Development and validation of a scale for the assessment of the knowledge-attitude-practice of parents towards children snoring.

BACKGROUND: Children Snoring is a common childhood disorder that affects the growth and development of children and is detrimental to their health. Increasing awareness of Children Snoring among parents is important. AIM: To develop the Knowledge-Attitude-Practice of Parents towards Children Snoring Scale and test the reliability and validity of the scale. METHODS: The development of the tool was divided into two phases involving 1257 parents from China. In the first phase, an initial project bank was created through a literature review. This was followed by a Delphi expert consultation, group discussion and pre-survey. The second stage screened the items and conducted an exploratory factor analysis, then conducted a confirmatory factor analysis and tested for reliability and validity. RESULTS: Support was found for the 25-item Knowledge-Attitude-Practice toward Children Snoring scale. Exploratory and confirmatory factor analyses provide support for four subscales: (parental basic cognition toward Children Snoring; parents' perception of complications of Children Snoring; parents' attitude towards Children Snoring; parents' concern and prevention of Children Snoring). Internal consistency for the total scale was high (Cronbach's α = 0.93). The intraclass correlation coefficient of test-retest reliability was 0.92 (95%CI: 0.85 to 0.95), which provided support for the stability of the scale. CONCLUSION: The Knowledge-Attitude-Practice of Parents towards Children Snoring scale shows promise as a measure that may be used by medical workers and community children's health managers.

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.

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.

A Novel Enhancement Approach Following MVMD and NMF Separation of Complex Snoring Signals.

Snoring is a prominent characteristic of sleep-disordered breathing, and its detection is critical for determining the severity of the upper airway obstruction and improving daily quality of life. Home snoring analysis is a highly invasive method, but it becomes challenging when a sleeping partner also snores, leading to distorted evaluations in such environments. In this article, we tackle the problem of complex snore signal separation of multiple snorers. This article introduces two audio-based methods that efficiently extract an individual's snoring signal, allowing for the analysis of sleep-breathing disorders in a normal sleeping environment without isolating individuals. In the first method, Principal Component Analysis (PCA) identifies the source components from the finite number of modes generated by the decomposition of the snoring mixture using Multivariate Variational Mode Decomposition (MVMD). The second method applies Blind Source Separation (BSS) based on Non-Negative Matrix Factorization (NMF) to separate the single-channel snoring mixture. Furthermore, the decomposed signals are tuned using the iterative enhancement algorithm to adequately match the source snoring signals. These methods were evaluated by simulating various real-time snoring recordings of 7 subjects (2 men, 2 women, and 3 children). The correlation coefficient between the source and its separated signal was computed to assess the separation results, exhibiting good performance of the methods used. The enhancement approach also demonstrated its efficiency by increasing the correlation over to 80% in both methods. The experimental results show that the proposed algorithms are effective and practical for separating mixed snoring signals.

Fractional exhaled nitric oxide-a possible biomarker for risk of obstructive sleep apnea in snorers.

