A multi-branch convolutional neural network for snoring detection based on audio.

Obstructive sleep apnea (OSA) is associated with various health complications, and snoring is a prominent characteristic of this disorder. Therefore, the exploration of a concise and effective method for detecting snoring has consistently been a crucial aspect of sleep medicine. As the easily accessible data, the identification of snoring through sound analysis offers a more convenient and straightforward method. The objective of this study was to develop a convolutional neural network (CNN) for classifying snoring and non-snoring events based on audio. This study utilized Mel-frequency cepstral coefficients (MFCCs) as a method for extracting features during the preprocessing of raw data. In order to extract multi-scale features from the frequency domain of sound sources, this study proposes the utilization of a multi-branch convolutional neural network (MBCNN) for the purpose of classification. The network utilized asymmetric convolutional kernels to acquire additional information, while the adoption of one-hot encoding labels aimed to mitigate the impact of labels. The experiment tested the network's performance by utilizing a publicly available dataset consisting of 1,000 sound samples. The test results indicate that the MBCNN achieved a snoring detection accuracy of 99.5%. The integration of multi-scale features and the implementation of MBCNN, based on audio data, have demonstrated a substantial improvement in the performance of snoring classification.

Sleep characteristics, early spontaneous movements, and developmental functioning in preterm infants in the early postnatal period.

OBJECTIVE: This study aimed to investigate the following: (i) sleep characteristics in preterm infants at 9-20 weeks of corrected age, and (ii) differences in early spontaneous movements and developmental functioning results between the groups based on some sleep characteristics. METHODS: Seventy-four preterm infants (36 female) were included. Sleep characteristics were assessed according to the Brief Infant Sleep Questionnaire (BISQ). The infants were divided into two groups based on total sleep duration: less than 12 h (38 infants), and 12 h and more (36 infants). Video recordings were made for the General Movements Assessment (GMA) and evaluated using the Motor Optimality Score for 3- to 5-Month-Old-Infants-Revised (MOS). Cognitive, language, and motor development were assessed using the Bayley Scales of Infant and Toddler Development, Third Edition (Bayley-III). RESULTS: The total sleep duration of all preterm infants (mean ± SD) was 11.8 ± 3.3 h. Infants who had absent fidgety movements slept less than 12 h, and fidgety movements differed between the groups (p = 0.012). Infants who slept 12 h or more had significantly higher MOS (p = 0.041), cognitive (p = 0.002), language (p < 0.001), and motor (p = 0.002) development results. Infants who snored had lower MOS (p = 0.001), cognitive (p = 0.004), language (p = 0.002), and motor (p = 0.001) development results. Infants with fewer than three nocturnal awakenings had significantly higher Bayley-III cognitive (p = 0.007), language (p = 0.032), and motor (p = 0.005) domain results. Prone and supine sleeping positions showed higher motor domain results than lateral positions (p = 0.001). CONCLUSIONS: Sleep in preterm infants might be a key factor in early developmental functioning processes and nervous system integrity. Even in the first months of life, there are substantial differences in cognitive, language, and motor development in association with sleep characteristics.

The relationship between body mass index and sleep in women with risk factors for gestational diabetes mellitus.

Background: Both obesity and sleep disorders are common among women during pregnancy. Although prior research has identified a relationship between obesity and sleep disorders, those findings are from women later in pregnancy. Objective: To explore the relationships between self-reported sleep duration, insufficient sleep and snoring with body mass index (BMI) among multiethnic women at risk of gestational diabetes mellitus (GDM)in early pregnancy. Methods: Cross-sectional study of baseline data from women at risk of GDM enrolled in the Treatment of BOoking Gestational diabetes Mellitus (TOBOGM) multicentre trial across 12 Australian/Austrian sites. Participants completed a questionnaire before 20 weeks' gestation to evaluate sleep. BMI <25 kg/m2 served as the reference group in multivariable logistic regression. Results: Among the 2865 women included, the prevalence of overweight and obesity classes I-III was 28%, 19%, 11% and 12%, respectively. There was no relationship between sleep duration and BMI. The risk of insufficient sleep >5 days/month was higher in class II and class III obesity (1.38 (1.03-1.85) and 1.34 (1.01-1.80), respectively), and the risk of snoring increased as BMI increased (1.59 (1.25-2.02), 2.68 (2.07-3.48), 4.35 (3.21-5.88) to 4.96 (3.65-6.74), respectively)). Conclusions: Obesity is associated with insufficient sleep among pregnant women at risk of GDM. Snoring is more prevalent with increasing BMI.

