passau snore sound corpus demonstrate that the scGANs-based systems can remarkably outperform other classic data augmentation systems, and are also competitive to other recently reported systems for ASSC.

Effect of mean apnea-hypopnea duration in patients with obstructive sleep apnea on clinical and polysomnography parameter.

OBJECTIVE: Apnea-hypopnea index is the number of apnea-hypopnea events observed during polysomnography within an hour. Mean apnea-hypopnea duration is the mean duration of all apneas and hypopneas. In this study, we aimed to investigate the association of mean apnea-hypopnea duration in patients with obstructive sleep apnea with clinical and polysomnographic parameters. METHODS: In our hospital, a total of 764 patients were diagnosed with OSA by polysomnography in 2017. Age, body mass index, and the current diseases were recorded. Sleep structures obtained from polysomnography readings, blood oxygen levels, apnea-hypopnea index, and mean average duration were recorded. Patients with mean average duration of 20 s or more were assigned to the long average duration group and those with less than 20 s were assigned to the short average duration group. Groups were compared in terms of clinical and polysomnographic parameters. RESULTS: Snoring, witnessed apnea, morning tiredness, and hypertension were significantly higher in the long average duration group. There was statistically significantly more male patients and higher neck circumference in the MAD group. Total wake duration, percentage of sleep, stage 3, stage 1, and mean oxygen saturation percentage of the long average duration group were significantly reduced. CONCLUSION: In present study, the patients with obstructive sleep apnea with long average duration were found to have more negative effects of sleep apnea than the patients with short average duration. We think that the use of mean apnea-hypopnea duration as an indicator with apnea-hypopnea index will be beneficial for the follow-up and treatment of the disease.

[VOTE versus ACLTE: comparison of two snoring noise classifications using machine learning methods]. / VOTE versus ACLTE: Vergleich zweier Schnarchgeräuschklassifikationen mit Methoden des maschinellen Lernens.

BACKGROUND: Acoustic snoring sound analysis is a noninvasive method for diagnosis of the mechanical mechanisms causing snoring that can be performed during natural sleep. The objective of this work is development and evaluation of classification schemes for snoring sounds that can provide meaningful diagnostic support. MATERIALS AND METHODS: Based on two annotated snoring noise databases with different classifications (s-VOTE with four classes versus ACLTE with five classes), identically structured machine classification systems were trained. The feature extractor openSMILE was used in combination with a linear support vector machine for classification. RESULTS: With an unweighted average recall (UAR) of 55.4% for the s­VOTE model and 49.1% for the ACLTE, the results are at a similar level. In both models, the best differentiation is achieved for epiglottic snoring, while velar and oropharyngeal snoring are more often confused. CONCLUSION: Automated acoustic methods can help diagnose sleep-disordered breathing. A reason for the restricted recognition performance is the limited size of the training datasets.

Anthropometric Measures and Prediction of Maternal Sleep-Disordered Breathing.

STUDY OBJECTIVES: Pregnant women are at risk for sleep-disordered breathing (SDB); however, screening methods in this dynamic population are not well studied. The aim of this study was to examine whether anthropometric measures can accurately predict SDB in pregnant women. METHODS: Pregnant women with snoring and overweight/obesity were recruited in the first trimester. Anthropometric measures were performed according to the International Standards for Anthropometric Assessment, including a seated neutral and extended neck Mallampati class. Home sleep apnea monitoring was performed using a level III device after completion of anthropometric assessment. SDB was defined as an apnea-hypopnea index ≥ 5 events/h of sleep. Pearson and Spearman tests examined correlations between various measures. Generalized linear models, sensitivity, specificity, and area under the curve as well as odds ratios were performed to test the model. RESULTS: A total of 129 participants were recruited, and 23 had SDB. Average gestational age was 10.6 ± 1.9 weeks. Due to concerns over multicollinearity, the final model included extended Mallampati class and upright neck circumference. Neck circumference was significantly higher in participants with Mallampati classes 2/3 and grade 4 compared to participants with Mallampati class 1 (P = .0005). Increasing neck circumference was associated with higher odds of SDB (P = .0022). In Mallampati class 1, odds ratio for SDB was 2.89 (1.19, 7.03) per unit increase in neck circumference. CONCLUSIONS: Modeling neck circumference while allowing for differences by Mallampati class showed a nearly threefold increase in the risk of SDB with increasing neck circumference in women with Mallampati class 1. Other potential sites of airway obstruction need to be investigated in future research.

