Automatic detection, segmentation and assessment of snoring from ambient acoustic data

HEAR4Health: a blueprint for making computer audition a staple of modern healthcare

Recent years have seen a rapid increase in digital medicine research in an attempt to transform traditional healthcare systems to their modern, intelligent, and versatile equivalents that are adequately equipped to tackle contemporary challenges. This has led to a wave of applications that utilise AI technologies; first and foremost in the fields of medical imaging, but also in the use of wearables and other intelligent sensors. In comparison, computer audition can be seen to be lagging behind, at least in terms of commercial interest. Yet, audition has long been a staple assistant for medical practitioners, with the stethoscope being the quintessential sign of doctors around the world. Transforming this traditional technology with the use of AI entails a set of unique challenges. We categorise the advances needed in four key pillars: Hear, corresponding to the cornerstone technologies needed to analyse auditory signals in real-life conditions; Earlier, for the advances needed in computational and data efficiency; Attentively, for accounting to individual differences and handling the longitudinal nature of medical data; and, finally, Responsibly, for ensuring compliance to the ethical standards accorded to the field of medicine. Thus, we provide an overview and perspective of HEAR4Health: the sketch of a modern, ubiquitous sensing system that can bring computer audition on par with other AI technologies in the strive for improved healthcare systems.

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.

Tracheal sound-based apnea detection using hidden Markov model in sedated volunteers and post anesthesia care unit patients

The current method of apnea detection based on tracheal sounds is limited in certain situations. In this work, the Hidden Markov Model (HMM) algorithm based on segmentation is used to classify the respiratory and non-respiratory states of tracheal sounds, to achieve the purpose of apnea detection. Three groups of tracheal sounds were used, including two groups of data collected in the laboratory and a group of patient data in the post anesthesia care unit (PACU). One was used for model training, and the others (laboratory test group and clinical test group) were used for testing and apnea detection. The trained HMMs were used to segment the tracheal sounds in laboratory test data and clinical test data. Apnea was detected according to the segmentation results and respiratory flow rate/pressure which was the reference signal in two test groups. The sensitivity, specificity, and accuracy were calculated. For the laboratory test data, apnea detection sensitivity, specificity, and accuracy were 96.9%, 95.5%, and 95.7%, respectively. For the clinical test data, apnea detection sensitivity, specificity, and accuracy were 83.1%, 99.0% and 98.6%. Apnea detection based on tracheal sound using HMM is accurate and reliable for sedated volunteers and patients in PACU.

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

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

Development and Evaluation of a Pillow to Prevent Snoring Using the Cervical Spine Recurve Method

Snoring lowers the quality of sleep, causing many secondary diseases. In response, various types of preventive devices were manufactured, but most of them were far from actual snoring prevention by only sensing snoring and giving feedback. In this study, we proposed a new method to prevent snoring by adjusting the posture during sleep by widening the oropharynx space. An increase in the oropharynx area was confirmed through the expansion of the cervical spine, and a dedicated pillow that can extend through an angle of up to 20° was manufactured. Through this developed method, it was possible to easily extend the cervical spine angle in a supine position to the user, and the frequency of snoring was then tested. As a result, it was confirmed that by using the pillow with an expansion angle of 20° or more, snoring did not occur. Furthermore, looking at the evaluation results of the subjective levels of satisfaction, sleep-related items received an average of 5.9 or higher, and function-related items received high scores with an average of 5.7. We can confirm that the reliability of performance evaluation will be dramatically improved if the scope of the subject group is expanded to include various body types, ages, and genders and conduct performance evaluations for each group.

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

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

BI - Directional long short-term memory for automatic detection of sleep apnea events based on single channel EEG signal

Sleep apnea syndrome (SAS) is a sleeping disorder in which breathing stops regularly. Even though its prevalence is high, many cases are not reported due to the high cost of inspection and the limits of monitoring devices. To address this, based on the bidirectional long and short-term memory network (BI-LSTM), we designed a single-channel electroencephalography (EEG) sleep monitoring model that can be used in portable SAS monitoring devices. Model training and evaluation of EEG signals obtained by polysomnography were performed on the event segments of 42 subjects. Adam and 10-fold cross-validation were employed to optimize parameters and evaluate network performance. The results showed that BI-LSTM has a precision of 84.21% and accuracy of 92.73%.

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.