STUDY OBJECTIVES: Airway inflammation in patients with obstructive sleep apnea (OSA) has been described and can be assessed by measuring the biomarker fractional exhaled nitric oxide (FeNO). In this pilot study, we investigated FeNO measurements in identification of OSA among persons with snoring. METHODS: In this study we aimed to investigate (1) if FeNO could be used in screening for OSA, (2) if daytime sleepiness correlated to FeNO levels, and (3) whether asthma affected FeNO levels. Persons with snoring were prospectively included in three primary care ear, nose, and throat clinics. Patients underwent spirometry, FeNO tests, and partial polygraphy. They filled out questionnaires on sinonasal and asthma symptoms, daytime sleepiness, and quality of life. Current smokers, patients with upper airway inflammatory conditions, and patients treated with steroids were excluded. RESULTS: Forty-nine individuals were included. Median apnea-hypopnea index was 11.4, mean age was 50.9 years, and 29% were females. OSA was diagnosed in 73% of the patients of whom 53% had moderate-severe disease. Patients with moderate-severe OSA had significantly higher FeNO counts than patients with no or mild OSA (P = .024). Patients younger than 50 years with a FeNO below 15 had the lowest prevalence of moderate-severe OSA. No correlation was found between FeNO measurements and daytime sleepiness, and asthma did not affect FeNO levels. CONCLUSIONS: We found a low prevalence of moderate-severe OSA in persons with snoring when FeNO and age were low. This might be considered in a future screening model, though further studies testing the FeNO cutoff level and the diagnostic accuracy are warranted. CLINICAL TRIAL REGISTRATION: Registry: ClinicalTrials.gov; Name: NO Measurements in Screening for Asthma and OSA, in Patients With Severe Snoring; URL: https://clinicaltrials.gov/study/NCT03964324; Identifier: NCT03964324. CITATION: Kiaer E, Ravn A, Jennum P, et al. Fractional exhaled nitric oxide-a possible biomarker for risk of obstructive sleep apnea in snorers. J Clin Sleep Med. 2024;20(1):85-92.

Association between snoring, daytime sleepiness and cardiovascular disease in Chinese rural adults.

BACKGROUNDS AND AIMS: Evidence on the association between habitual snoring, excessive daytime sleepiness (EDS), and cardiovascular diseases (CVDs) remains uncertain and limited. The study aimed to explore the independent and joint association between habitual snoring, EDS, and CVDs in rural Chinese adults. METHODS AND RESULTS: A total of 28,140 participants from the Henan rural cohort study were included. Sleep status information was obtained by self-reported. Based on their sleep status, the participants were classified into four groups: "no snoring and no EDS (NSNS) (reference group)", "snoring and no EDS (SNS)", "no snoring and EDS (NSS)", "snoring and EDS (SS)." The logistic regression models were used to calculate independent and joint odds ratios (OR) and 95% confidence intervals (CI) between the snoring, EDS status and stroke, CHD, and CVD. Of the 28,140 participants, 740 subjects reported snoring and sleepiness. The ORs and (95% CIs) for CVDs in the adjusted model were 1.31 (1.20-1.43) for participants who snored frequently and 2.44 (1.76-3.39) for frequent sleepiness compared with no snoring and no sleepiness. Individuals with both snoring and sleepiness had higher odds of CVDs compared with no snoring and no sleepiness (OR: 2.18, 95%CI: 1.80-2.62). CONCLUSION: Habitual snoring and excessive daytime sleepiness were independently and jointly associated with CVDs in the Chinese rural population. More studies are needed to explore the mechanisms of the relationship. CLINICAL TRIAL REGISTRATION: The Henan Rural Cohort Study has been registered at the Chinese Clinical Trial Register (Registration number: ChiCTR-OOC-15006699). Date of registration: 2015-52 07-06. http://www.chictr.org.cn/showproj.aspx?proj=11375.

Automatic snoring detection using a hybrid 1D-2D convolutional neural network.

Snoring, as a prevalent symptom, seriously interferes with life quality of patients with sleep disordered breathing only (simple snorers), patients with obstructive sleep apnea (OSA) and their bed partners. Researches have shown that snoring could be used for screening and diagnosis of OSA. Therefore, accurate detection of snoring sounds from sleep respiratory audio at night has been one of the most important parts. Considered that the snoring is somewhat dangerously overlooked around the world, an automatic and high-precision snoring detection algorithm is required. In this work, we designed a non-contact data acquire equipment to record nocturnal sleep respiratory audio of subjects in their private bedrooms, and proposed a hybrid convolutional neural network (CNN) model for the automatic snore detection. This model consists of a one-dimensional (1D) CNN processing the original signal and a two-dimensional (2D) CNN representing images mapped by the visibility graph method. In our experiment, our algorithm achieves an average classification accuracy of 89.3%, an average sensitivity of 89.7%, an average specificity of 88.5%, and an average AUC of 0.947, which surpasses some state-of-the-art models trained on our data. In conclusion, our results indicate that the proposed method in this study could be effective and significance for massive screening of OSA patients in daily life. And our work provides an alternative framework for time series analysis.