Smartphone-based delivery of oropharyngeal exercises for treatment of snoring: a randomized controlled trial.

PURPOSE: Upper airway exercises for snoring treatment can be effective but difficult to administer and monitor. We hypothesized that a brief, relatively simple daily upper airway exercise regimen, administered by a smartphone application, would reduce snoring and encourage compliance. METHODS: Targeted vowel sounds causing tongue base movements were incorporated into a voice-controlled smartphone game application. Participants with habitual snoring, apnea hypopnea index (AHI) ≤ 14 events/h, and BMI ≤ 32 kg/m2 were randomly assigned to perform 15 min of daily gameplay (intervention group) or 5 s of daily voice recording (control group) and to audio record their snoring for 2 nights/week for up to 12 weeks. Sounds above 60 dB were extracted from recordings for snore classification with machine learning support vector machine classifiers. RESULTS: Sixteen patients (eight in each group) completed the protocol. Groups were similar at baseline in gender distribution (five males, three females), mean BMI (27.5 ± 3.8 vs 27.4 ± 3.8 kg/m2), neck circumference (15.1 ± 1.6 vs 14.7 ± 1.7 in.), Epworth Sleepiness Score (8 ± 3.5 vs 7 ± 4.0), and AHI (9.2 ± 4.0 vs 8.2 ± 3.2 events/h). At 8 weeks, the absolute change in snoring rate (> 60 dB/h) was greater for the intervention group than the control group (- 49.3 ± 55.3 vs - 6.23 ± 23.2; p = 0.037), a 22 and 5.6% reduction, respectively. All bed partners of participants in the intervention group reported reduced snoring volume and frequency, whereas no change was reported for the control group. CONCLUSIONS: Smartphone application-administered upper airway training reduces objective and subjective snoring measures and improves sleep quality. TRIAL REGISTRATION: ClinicalTrials.gov ; no.: NCT03264963; URL: www.clinicaltrials.gov.

Low Level Texture Features for Snore Sound Discrimination.

Snoring is often associated with serious health risks such as obstructive sleep apnea and heart disease and may require targeted surgical interventions. In this regard, research into automatically and unobtrusively analysing the site of blockages that cause snore sounds is growing in popularity. Herein, we investigate the use of low level image texture features in classification of four specific types of snore sounds. Specifically, we explore histogram of local binary patterns (LBP) in dense grid of rectangular regions and histogram of oriented gradients (HOG) extracted from colour spectrograms for snore sound characterisation. Support vector machines with homogeneous mapping are used in the classification stage of the proposed method. Various experimental works are carried out with both LBP and HOG descriptors on the INTERSPEECH ComParE 2017 snoring sub-challenge dataset. Results presented indicate that LBP descriptors are better than the HOG descriptors in snore type detection and fusion of the LBP and HOG descriptors produces stronger results than either individual descriptor. Further, when compared to the challenge baseline and state-of-the-art deep spectrum features, our approach achieved relative percentage increases in unweighted average recall of 23.1% and 8.3% respectively.

Snoring classified: The Munich-Passau Snore Sound Corpus.

OBJECTIVE: Snoring can be excited in different locations within the upper airways during sleep. It was hypothesised that the excitation locations are correlated with distinct acoustic characteristics of the snoring noise. To verify this hypothesis, a database of snore sounds is developed, labelled with the location of sound excitation. METHODS: Video and audio recordings taken during drug induced sleep endoscopy (DISE) examinations from three medical centres have been semi-automatically screened for snore events, which subsequently have been classified by ENT experts into four classes based on the VOTE classification. The resulting dataset containing 828 snore events from 219 subjects has been split into Train, Development, and Test sets. An SVM classifier has been trained using low level descriptors (LLDs) related to energy, spectral features, mel frequency cepstral coefficients (MFCC), formants, voicing, harmonic-to-noise ratio (HNR), spectral harmonicity, pitch, and microprosodic features. RESULTS: An unweighted average recall (UAR) of 55.8% could be achieved using the full set of LLDs including formants. Best performing subset is the MFCC-related set of LLDs. A strong difference in performance could be observed between the permutations of train, development, and test partition, which may be caused by the relatively low number of subjects included in the smaller classes of the strongly unbalanced data set. CONCLUSION: A database of snoring sounds is presented which are classified according to their sound excitation location based on objective criteria and verifiable video material. With the database, it could be demonstrated that machine classifiers can distinguish different excitation location of snoring sounds in the upper airway based on acoustic parameters.