The effect of drug-induced sleep endoscopy on surgical outcomes for obstructive sleep apnea: a systematic review.

PURPOSE: Drug-induced sleep endoscopy (DISE) is the most widespread diagnostic tool for upper-airway endoscopic evaluation of snoring and obstructive sleep apnea (OSA). However, a consensus on the effectiveness of DISE on surgical outcomes is still lacking. This study aimed to quantify the effect of DISE on surgical outcomes and to compare DISE with awake examination using the Müller Maneuver (MM). METHODS: This systematic review was performed according to the PRISMA guidelines. Published studies from the last 30 years were retrieved from the Cochrane Library, MEDLINE, SCOPUS, and PubMed databases. Studies comparing DISE with awake examination, or MM were included. Surgical success rate was defined according to Sher's criteria, achieving a postoperative apnoea-hypopnea index (AHI) value < 20 events per hour and a 50% improvement from preoperative AHI. Outcomes are presented in terms of surgical success, pre- and postoperative AHI, Epworth sleepiness score (ESS), oxygen desaturation index (ODI) and lowest oxygen saturation (LOS). RESULTS: This review included 8 studies comprising 880 patients. DISE group showed a higher LOS increase, ODI decrease, ESS decrease than non-DISE group (6.83 ± 3.7 versus 3.68 ± 2.9, p<0.001; 19.6 ± 11.2 versus 12.6 ± 10.4, p<0.001; 6.72 ± 4.1 versus 3.69 ± 3.1, p<0.001). Differences in surgical success rate were significant only between DISE and MM (64.04% versus 52.48%, p = 0.016). AHI decrease resulted higher in non-DISE than in DISE group (39.92 ± 24.7 versus 30.53 ± 21.7, p<0.001). CONCLUSION: Results of this systematic review suggest that the evidence is mixed regarding a positive effect of DISE on surgical outcomes.

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.

Sensory processing and sleep characteristics in preterm infants in the early period of life.

OBJECTIVE: The present study aimed to investigate the following: (i) differences in sensory processing and sleep characteristics between preterm infants born at < 32 weeks', vs. those born at ≥ 32 weeks' gestation; (ii) differences in sleep characteristics between preterm infants with typical vs. atypical sensory processing; and (iii) relationship between sensory processing and sleep characteristics in preterm infants at 3 months of age. METHODS: A total of 189 preterm infants, 54 born at < 32 weeks' gestation (26 females; mean gestational age [standard deviation (SD)], 30.1 [1.7] weeks), and 135 born at ≥ 32 weeks' gestation (78 females; mean gestational age [SD], 34.9 [0.9] weeks) were included in the present study. Sleep characteristics were evaluated using the Brief Infant Sleep Questionnaire, and sensory processing was assessed using the Infant Sensory Profile-2. RESULTS: There were no significant differences in sensory processing (P > 0.05) or sleep characteristics (P > 0.05) between the preterm groups; however, more infants snored in the <32 weeks' gestation group (P = 0.035). Preterm infants with atypical sensory processing showed lower nighttime (P = 0.027) and total sleep durations (P = 0.032), and higher rates of nocturnal wakefulness (P = 0.038) and snoring (P = 0.001) than preterm infants with typical sensory processing. A significant relationship, therefore, was observed between sensory processing and sleep characteristics (P < 0.05). CONCLUSIONS: Sensory processing patterns may play an important role in understanding sleep problems in preterm infants. The early detection of sleep problems and sensory processing difficulties are necessary for early intervention.

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.

3D 4K exoscope in snore surgery simulation: pre-clinical experience.