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.

Pilot study of contactless sleep apnea detection based on snore signals with hardware implementation.

Objective.Sleep apnea has a high incidence and is a potentially dangerous disease, and its early detection and diagnosis are challenging. Polysomnography (PSG) is considered the best approach for sleep apnea detection, but it requires cumbersome and complicated operations. Thus, it cannot satisfy the family healthcare needs.Approach.To facilitate the initial detection of sleep apnea in the home environment, we developed a sleep apnea classification model based on snoring and hybrid neural network, and implemented the well trained model in an embedded hardware platform. We used snore signals from 32 patients at Shenzhen People's Hospital. The Mel-Fbank features were extracted from snore signals to build a sleep apnea classification model based on Bi-LSTM with attention mechanism.Main results.The proposed model classified snore signals into four types: hypopnea, normal condition, obstructive sleep apnea, and central sleep apnea, with 83.52% and 62.31% accuracies, corresponding to the subject-dependence and subject-independence validation, respectively. After pruning and model quantization, at the cost of 0.81% and 0.95% accuracy loss of the subject dependence and subject independence classification, respectively, the number of model parameters and model storage space were reduced by 32.12% and 60.37%, respectively. The model exhibited accuracies of 82.71% and 61.36% based on the subject dependence and subject independence validations, respectively. When the well trained model was successfully porting and running on an STM32 ARM-embedded platform, the model accuracy was 58.85% for the four classifications based on leave-one-subject-out validation.Significance.The proposed sleep apnea detection model can be used in home healthcare for the initial detection of sleep apnea.

Orofacial dysfunction screening examinations in children with sleep-disordered breathing symptoms.

Orofacial myofunctional disorders (OMD) and sleep-disordered breathing (SDB) may present as comorbidities. Orofacial characteristics might serve as a clinical marker of SDB, allowing early identification and management of OMD and improving treatment outcomes for sleep disorders. The study aims to characterize OMD in children with SDB symptoms and to investigate possible relationships between the presence of various components of OMD and symptoms of SDB. A cross-sectional study of healthy children aged 6-8 from primary schools was conducted in central Vietnam in 2019. SDB symptoms were collected using the parental Pediatric Sleep Questionnaire, Snoring Severity Scale, Epworth Daytime Sleepiness Scale, and lip-taping nasal breathing assessment. Orofacial myofunctional evaluation included assessment of tongue mobility, as well as of lip and tongue strength using the Iowa Oral Performance Instrument, and of orofacial characteristics by the protocol of Orofacial Myofunctional Evaluation with Scores. Statistical analysis was used to investigate the relationship between OMD components and SDB symptoms. 487 healthy children were evaluated, of whom 46.2% were female. There were 7.6% of children at high risk of SDB. Children with habitual snoring (10.3%) had an increased incidence of restricted tongue mobility and decreased lip and tongue strength. Abnormal breathing patterns (22.4%) demonstrated lower posterior tongue mobility and lower muscle strength. Daytime sleepiness symptoms were associated with changes in muscle strength, facial appearance, and impaired orofacial function. Lower strengths of lip and tongue or improper nasal breathing were more likely to be present in children with reported sleep apnea (6.6%). Neurobehavioral symptoms of inattention and hyperactivity were linked to anomalous appearance/posture, increases in tongue mobility and oral strength. This study demonstrates a prevalence of orofacial myofunctional anomalies in children exhibiting SDB symptoms. Children with prominent SDB symptoms should be considered as candidates for further orofacial myofunctional assessment.

Elevoplasty®: An Innovative, Minimally Invasive Procedure for the Treatment of Snoring.