Signal shape feature for automatic snore and breathing sounds classification.

Snore analysis techniques have recently been developed for sleep studies. Most snore analysis techniques require reliable methods for the automatic classification of snore and breathing sounds in the sound recording. In this study we focus on this problem and propose an automated method to classify snore and breathing sounds based on the novel feature, 'positive/negative amplitude ratio (PNAR)', to measure the shape of the sound signal. The performance of the proposed method was evaluated using snore and breathing recordings (snore: 22,643 episodes and breathing: 4664 episodes) from 40 subjects. Receiver operating characteristic (ROC) analysis showed that the proposed method achieved 0.923 sensitivity with 0.918 specificity for snore and breathing sound classification on test data. PNAR has substantial potential as a feature in the front end of a non-contact snore/breathing-based technology for sleep studies.

Distinguishing snoring sounds from breath sounds: a straightforward matter?

BACKGROUND: Although snoring is a common problem, no unequivocal definition yet exists for this acoustic phenomenon. The primary study objective was to investigate whether snoring sounds can be distinguished at all clearly from breath sounds. Our secondary objective was to evaluate whether the sound pressure level in common use and psychoacoustic parameters are suitable for making this distinction. METHODS: Twenty-five subjects exposed to 55 sound sequences were asked to decide whether these were breath sounds or snoring sounds, and to indicate how certain they were about their decision. The sound pressure level and the psychoacoustic parameters of loudness, sharpness, roughness, and fluctuation strength were then analyzed, and psychoacoustic annoyance was calculated from these parameters. RESULTS: Sixteen percent of the sound sequences could not be classified unequivocally, although the individual raters stated that they were still moderately certain about their decision. The sound pressure level and psychoacoustic parameters were capable of distinguishing between breath sounds and snoring sounds. The optimum for sensitivity and specificity was 76.9 and 78.8 %, respectively. CONCLUSIONS: Because snoring appears to be a subjective impression, at least in part, a generally valid acoustic definition therefore seems to be impossible. The sound pressure level and psychoacoustic parameters are suitable for distinguishing between breath sounds and snoring sounds. Nevertheless, when interpreting results, the only moderate validity of these parameters due to the absence of a universally valid definition of snoring should be taken into account.

Comparison of SVM and ANFIS for snore related sounds classification by using the largest Lyapunov exponent and entropy.

Snoring, which may be decisive for many diseases, is an important indicator especially for sleep disorders. In recent years, many studies have been performed on the snore related sounds (SRSs) due to producing useful results for detection of sleep apnea/hypopnea syndrome (SAHS). The first important step of these studies is the detection of snore from SRSs by using different time and frequency domain features. The SRSs have a complex nature that is originated from several physiological and physical conditions. The nonlinear characteristics of SRSs can be examined with chaos theory methods which are widely used to evaluate the biomedical signals and systems, recently. The aim of this study is to classify the SRSs as snore/breathing/silence by using the largest Lyapunov exponent (LLE) and entropy with multiclass support vector machines (SVMs) and adaptive network fuzzy inference system (ANFIS). Two different experiments were performed for different training and test data sets. Experimental results show that the multiclass SVMs can produce the better classification results than ANFIS with used nonlinear quantities. Additionally, these nonlinear features are carrying meaningful information for classifying SRSs and are able to be used for diagnosis of sleep disorders such as SAHS.

Obstructive sleep apnea screening by integrating snore feature classes.