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

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

Recurrent Neural Network for Classification of Snoring and Non-Snoring Sound Events

Obstructive sleep apnea (OSA) is a disorder that affects up to 38% of the western population. It is characterized by repetitive episodes of partial or complete collapse of the upper airway during sleep. These episodes are almost always accompanied by loud snoring. Questionnaires such as STOP-BANG exploit snoring to screen for OSA. However, they are not quantitative and thus do not exploit its full potential. A method for automatic detection of snoring in whole-night recordings is required to enable its quantitative evaluation. In this study, we propose such a method. The centerpiece of the proposed method is a recurrent neural network for modeling of sequential data with variable length. Mel-frequency cepstral coefficients, which were extracted from snoring and non-snoring sound events, were used as inputs to the proposed network. A total of 20 subjects referred to clinical sleep recording were also recorded by a microphone that was placed 70 cm from the top end of the bed. These recordings were used to assess the performance of the proposed method. When it comes to the detection of snoring events, our results show that the proposed method has an accuracy of 95%, sensitivity of 92%, and specificity of 98%. In conclusion, our results suggest that the proposed method may improve the process of snoring detection and with that the process of OSA screening. Follow-up clinical studies are required to confirm this potential.

Detection of sleep disordered breathing severity using acoustic biomarker and machine learning techniques

PURPOSE

Breathing sounds during sleep are altered and characterized by various acoustic specificities in patients with sleep disordered breathing (SDB). This study aimed to identify acoustic biomarkers indicative of the severity of SDB by analyzing the breathing sounds collected from a large number of subjects during entire overnight sleep.

METHODS

The participants were patients who presented at a sleep center with snoring or cessation of breathing during sleep. They were subjected to full-night polysomnography (PSG) during which the breathing sound was recorded using a microphone. Then, audio features were extracted and a group of features differing significantly between different SDB severity groups was selected as a potential acoustic biomarker. To assess the validity of the acoustic biomarker, classification tasks were performed using several machine learning techniques. Based on the apnea-hypopnea index of the subjects, four-group classification and binary classification were performed.

RESULTS

Using tenfold cross validation, we achieved an accuracy of 88.3% in the four-group classification and an accuracy of 92.5% in the binary classification. Experimental evaluation demonstrated that the models trained on the proposed acoustic biomarkers can be used to estimate the severity of SDB.

CONCLUSIONS

Acoustic biomarkers may be useful to accurately predict the severity of SDB based on the patient's breathing sounds during sleep, without conducting attended full-night PSG. This study implies that any device with a microphone, such as a smartphone, could be potentially utilized outside specialized facilities as a screening tool for detecting SDB.

Acoustics of snoring and automatic snore sound detection in children

OBJECTIVE

Acoustic analyses of snoring sounds have been used to objectively assess snoring and applied in various clinical problems for adult patients. Such studies require highly automatized tools to analyze the sound recordings of the whole night's sleep, in order to extract clinically relevant snore- related statistics. The existing techniques and software used for adults are not efficiently applicable to snoring sounds in children, basically because of different acoustic signal properties. In this paper, we present a broad range of acoustic characteristics of snoring sounds in children (N  =  38) in comparison to adult (N  =  30) patients.

APPROACH

Acoustic characteristics of the signals were calculated, including frequency domain representations, spectrogram-based characteristics, spectral envelope analysis, formant structures and loudness of the snoring sounds.

MAIN RESULTS

We observed significant differences in spectral features, formant structures and loudness of the snoring signals of children compared to adults that may arise from the diversity of the upper airway anatomy as the principal determinant of the snore sound generation mechanism. Furthermore, based on the specific audio features of snoring children, we proposed a novel algorithm for the automatic detection of snoring sounds from ambient acoustic data specifically in a pediatric population. The respiratory sounds were recorded using a pair of microphones and a multi-channel data acquisition system simultaneously with full-night polysomnography during sleep. Brief sound chunks of 0.5 s were classified as either belonging to a snoring event or not with a multi-layer perceptron, which was trained in a supervised fashion using stochastic gradient descent on a large hand-labeled dataset using frequency domain features.

SIGNIFICANCE

The method proposed here has been used to extract snore-related statistics that can be calculated from the detected snore episodes for the whole night's sleep, including number of snore episodes (total snoring time), ratio of snore to whole sleep time, variation of snoring rate, regularity of snoring episodes in time and amplitude and snore loudness. These statistics will ultimately serve as a clinical tool providing information for the objective evaluation of snoring for several clinical applications.