For non-obstructive sleep apnea diagnosed patients with predominantly palatal snoring, Elevoplasty® is an efficient, minimally invasive treatment option. Aimed at reducing snoring severity, the innovative procedure involves the placement of three to four small resorbable polydioxanone barbed sutures, which are buried in the tissues of the soft palate. After placement, the sutures are "activated" by a gentle pull, which provides a "lift" of the soft palatal tissues and uvula. The soft palate, thus, is moved off of the posterior pharyngeal tissues at the back of the throat, providing an increased opening of the posterior pharyngeal airway and a reduction in snoring severity. This article provides an overview of this procedure along with other treatments for snoring.

Evaluation of sleeping parameters with peripheral arterial tonometry in childhood sleep apnea and snoring: a clinical feasibility study.

PURPOSE: The influence of adenoidectomy ± tonsillotomy/tonsillectomy on objective sleep parameters in children with Obstructive Sleep Apnea (OSA) was determined with the help of ambulatory polygraphy (WatchPat300®, Neucomed Ltd., Vienna, Austria). These results were compared with the findings of the OSA-18 questionnaire. METHODS: 27 children treated with adenoidectomy ± tonsillotomy/tonsillectomy at the Department of Otorhinolaryngology, Head and Neck Surgery, Medical University of Innsbruck, were consecutively included in this prospective clinical trial. Pre- and postoperative objective sleeping parameters were assessed with outpatient polygraphy (WatchPat300®) and subjective symptoms with the OSA-18 questionnaire. RESULTS: Most of the children presented with severe OSA (41%, 11/27). The mean preoperative AHI was 10.2 (± 7.4). Postoperatively it declined to 3.7 (± 1.8; p < 0.0001). Following surgery 19/24 (79%) children had a mild OSA and 8/24 (21%) a moderate OSA. None of the children suffered from severe OSA anymore after surgery. The postoperative AHI did not correlate with the age (p = 0.3), BMIp (p = 0.6) or extent of surgery (p = 0.9). The mean postoperative OSA-18 survey score was significantly lower than the preoperative one (70.7 ± 26.7 vs. 34.5 ± 10.5; p < 0.0001). The postoperative OSA-18 questionnaire showed a normal survey score below 60 in 23/24 (96%) of the children. CONCLUSIONS: The WatchPat® device might be a feasible way for objective assessment of pediatric OSA in children older than 3 years. Adenoidectomy ± tonsillotomy/tonsillectomy caused a significant decrease of the AHI in children with OSA. This effect was especially pronounced in children with severe OSA and none of the children had persistent severe OSA after surgery.

[Prevalence of childhood obstructive sleep apnoea syndrome in a referral sleep unit]. / Prevalencia del síndrome de apnea obstructiva del sueño infantil en una unidad de sueño de referencia.

INTRODUCTION: Obstructive sleep apnoea syndrome (OSAS) affects between 1% and 6% of children. Its diagnosis includes: a) snoring and/or apnoea; and b) an apnoea and hypopnoea index >3/hour obtained by polysomnography (PSG). The main aim of this work is to determine the prevalence of OSAS in our study population. PATIENTS AND METHODS: We conducted a descriptive study with a sample of 151 children aged between 1 and 12 years, who had been referred to the sleep unit of the Hospital General Universitario Gregorio Maranon for a PSG. We analysed the demographic variables sex and age; the clinical variables snoring, apnoeas and tonsillar hypertrophy; and the presence of OSAS based on the polysomnographic diagnostic criterion of an apnoea and hypopnoea index >3/hour. RESULTS: The mean age of the sample was 5.37 years (standard deviation: 3.05) and 64.9% were males. In 90.1% of cases, the reason for the visit was suspected OSAS. Snoring, apnoeas and tonsillar hypertrophy were observed in 73.5, 48.7 and 60% of cases, respectively. OSAS was diagnosed en 19 children (12.6%); in 13.5% of snorers; in 15.1% of those with apnoeas; and in 15.6% of the children with tonsillar hypertrophy. CONCLUSIONS: In our study, the prevalence of OSAS in children was 12.6%, which is higher than that reported in most epidemiological studies that include PSG for the diagnosis of OSAS.