Obstructive sleep apnea (OSA) is a serious sleep disorder with high community prevalence. More than 80% of OSA suffers remain undiagnosed. Polysomnography (PSG) is the current reference standard used for OSA diagnosis. It is expensive, inconvenient and demands the extensive involvement of a sleep technologist. At present, a low cost, unattended, convenient OSA screening technique is an urgent requirement. Snoring is always almost associated with OSA and is one of the earliest nocturnal symptoms. With the onset of sleep, the upper airway undergoes both functional and structural changes, leading to spatially and temporally distributed sites conducive to snore sound (SS) generation. The goal of this paper is to investigate the possibility of developing a snore based multi-feature class OSA screening tool by integrating snore features that capture functional, structural, and spatio-temporal dependences of SS. In this paper, we focused our attention to the features in voiced parts of a snore, where quasi-repetitive packets of energy are visible. Individual snore feature classes were then optimized using logistic regression for optimum OSA diagnostic performance. Consequently, all feature classes were integrated and optimized to obtain optimum OSA classification sensitivity and specificity. We also augmented snore features with neck circumference, which is a one-time measurement readily available at no extra cost. The performance of the proposed method was evaluated using snore recordings from 86 subjects (51 males and 35 females). Data from each subject consisted of 6-8 h long sound recordings, made concurrently with routine PSG in a clinical sleep laboratory. Clinical diagnosis supported by standard PSG was used as the reference diagnosis to compare our results against. Our proposed techniques resulted in a sensitivity of 93±9% with specificity 93±9% for females and sensitivity of 92±6% with specificity 93±7% for males at an AHI decision threshold of 15 events/h. These results indicate that our method holds the potential as a tool for population screening of OSA in an unattended environment.

Obstructive apnea hypopnea index estimation by analysis of nocturnal snoring signals in adults.

STUDY OBJECTIVE: To develop a whole-night snore sounds analysis algorithm enabling estimation of obstructive apnea hypopnea index (AHI(EST)) among adult subjects. DESIGN: Snore sounds were recorded using a directional condenser microphone placed 1 m above the bed. Acoustic features exploring intra-(mel- cepstability, pitch density) and inter-(running variance, apnea phase ratio, inter-event silence) snore properties were extracted and integrated to assess AHI(EST). SETTING: University-affiliated sleep-wake disorder center and biomedical signal processing laboratory. PATIENTS: Ninety subjects (age 53 ± 13 years, BMI 31 ± 5 kg/m(2)) referred for polysomnography (PSG) diagnosis of OSA were prospectively and consecutively recruited. The system was trained and tested on 60 subjects. Validation was blindly performed on the additional 30 consecutive subjects. MEASUREMENTS AND RESULTS: AHI(EST) correlated with AHI (AHI(PSG); r(2) = 0.81, P < 0.001). Area under the receiver operating characteristic curve of 85% and 92% for thresholds of 10 and 20 events/h, respectively, were obtained for OSA detection. Both Altman-Bland analysis and diagnostic agreement criteria revealed 80% and 83% agreements of AHI(EST) with AHI(PSG), respectively. CONCLUSIONS: Acoustic analysis based on intra- and inter-snore properties can differentiate subjects according to AHI. An acoustic-based screening system may address the growing needs for reliable OSA screening tool. Further studies are needed to support these findings.

Somnology 101: a primer on sleep disorders, their impact on society, and a role for dentistry.

Sleep is necessary for our existence. It is one-third of a commitment to health along with nutrition and exercise. While we spend one-third of our lives asleep, studies show one-third of the U.S. population suffers with a significant sleep disorder at some point in their lifetime. This manuscript introduces sleep and sleep disorders, focuses on those sleep disorders within the domain of dentistry, and addresses contributions the dental community can make toward specific sleep problems.

Multiclass classification of subjects with sleep apnoea-hypopnoea syndrome through snoring analysis.