SNORAP: A Device for the Correction of Impaired Sleep Health by Using Tactile Stimulation for Individuals with Mild and Moderate Sleep Disordered Breathing

Sleep physiology and sleep hygiene play significant roles in maintaining the daily lives of individuals given that sleep is an important physiological need to protect the functions of the human brain. Sleep disordered breathing (SDB) is an important disease that disturbs this need. Snoring and Obstructive Sleep Apnea Syndrome (OSAS) are clinical conditions that affect all body organs and systems that intermittently, repeatedly, with at least 10 s or more breathing stops that decrease throughout the night and disturb sleep integrity. The aim of this study was to produce a new device for the treatment of patients especially with position and rapid eye movement (REM)-dependent mild and moderate OSAS. For this purpose, the main components of the device (the microphone (snore sensor), the heart rate sensor, and the vibration motor, which we named SNORAP) were applied to five volunteer patients (male, mean age: 33.2, body mass index mean: 29.3). After receiving the sound in real time with the microphone, the snoring sound was detected by using the Audio Fingerprint method with a success rate of 98.9%. According to the results obtained, the severity and the number of the snoring of the patients using SNORAP were found to be significantly lower than in the experimental conditions in the apnea hypopnea index (AHI), apnea index, hypopnea index, in supine position’s AHI, and REM position’s AHI before using SNORAP (Paired Sample Test, p < 0.05). REM sleep duration and nocturnal oxygen saturation were significantly higher when compared to the group not using the SNORAP (Paired Sample Test, p < 0.05).

Automatic picking of snore events from overnight breath sound recordings

Snoring is one of the earliest symptoms of Obstructive Sleep Apnea (OSA). However, the unavailability of an objective snore definition is a major obstacle in developing automated snore analysis system for OSA screening. The objectives of this paper is to develop a method to identify and extract snore sounds from a continuous sound recording following an objective definition of snore that is independent of snore loudness. Nocturnal sounds from 34 subjects were recorded using a non-contact microphone and computerized data-acquisition system. Sound data were divided into non-overlapping training (n = 21) and testing (n = 13) datasets. Using training dataset an Artificial Neural Network (ANN) classifier were trained for snore and non-snore classification. Snore sounds were defined based on the key observation that sounds perceived as `snores' by human are characterized by repetitive packets of energy that are responsible for creating the vibratory sound peculiar to snorers. On the testing dataset, the accuracy of ANN classifier ranged between 86 - 89%. Our results indicate that it is possible to define snoring using loudness independent, objective criteria, and develop automated snore identification and extraction algorithms.

Validation of a new snoring detection device based on a hysteresis extraction algorithm

OBJECTIVE

This paper aims to introduce and validate our newly developed snoring detection device to automatically identify the incidence and amplitude of snores using the hysteresis extraction method.

METHODS

Thirty patients (16 males and 14 females) with a history of snoring were included in this study. Each patient underwent a conventional polysomnography (PSG). Natural overnight snoring was recorded from each subject using our original snore detection device and an integrated circuit (IC) recorder while the patient slept during PSG. A new algorithm based on hysteresis extraction was used to detect snores and qualify the level of each event at 30-s intervals (one epoch). The automated and subjective assessment concordance was evaluated by comparing a total of 27,295 epochs, and sensitivity, specificity, and accuracy were calculated.

RESULTS

Study population analysis revealed a mean rate of snore time against the total sleep time of 14.1±7.9%. Further, validation of the automatic snore detection revealed the following: sensitivity, 71.2%; specificity, 93.1%; positive predictive value, 77.7%; negative predictive value, 94.6%; and accuracy, 90.7%.

CONCLUSIONS

This study revealed the efficacy of our newly developed snoring detection device and indicated that it may serve as a useful method in further snoring analysis via objective medical assessment. However, the sample size of 30 subjects was relatively small; therefore, further research is needed to evaluate this device.

Breathing and Snoring Sound Characteristics during Sleep in Adults

STUDY OBJECTIVES

Sound level meter is the gold standard approach for snoring evaluation. Using this approach, it was established that snoring intensity (in dB) is higher for men and is associated with increased apnea-hypopnea index (AHI). In this study, we performed a systematic analysis of breathing and snoring sound characteristics using an algorithm designed to detect and analyze breathing and snoring sounds. The effect of sex, sleep stages, and AHI on snoring characteristics was explored.

METHODS

We consecutively recruited 121 subjects referred for diagnosis of obstructive sleep apnea. A whole night audio signal was recorded using noncontact ambient microphone during polysomnography. A large number (> 290,000) of breathing and snoring (> 50 dB) events were analyzed. Breathing sound events were detected using a signal-processing algorithm that discriminates between breathing and nonbreathing (noise events) sounds.