TITLE: Prevalencia del síndrome de apnea obstructiva del sueño infantil en una unidad de sueño de referencia.Introducción. El síndrome de apnea obstructiva del sueño (SAOS) afecta a entre el 1 y el 6% de la población infantil. En su diagnóstico, se incluyen: a) ronquidos y/o apneas; y b) un índice de apneas e hipopneas >3/hora obtenido en la polisomnografía (PSG). El objetivo principal de este trabajo es determinar la prevalencia del SAOS en nuestra población de estudio. Pacientes y métodos. Estudio descriptivo con una muestra de 151 niños con edades comprendidas entre 1 y 12 años, remitidos a la unidad de sueño del Hospital General Universitario Gregorio Marañón para la realización de una PSG. Se analizaron las variables demográficas sexo y edad; las variables clínicas ronquidos, apneas e hipertrofia amigdalar; y la presencia de SAOS basada en el criterio diagnóstico polisomnográfico de un índice de apneas e hipopneas >3/hora. Resultados. La edad media de la muestra fue de 5,37 años (desviación estándar: 3,05) y el 64,9% eran varones. En el 90,1% de los casos, el motivo de consulta fue sospecha de SAOS. Los ronquidos, las apneas y la hipertrofia amigdalar se observaron en el 73,5, el 48,7 y el 60% de los casos, respectivamente. Se diagnosticó SAOS en 19 (12,6%) niños; en el 13,5% de los roncadores; en el 15,1% de los niños con apneas; y en el 15,6% de los niños con hipertrofia amigdalar. Conclusiones. En nuestro estudio, la prevalencia del SAOS en niños fue del 12,6%, superior a la descrita en la mayoría de los estudios epidemiológicos, pero similar a la observada en los que incluyen la PSG para el diagnóstico del SAOS.

Predictive value of NoSAS questionnaire combined with the modified Mallampati grade for hypoxemia during routine sedation for gastrointestinal endoscopy.

BACKGROUND: The incidence of hypoxemia during painless gastrointestinal endoscopy remains a matter of concem. To date, there is no recognized simple method to predict hypoxemia in digestive endoscopic anesthesia. The NoSAS (neck circumference, obesity, snoring, age, sex) questionnaire, an objective and simple assessment scale used to assess obstructive sleep apnea (OSA), combined with the modified Mallampati grade (MMP), may have certain screening value. This combination may allow anesthesiologists to anticipate, manage, and consequently decrease the occurrence of hypoxemia. METHODS: This study was a prospective observational trial. The primary endpoint was the incidence of hypoxaemia defined as pulse oxygen saturation (SpO2) < 95% for 10 s. A total of 2207 patients admitted to our hospital for painless gastrointestinal endoscopy were studied. All patients were measured for age, height, weight, body mass index, neck circumference, snoring, MMP, and other parameters. Patients were divided into hypoxemic and non-hypoxemic groups based on the SpO2. The ROC curve was plotted to evaluate the screening value of the NoSAS questionnaire separately and combined with MMP for hypoxemia. The total NoSAS score was evaluated at cut-off points of 8 and 9. RESULTS: With a NoSAS score ≥ 8 as the critical value for analysis, the sensitivity for hypoxemia was 58.3%, the specificity was 88.4%, and the area under the ROC was 0.734 (P < 0.001, 95% CI: 0.708-0.759). With a NoSAS score ≥ 9 as a critical value, the sensitivity for hypoxemia was 36.50%, the specificity rose to 96.16%, and the area under the ROC was 0.663 (P < 0.001, 95% CI: 0.639-0.688). With the NoSAS Score combined with MMP for analysis, the sensitivity was 78.4%, the specificity was 84%, and the area under the ROC was 0.859 (P < 0.001, 95%CI:0.834-0.883). CONCLUSIONS: As a new screening tool, the NoSAS questionnaire is simple, convenient, and useful for screening hypoxemia. This questionnaire, when paired withMMP, is likely to be helpful for the screening of hypoxemia.