PURPOSE: The application of 3D exoscopic technology is spreading worldwide, in several surgical scenarios. In this study, we present the first-time use of the exoscopic system (VITOM® and Versacrane™) in a cadaver simulation of transoral Snore Surgery. METHODS: All participants (n = 14) were asked to perform 2 exercises that simulate tasks required in Snore Surgery, they were then administered a questionnaire assessing their evaluation of the applied exoscopic technology. Participants were divided into groups according to age and experience. RESULTS: Mean zooming and focusing time was higher in young surgeons than in seniors, and similar results were obtained for mean procedural times. The responses to the questionnaire showed that in the vast majority (86%), the exoscopic technology was well rated. CONCLUSION: The exoscope can be considered a useful tool, thanks to its magnifying power and high-definition images, as well as for its indirect ability to enhance staff involvement in the procedure and for educational purposes.

Long-term average spectrum measures of consecutive snore sounds from different sources determined by drug-induced sleep endoscopy.

STUDY OBJECTIVES: The goal of this study was to investigate the value of the long-term average spectrum in the acoustic analysis of snore sounds arising from different sources in the upper airway. METHODS: Long-term average spectrum was used to analyze sequences of 10 consecutive snore sounds that had been divided into 2 groups, soft-palate type and lateral-wall type, according to the vibration site generating the snore sounds and the patterns of soft tissue collapse in the upper airway as identified by drug-induced sleep endoscopy. We calculated the first spectral peak, mean spectral energy, high-frequency energy, 0-1 kHz spectral energy, 1-5 kHz spectral energy, and 0-1 kHz/1-5 kHz difference from each group and compared the differences between them. RESULTS: All parameters except mean spectral energy showed significant differences between the 2 groups. The first spectral peak of less than 265.53 Hz, and the 0-1k/1-5 kHz difference of less than -11.6 dB strongly suggests soft-palate-type snore sounds. CONCLUSIONS: Long-term average spectrum has potential application for snore sound source identification. We recommend using first spectral peak and a 0-1 kHz/1-5 Hz difference to identify soft-palate-type snore sounds. CITATION: Peng H, Xu H, Xu Z, Jia R, Yu H. Long-term average spectrum measures of consecutive snore sounds from different sources determined by drug-induced sleep endoscopy. J Clin Sleep Med. 2023;19(1):145-150.

[Role of Robotic Surgery in ENT]. / Bedeutung der transoralen robotischen Chirurgie in der HNO.

Since the beginning of the 21st century, surgical robots have been used in the ENT-environment. They primarily support surgeons in minimal invasive transoral operations, especially in multidisciplinary treatment concepts of head and neck tumors, but also in snoring surgery the robot provides a complement to the established transoral laser surgery. In the meantime there is a large number of data that deals with the importance of oncological results, function maintenance, economics and future perspectives.Operation areas of the current robot devices are still limited in the ENT-environment. As the number of cases are small, efforts are being made to connect centres on a national and international level. Thus, uniform training standards, targeted knowledge and data exchange as well as further development of systems would be managed better. The creation of small and agile ENT-specific equipment could expand the possibilities as a next step for the future and finally lead to a wide scale of ENT-surgical applications.

Evaluation of the relationship between malocclusions and sleep-disordered breathing in children.

OBJECTIVE: To determine the relationship between dental/skeletal malocclusions and sleep-disordered breathing (SDB) in the early diagnosis and treatment of sleep disorders in children. METHODS: Patients were evaluated by pedodontists to identify dental, skeletal, and functional malocclusion (n = 240; <15 years). In order to determine the sleep and daytime behavior of the patients, pediatric sleep questionnaires (PSQ) were applied. Per results of the PSQ, patients with a mean of ≥ 0.33 were defined as the high-risk group. RESULTS: A total of 25.8% children were in the high-risk group, with the most convex profile, high-angle growth direction, and mandibular retrognathy. The prevalence of habitual snoring, mouth breathing, and dry mouth was 48.4%, 64.5%, and 87.2% among all high-risk children, respectively. CONCLUSION: Convex profile, high-angle growth direction, and retrognathic mandible were determined as risk factors for SDB. The prevalence of dry mouth, mouth breathing, and snoring was higher in the high-risk group.

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.

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.

Association of snoring characteristics with predominant site of collapse of upper airway in obstructive sleep apnea 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 hypothesized that multiparameter 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 obstructive sleep apnea 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 hypopnea 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 hypopnea event into three classes (lateral wall, palate, and tongue base). The predominant site of collapse for a sleep period was determined from the individual hypopnea 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 fit 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 hypopnea 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.

Application of substitution box of present cipher for automated detection of snoring sounds.