RESULTS

Snoring index (events/h, SI) was 23% higher for men (p = 0.04), and in both sexes SI gradually declined by 50% across sleep time (p < 0.01) independent of AHI. SI was higher in slow wave sleep (p < 0.03) compared to S2 and rapid eye movement sleep; men have higher SI in all sleep stages than women (p < 0.05). Snoring intensity was similar in both genders in all sleep stages and independent of AHI. For both sexes, no correlation was found between AHI and snoring intensity (r = 0.1, p = 0.291).

CONCLUSIONS

This audio analysis approach enables systematic detection and analysis of breathing and snoring sounds from a full night recording. Snoring intensity is similar in both sexes and was not affected by AHI.

Sleep-related breathing biomarkers as a predictor of vital functions

Because an average human spends one third of his life asleep, it is apparent that the quality of sleep has an important impact on the overall quality of life. To properly understand the influence of sleep, it is important to know how to detect its disorders such as snoring, wheezing, or sleep apnea. The aim of this study is to investigate the predictive capability of a dual-modality analysis scheme for methods of sleep-related breathing disorders (SRBDs) using biosignals captured during sleep. Two logistic regressions constructed using backward stepwise regression to minimize the Akaike information criterion were extensively considered. To evaluate classification correctness, receiver operating characteristic (ROC) curves were used. The proposed classification methodology was validated with constructed Random Forests methodology. Breathing sounds and electrocardiograms of 15 study subjects with different degrees of SRBD were captured and analyzed. Our results show that the proposed classification model based on selected parameters for both logistic regressions determine the different types of acoustic events during sleep. The ROC curve indicates that selected parameters can distinguish normal versus abnormal events during sleep with high sensitivity and specificity. The percentage of prediction for defined SRBDs is very high. The initial assumption was that the quality of result is growing with the number of parameters included in the model. The best recognition reached is more than 89% of good predictions. Thus, sleep monitoring of breath leads to the diagnosis of vital function disorders. The proposed methodology helps find a way of snoring rehabilitation, makes decisions concerning future treatment, and has an influence on the sleep quality.

Snoring sound classification from respiratory signal

Snoring is common in the general population and the irregularity could lead to the presence of Obstructive sleep apnea. Diagnosis of OSA could therefore be made by snoring sound analysis. However, there is still a shortage of robust methods to automatically detect snoring sounds without the need to calibrate for every individual. In this paper, a novel method based on neural network is proposed to classify breathing sound episodes from snoring and non-snoring sound segments. Our snore detection algorithm was applied to the tracheal sounds of nine individuals with different OSA severities. On the testing dataset, the classifier achieved a sensitivity and specificity of 95.9% and 97.6% respectively. Our results indicate that using such a method could help to detect snoring sounds with high accuracy which would be useful in the diagnosis of sleep apnea.

Audio signal analysis in combination with noncontact bio-motion data to successfully monitor snoring

This paper proposes a novel algorithm for automatic detection of snoring in sleep by combining non-contact bio-motion data with audio data. The audio data is captured using low end Android Smartphones in a non-clinical environment to mimic a possible user-friendly commercial product for sleep audio monitoring. However snore detection becomes a more challenging problem as the recorded signal has lower quality compared to those recorded in clinical environment. To have an accurate classification of snore/non-snore, we first compare a range of commonly used features extracted from the audio signal to find the best subject-independent features. Thereafter, bio-motion data is used to further improve the classification accuracy by identifying episodes which contain high amounts of body movements. High body movement indicates that the subject is turning, coughing or leaving the bed; during these instances snoring does not occur. The proposed algorithm is evaluated using the data recorded over 25 sessions from 7 healthy subjects who are suspected to be regular snorers. Our experimental results showed that the best subject-independent features for snore/non-snore classification are the energy of frequency band 3150-3650 Hz, zero crossing rate and 1st predictor coefficient of linear predictive coding. The proposed features yielded an average classification accuracy of 84.35%. The introduction of bio-motion data significantly improved the results by an average of 5.87% (p<;0.01). This work is the first study that successfully used bio-motion data to improve the accuracy of snore/non-snore classification.