SLEEP-SEE-THROUGH: Explainable Deep Learning for Sleep Event Detection and Quantification From Wearable Somnography.

Evidence is rapidly accumulating that multifactorial nocturnal monitoring, through the coupling of wearable devices and deep learning, may be disruptive for early diagnosis and assessment of sleep disorders. In this work, optical, differential air-pressure and acceleration signals, acquired by a chest-worn sensor, are elaborated into five somnographic-like signals, which are then used to feed a deep network. This addresses a three-fold classification problem to predict the overall signal quality (normal, corrupted), three breathing-related patterns (normal, apnea, irregular) and three sleep-related patterns (normal, snoring, noise). In order to promote explainability, the developed architecture generates additional information in the form of qualitative (saliency maps) and quantitative (confidence indices) data, which helps to improve the interpretation of the predictions. Twenty healthy subjects enrolled in this study were monitored overnight for approximately ten hours during sleep. Somnographic-like signals were manually labeled according to the three class sets to build the training dataset. Both record- and subject-wise analyses were performed to evaluate the prediction performance and the coherence of the results. The network was accurate (0.96) in distinguishing normal from corrupted signals. Breathing patterns were predicted with higher accuracy (0.93) than sleep patterns (0.76). The prediction of irregular breathing was less accurate (0.88) than that of apnea (0.97). In the sleep pattern set, the distinction between snoring (0.73) and noise events (0.61) was less effective. The confidence index associated with the prediction allowed us to elucidate ambiguous predictions better. The saliency map analysis provided useful insights to relate predictions to the input signal content. While preliminary, this work supported the recent perspective on the use of deep learning to detect particular sleep events in multiple somnographic signals, thus representing a step towards bringing the use of AI-based tools for sleep disorder detection incrementally closer to clinical translation.

Automatic identifying OSAHS patients and simple snorers based on Gaussian mixture models.

Objective.Snoring is a typical symptom of Obstructive Sleep Apnea Hypopnea Syndrome (OSAHS). In this study, an effective OSAHS patient detection system based on snoring sounds is presented.Approach.The Gaussian mixture model (GMM) is proposed to explore the acoustic characteristics of snoring sounds throughout the whole night to classify simple snores and OSAHS patients respectively. A series of acoustic features of snoring sounds of are selected based on the Fisher ratio and learned by GMM. Leave-one-subject-out cross validation experiment based on 30 subjects is conducted to validation the proposed model. There are 6 simple snorers (4 male and 2 female) and 24 OSAHS patients (15 male and 9 female) investigated in this work. Results indicates that snoring sounds of simple snorers and OSAHS patients have different distribution characteristics.Main results.The proposed model achieves average accuracy and precision with values of 90.0% and 95.7% using selected features with a dimension of 100 respectively. The average prediction time of the proposed model is 0.134 ± 0.005 s.Significance.The promising results demonstrate the effectiveness and low computational cost of diagnosing OSAHS patients using snoring sounds at home.

[The efficacy of STOP-BANG questionnaire in screening of benign snoring and mild obstructive sleep apnea]. / A STOP-BANG kérdoív hatékonysága a benignus horkolás és az enyhe obstruktív alvási apnoe kiszurésében.