BACKGROUND AND PURPOSE: Snoring is one of the sleep disorders, and snoring sounds have been used to diagnose many sleep-related diseases. However, the snoring sound classification is done manually which is time-consuming and prone to human errors. An automated snoring sound classification model is proposed to overcome these problems. MATERIAL AND METHOD: This work proposes an automated snoring sound classification method using three new methods. These methods are maximum absolute pooling (MAP), the nonlinear present pattern, and two-layered neighborhood component analysis, and iterative neighborhood component analysis (NCAINCA) selector. Using these methods, a new snoring sound classification (SSC) model is presented. The MAP decomposition model is applied to snoring sounds to extract both low and high-level features. The presented model aims to attain high performance for SSC problem. The developed present pattern (Present-Pat) uses substitution box (SBox) and statistical feature generator. By deploying these feature generators, both textural and statistical features are generated. NCAINCA chooses the most informative/valuable features, and these selected features are fed to k-nearest neighbor (kNN) classifier with leave-one-out cross-validation (LOOCV). The Present-Pat based SSC system is developed using Munich-Passau Snore Sound Corpus (MPSSC) dataset comprising of four categories. RESULTS: Our model reached an accuracy and unweighted average recall (UAR) of 97.10 % and 97.60 %, respectively, using LOOCV. Moreover, a nocturnal sound dataset is used to show the universal success of the presented model. Our model attained an accuracy of 98.14 % using the used nocturnal sound dataset. CONCLUSIONS: Our developed classification model is ready to be tested with more data and can be used by sleep specialists to diagnose the sleep disorders based on snoring sounds.

Automatic classification of excitation location of snoring sounds.

STUDY OBJECTIVES: For surgical treatment of patients with obstructive sleep apnea-hypopnea syndrome, it is crucial to locate accurately the obstructive sites in the upper airway; however, noninvasive methods for locating the obstructive sites have not been well explored. Snoring, as the cardinal symptom of obstructive sleep apnea-hypopnea syndrome, should contain information that reflects the state of the upper airway. Through the classification of snores produced at four different locations, this study aimed to test the hypothesis that snores generated by various obstructive sites differ. METHODS: We trained and tested our model on a public data set that comprised 219 participants. For each snore episode, an acoustic and a physiological feature were extracted and concatenated, forming a 59-dimensional fusion feature. A principal component analysis and a support machine vector were used for dimensional reduction and snore classification. The performance of the proposed model was evaluated using several metrics: sensitivity, precision, specificity, area under the receiver operating characteristic curve, and F1 score. RESULTS: The unweighted average values of sensitivity, precision, specificity, area under the curve, and F1 were 86.36%, 89.09%, 96.4%, 87.9%, and 87.63%, respectively. The model achieved 98.04%, 80.56%, 72.73%, and 94.12% sensitivity for types V (velum), O (oropharyngeal), T (tongue), and E (epiglottis) snores. CONCLUSIONS: The characteristics of snores are related to the state of the upper airway. The machine-learning-based model can be used to locate the vibration sites in the upper airway.

Characteristics of pharyngeal paraesthesia symptoms in patients with obstructive sleep apnoea.

PURPOSE: This study aimed to investigate pharyngeal paraesthesia symptoms in patients with obstructive sleep apnoea (OSA). MATERIAL AND METHODS: Patients with snoring and suspected OSA as well as age-matched controls were recruited. All participants underwent nocturnal polysomnography (PSG) and pharyngeal paraesthesia assessment using the Glasgow-Edinburgh throat scale (GETS). The incidence and severity of pharyngeal paraesthesia symptoms were compared between the groups. RESULTS: A total of 280 patients who snored or were suspected of having OSA and 35 healthy, age-matched controls were recruited. The total pharyngeal paraesthesia symptom score was significantly higher in the OSA group than in the healthy group (12 [5, 23] vs. 3 [0, 9]; p < 0.001). The most frequent pharyngeal paraesthesia symptoms in the snore patients were Q7 (catarrh down the throat) and Q3 (discomfort/irritation in the throat), which are related to the irritability of the throat. The incidence of Q7 (OSA, 58% vs. controls, 14%; χ2 = 23.66; p < 0.001), Q3 (OSA, 46% vs. controls, 3%; χ2 = 23.07; p < 0.001), Q1 (feeling of something stuck in the throat; OSA, 33% vs. controls, 6%; χ2 = 11.00; p = 0.001), Q6 (swelling in the throat; OSA, 31% vs. controls, 0%; χ2 = 14.53; p < 0.001), Q9 (want to swallow all the time; OSA, 20% vs. controls, 6%; χ2 = 6.28; p = 0.012), Q5 (throat closing off; OSA, 24% vs. controls, 6%; χ2 = 6.16; p = 0.013), and Q2 (pain in the throat; OSA, 23% vs. controls, 6%; χ2 = 5.32; p = 0.021) was significantly higher in the OSA group than in the controls CONCLUSIONS: Patients with obstructive sleep apnoea have higher pharyngeal paraesthesia symptoms scores and tend to have irritated throats compared to healthy controls. CLINICAL TRIAL REGISTRATION: ClinicalTrials.gov identifier: NCT03506178.