Hidden Markov modelling of intra-snore episode behavior of acoustic characteristics of obstructive sleep apnea patients

Obstructive sleep apnea (OSA) is a breathing disorder that can cause serious medical consequences. It is caused by full (apnea) or partial (hypopnea) obstructions of the upper airway during sleep. The gold standard for diagnosis of OSA is the polysomnography (PSG). The main measure for OSA diagnosis is the apnea-hypopnea index (AHI). However, the AHI is a time averaged summary measure of vast amounts of information gathered in an overnight PSG study. It cannot capture the dynamic characteristics associated with apnea/hypopnea events and their overnight distribution. The dynamic characteristics of apnea/hypopnea events are affected by the structural and functional characteristics of the upper airway. The upper airway characteristics also affect the upper airway collapsibility. These effects are manifested in snoring sounds generated from the vibrations of upper airway structures which are then modified by the upper airway geometric and physical characteristics. Hence, it is highly likely that the acoustical behavior of snoring is affected by the upper airway structural and functional characteristics. In the current work, we propose a novel method to model the intra-snore episode behavior of the acoustic characteristics of snoring sounds which can indirectly describe the instantaneous and temporal dynamics of the upper airway. We model the intra-snore episode acoustical behavior by using hidden Markov models (HMMs) with Mel frequency cepstral coefficients. Assuming significant differences in the anatomical and physiological upper airway configurations between low-AHI and high-AHI subjects, we defined different snorer groups with respect to AHI thresholds 15 and 30 and also developed HMM-based classifiers to classify snore episodes into those groups. We also define a measure called instantaneous apneaness score (IAS) in terms of the log-likelihoods produced by respective HMMs. IAS indicates the degree of class membership of each episode to one of the predefined groups as well as the instantaneous OSA severity. We then assigned each patient to an overall AHI band based on the majority vote of each episode of snoring. The proposed method has a diagnostic sensitivity and specificity between 87-91%.

Nasal pressure recordings for automatic snoring detection

This study presents a rule-based method for automated, real-time snoring detection using nasal pressure recordings during overnight sleep. Although nasal pressure recordings provide information regarding nocturnal breathing abnormalities in a polysomnography (PSG) study or continuous positive airway pressure (CPAP) system, an objective assessment of snoring detection using these nasal pressure recordings has not yet been reported in the literature. Nasal pressure recordings were obtained from 55 patients with obstructive sleep apnea. The PSG data were also recorded simultaneously to evaluate the proposed method. This rule-based method for automatic, real-time snoring detection employed preprocessing, short-time energy and the central difference method. Using this methodology, a sensitivity of 85.4% and a positive predictive value of 92.0% were achieved in all patients. Therefore, we concluded that the proposed method is a simple, portable and cost-effective tool for real-time snoring detection in PSG and CPAP systems that does not require acoustic analysis using a microphone.

Automatic snoring detection from nasal pressure data

This study presents a method for automatic snoring detection from a nasal pressure data. First, a spectrogram analysis was performed in order to obtain information about the spectral characteristic of nasal pressure data. The automatic method is based on a simple signal filtering and short-time energy technique. Fifteen patients were participated in order to evaluation the performance of the proposed method. Results are compared with manually labeled snoring events by watching video records. The sensitivity and positive predictivity value were 93.73% and 93.70%, respectively. The results in this study could provide sleep experts with the method to objectively monitor sleep-disordered breathing in CPAP system or PSG study.

Acoustic Analysis of Snoring in the Diagnosis of Obstructive Sleep Apnea Syndrome: A Call for More Rigorous Studies

BACKGROUND

Snoring is a common symptom of obstructive sleep apnea syndrome (OSA) and has recently been considered for diagnosis of OSA.

OBJECTIVES

The goal of the current study was to systematically determine the accuracy of acoustic analysis of snoring in the diagnosis of OSA using a meta-analysis.

METHODS

PubMed, Cochrane Library database, and EMBASE were searched up to July 15, 2014. A systematic review and meta-analysis of sensitivity, specificity, and other measures of accuracy of acoustic analysis of snoring in the diagnosis of OSA were conducted. The median of apneahypopnea index threshold was 10 events/h, range: 5-15 or 10-15 if aforementioned suggestion is adopted.

RESULTS

A total of seven studies with 273 patients were included in the meta-analysis. The pooled estimates were as follows: sensitivity, 88% (95% confidence interval [CI]: 82-93%); specificity, 81% (95% CI: 72-88%); positive likelihood ratio (PLR), 4.44 (95% CI: 2.39-8.27); negative likelihood ratio (NLR), 0.15 (95% CI: 0.10-0.24); and diagnostic odds ratio (DOR), 32.18 (95% CI: 13.96-74.81). χ(2) values of sensitivity, specificity, PLR, NLR, and DOR were 2.37, 10.39, 12.57, 3.79, and 6.91 respectively (All p > 0.05). The area under the summary receiver operating characteristic curve was 0.93. Sensitivity analysis demonstrated that the pooled estimates were stable and reliable. The results of publication bias were not significant (p = 0.30).