The gold standard for diagnosing sleep apnoea-hypopnoea syndrome (SAHS) is polysomnography (PSG), an expensive, labour-intensive and time-consuming procedure. Accordingly, it would be very useful to have a screening method to allow early assessment of the severity of a subject, prior to his/her referral for PSG. Several differences have been reported between simple snorers and SAHS patients in the acoustic characteristics of snoring and its variability. In this paper, snores are fully characterised in the time domain, by their sound intensity and pitch, and in the frequency domain, by their formant frequencies and several shape and energy ratio measurements. We show that accurate multiclass classification of snoring subjects, with three levels of SAHS, can be achieved on the basis of acoustic analysis of snoring alone, without any requiring information on the duration or the number of apnoeas. Several classification methods are examined. The best of the approaches assessed is a Bayes model using a kernel density estimation method, although good results can also be obtained by a suitable combination of two binary logistic regression models. Multiclass snore-based classification allows early stratification of subjects according to their severity. This could be the basis of a single channel, snore-based screening procedure for SAHS.

Perceived sleep quality among edentulous elders.

BACKGROUND: Anatomical changes associated with edentulism are thought to disturb seniors' sleep. OBJECTIVES: (1) To determine sleep quality and daytime sleepiness of edentulous elders. (2) To examine the association between oral health-related quality of life and sleep quality. METHODS: Data were collected at a 1-year follow-up from 173 healthy edentulous elders who had participated in a randomised controlled trial and randomly received two types of mandibular prosthesis. Subjective sleep quality was assessed using the Pittsburgh Sleep Quality Index (PSQI, range 0-21), with higher scores indicating poorer sleep quality. The Epworth Sleepiness Scale (ESS) was used to measure the level of perceived daytime sleepiness, and scores ≥10 indicated sleepiness. RESULTS: The mean global PSQI and ESS scores were 4.7 ± 3.5 and 5.3 ± 3.9. There were no differences in sleep quality or sleepiness between those who wore their dentures at night and those who did not. Elders with frequent denture problems were sleepier during the day than those with fewer problems (p = 0.0034). General health (p = 0.02) and oral health-related quality of life (p = 0.001) are significant predictors of sleep quality. CONCLUSION: Healthy edentulous elders, independent of nocturnal wearing of their prosthesis, are good sleepers. Maintaining high oral health quality of life could contribute to better sleep.

The NAMES assessment: a novel combined-modality screening tool for obstructive sleep apnea.

PURPOSE: Obstructive sleep apnea (OSA) remains underdiagnosed, despite our understanding of its impact on general health. Current screening methods utilize either symptoms or physical exam findings suggestive of OSA, but not both. The purpose of this study was to develop a novel screening tool for the detection of OSA, the NAMES assessment (neck circumference, airway classification, comorbidities, Epworth scale, and snoring), combining self-reported historical factors with physical exam findings. METHODS: Subjects were adults without previously diagnosed OSA, referred to a community sleep center for suspicion of OSA. General health, Epworth Sleepiness Scale (ESS), and Berlin questionnaires were completed, and a physical exam focusing on modified Friedman (MF) grade, body mass index (BMI), and neck circumference (NC) was performed prior to polysomnography. OSA was defined by a respiratory disturbance index ≥15. Each variable was dichotomized, and cutoff values were determined for the NAMES tool in a pilot group of 150 subjects. The NAMES score was calculated from NC, MF, comorbidities, ESS, and loud snoring values. The performances of the NAMES, Berlin questionnaire, and ESS screening tests in predicting OSA were then compared in a validation group of 509 subjects. RESULTS: In the pilot population, the cutoff value for the composite NAMES tool was calculated at ≥3 points. In the validation group, NAMES demonstrated similar test characteristics to the Berlin questionnaire, and sensitivity was better than that seen with the Epworth scale. The addition of BMI and gender to the tool improved screening characteristics. CONCLUSIONS: The NAMES assessment is an effective, inexpensive screening strategy for moderate to severe OSA.

[Clinical features, diagnostics, and treatment of rhonchopathy].

At present, diagnostics and treatment of pathological snoring is a topical medical and social problem as follows from the results of statistical and epidemiological studies of the prevalence of rhonchus and apnea in the general population and a large number of relevant publications both in the domestic and the foreign literature. According to statistics, every fifth subject at the age above 30 years snores when sleeping. Recent surveys have demonstrated that rhonchus is a precursory symptom and a manifestation of one of a most serious clinical conditions, obstructive sleep apnea syndrome (OSAS). One of the main achievements in the field of snoring research and treatment is the development of an objective method for the evaluation of the respiratory function during sleep known as polysomnography (PSG).