Barbed suture Extrusion and Exposure in palatoplasty for OSA: What does it mean?

PURPOSE: Analyze Extrusion&Exposion (E&E), its implications in the functional, anatomical results and subjective discomfort in OSA patients treated with Barbed Reposition Pharyngoplasty (BRP). MATERIALS AND METHODS: 488 patients treated with BRP or multilevel TORS. Stratafix wire was used in 230 patients, V-Loc in 258. E&E, timing and localization evaluated at follow-up. Polygraphy used to assess the impact of E&E on functional results, PPOPS questionnaire used for subjective discomfort. RESULTS: E&E in the entire group was 18,4%, with significant difference between Stratafix and V-Loc wire (p = 0,002), but not between BRP alone and multilevel surgery (p = 0,68). 28,9% of extrusion happened within the first seven days, 76,7% between seven days and two months, 5,5% after two months. Symptomatic clinical profile has been seen in 62,2%, asymptomatic one in 37,8% of patients. 35,5% of E&E were localized in tonsillar bed, 46,7% in soft palate and 20% in other sites. Mean delta-AHI of E&E patients was -15,87 ± 16.82 compared with one of those who did not have E&E was -16.34 ± 22,77 (p = 0,38). Mean PPOPS of 183 patients analyzed was 12,32 ± 4,96. Mean PPOPS of extruded group was 12,94 ± 4,68 and 11,92 ± 5,11 in not extruded one (p = 0,166). CONCLUSIONS: E&E are suture-type sensitive (V-Loc > Stratafix), reported more frequent when BRP is performed alone than BRP-TORS with no statistical significance. 76,7% of the E&E occur after patient discharge and within 2 months. About half of the E&E were localized in soft palate. There is no need to fear Extrusion&Exposition because it does not affect in a negative way subjective and PSG outcome.

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.

Are annoyance scores based on sound pressure levels suitable for snoring assessment in the home environment?

PURPOSE: An objective statement about the annoyance of snoring can be made with the Psychoacoustic Snore Score (PSS). The PSS was developed based on subjective assessments and is strongly influenced by observed sound pressure levels. Robustness against day-to-day interfering noises is a fundamental requirement for use at home. This study investigated whether or not the PSS is suitable for use in the home environment. METHODS: Thirty-six interfering noises, which commonly occur at night, were played in the acoustic laboratory in parallel with 5 snoring sounds. The interfering noises were each presented at sound pressure levels ranging from 25 to 55 dB(A), resulting in 3255 distinct recordings. Annoyance was then assessed using the PSS. RESULTS: In the case of minimally annoying snoring sounds, interfering noises with a sound pressure level of 25 dB(A) caused significant PSS changes from 40 to 55 dB(A) for annoying snoring sounds. If the interfering noise was another snoring sound, the PSS was more robust depending on the sound pressure level of the interfering noise up to 10 dB(A). Steady (no-peak) interfering noises influenced the PSS more strongly than peak noises. CONCLUSIONS: The PSS is significantly distorted by quiet interfering noises. Its meaningfulness therefore depends strongly on the acoustic environment. It may therefore be assumed that scores dependent on sound pressure level are suitable for measurements when there is minimal ambient noise, as in the sleep laboratory. However, for measurements where noise is incalculable, as in the home environment, interfering noises may distort the results.