INTRODUCTION: Polysomnography is the gold standard for diagnosing sleep-related breathing disorders. Respiratory pulse oximetry can be used for screening, and several pre-screening questionnaires are available to assess the risk of obstructive sleep apnea. STOP-BANG questionnaire is simple and effective according to the literature. OBJECTIVE: Investigating the effectiveness of the STOP-BANG questionnaire for screening benign snoring and mild obstructive sleep apnea. METHOD: We analyzed the data of patients examined in our department for suspected sleep-related breathing disorder between 20. 06. 2021 and 19. 03. 2022. We compared the subsequently calculated STOP-BANG scores to the respiratory pulsoximetry results. Due to the lack of information regarding the intensity of snoring, the analysis was performed both with positive and negative results for this criterion. Sensitivity, specificity, positive and negative predictive values were calculated. RESULTS: We analyzed the data of 36 patients, one of them was examined twice due to weight loss. Benign snoring was confirmed by 19 patients, mild obstructive sleep apnea in 9, moderate in 4, and severe in 5 cases. Assuming loud snoring, the sensitivity was 100%, the specificity 21%, the positive predictive value 29%, and the negative predictive value 100%. Assuming no loud snoring, the sensitivity was 100%, the specificity 54%, the positive predictive value 41%, and the negative predictive value 100%. CONCLUSION: STOP-BANG questionnaire is effective, and can also be used in primary care to screen benign snoring and mild obstructive sleep apnea. Unnecessary device tests can be reduced by using it, resulting in significantly shorter waiting times for the sleep tests for high-risk patients. Orv Hetil. 2023; 164(7): 265-272.

Consumer sleep technology for the screening of obstructive sleep apnea and snoring: current status and a protocol for a systematic review and meta-analysis of diagnostic test accuracy.

There are concerns about the validation and accuracy of currently available consumer sleep technology for sleep-disordered breathing. The present report provides a background review of existing consumer sleep technologies and discloses the methods and procedures for a systematic review and meta-analysis of diagnostic test accuracy of these devices and apps for the detection of obstructive sleep apnea and snoring in comparison with polysomnography. The search will be performed in four databases (PubMed, Scopus, Web of Science, and the Cochrane Library). Studies will be selected in two steps, first by an analysis of abstracts followed by full-text analysis, and two independent reviewers will perform both phases. Primary outcomes include apnea-hypopnea index, respiratory disturbance index, respiratory event index, oxygen desaturation index, and snoring duration for both index and reference tests, as well as the number of true positives, false positives, true negatives, and false negatives for each threshold, as well as for epoch-by-epoch and event-by-event results, which will be considered for the calculation of surrogate measures (including sensitivity, specificity, and accuracy). Diagnostic test accuracy meta-analyses will be performed using the Chu and Cole bivariate binomial model. Mean difference meta-analysis will be performed for continuous outcomes using the DerSimonian and Laird random-effects model. Analyses will be performed independently for each outcome. Subgroup and sensitivity analyses will evaluate the effects of the types (wearables, nearables, bed sensors, smartphone applications), technologies (e.g., oximeter, microphone, arterial tonometry, accelerometer), the role of manufacturers, and the representativeness of the samples.

Distinguishing central from obstructive hypopneas on a clinical polysomnogram.

Among sleep-related disordered breathing events, hypopneas are the most frequent. Like obstructive and central apneas, hypopneas may be obstructive or central (reduced drive) in origin. Nevertheless, unlike apneas, categorizing hypopneas as either "obstructive" or "central" is often difficult or ambiguous. It has been suggested that hypopneas could be categorized as obstructive when associated with snoring, inspiratory flow limitation, or paradoxical thoraco-abdominal excursions. This approach, however, has not been extensively tested and misclassification of hypopneas is unavoidable. Yet, much rides on the accurate distinction of these events to guide therapy with medical devices or pharmacological therapy in each patient. Additionally, accurate hypopnea classification is critical for design of clinical trials, because therapeutic responses differ depending on the subtype of hypopnea. Correctly classifying hypopneas can also allay concerns about obtaining coverage for therapies that specifically target either central or obstructive sleep-disordered breathing events. The present paper expands on the current criteria for differentiating obstructive from central hypopneas and provides illustrative tracings that can help classify these events. CITATION: Javaheri S, Rapoport DM, Schwartz AR. Distinguishing central from obstructive hypopneas on a clinical polysomnogram. J Clin Sleep Med. 2023;19(4):823-834.