CONCLUSIONS

Acoustic analysis of snoring is a relatively accurate but not a strong method for diagnosing OSA. There is an urgent need for rigorous studies involving large samples and single snore event tests with an efficacy criterion that reflects the particular features of snoring acoustics for OSA diagnosis.

Polyvinylidene fluoride sensor-based method for unconstrained snoring detection

We established and tested a snoring detection method using a polyvinylidene fluoride (PVDF) sensor for accurate, fast, and motion-artifact-robust monitoring of snoring events during sleep. Twenty patients with obstructive sleep apnea participated in this study. The PVDF sensor was located between a mattress cover and mattress, and the patients' snoring signals were unconstrainedly measured with the sensor during polysomnography. The power ratio and peak frequency from the short-time Fourier transform were used to extract spectral features from the PVDF data. A support vector machine was applied to the spectral features to classify the data into either the snore or non-snore class. The performance of the method was assessed using manual labelling by three human observers as a reference. For event-by-event snoring detection, PVDF data that contained 'snoring' (SN), 'snoring with movement' (SM), and 'normal breathing' epochs were selected for each subject. As a result, the overall sensitivity and the positive predictive values were 94.6% and 97.5%, respectively, and there was no significant difference between the SN and SM results. The proposed method can be applied in both residential and ambulatory snoring monitoring systems.

Voice dosimetry and monitoring, with emphasis on professional voice diseases: Critical review and framework for future research

Professional voice has become an important issue in the field of occupational health. Similarly, voice diseases related to occupations gain interest in insurance medicine, particularly within the frame of specific insurance systems for occupational diseases. Technological developments have made possible dosimetry of voice loading in the work-place, as well as long-term monitoring of relevant voice parameters during professional activities. A critical review is given, with focus on the specificity of occupational voice use and on the point of view of insurance medicine. Remaining questions and suggestions for future research are proposed.

Snore related signals processing in a private cloud computing system

Snore related signals (SRS) have been demonstrated to carry important information about the obstruction site and degree in the upper airway of Obstructive Sleep Apnea-Hypopnea Syndrome (OSAHS) patients in recent years. To make this acoustic signal analysis method more accurate and robust, big SRS data processing is inevitable. As an emerging concept and technology, cloud computing has motivated numerous researchers and engineers to exploit applications both in academic and industry field, which could have an ability to implement a huge blue print in biomedical engineering. Considering the security and transferring requirement of biomedical data, we designed a system based on private cloud computing to process SRS. Then we set the comparable experiments of processing a 5-hour audio recording of an OSAHS patient by a personal computer, a server and a private cloud computing system to demonstrate the efficiency of the infrastructure we proposed.

A review of signals used in sleep analysis

This article presents a review of signals used for measuring physiology and activity during sleep and techniques for extracting information from these signals. We examine both clinical needs and biomedical signal processing approaches across a range of sensor types. Issues with recording and analysing the signals are discussed, together with their applicability to various clinical disorders. Both univariate and data fusion (exploiting the diverse characteristics of the primary recorded signals) approaches are discussed, together with a comparison of automated methods for analysing sleep.

Automatic detection of whole night snoring events using non-contact microphone

Objective

Although awareness of sleep disorders is increasing, limited information is available on whole night detection of snoring. Our study aimed to develop and validate a robust, high performance, and sensitive whole-night snore detector based on non-contact technology.

Design

Sounds during polysomnography (PSG) were recorded using a directional condenser microphone placed 1 m above the bed. An AdaBoost classifier was trained and validated on manually labeled snoring and non-snoring acoustic events.

Patients

Sixty-seven subjects (age 52.5±13.5 years, BMI 30.8±4.7 kg/m², m/f 40/27) referred for PSG for obstructive sleep apnea diagnoses were prospectively and consecutively recruited. Twenty-five subjects were used for the design study; the validation study was blindly performed on the remaining forty-two subjects.

Measurements and Results

To train the proposed sound detector, >76,600 acoustic episodes collected in the design study were manually classified by three scorers into snore and non-snore episodes (e.g., bedding noise, coughing, environmental). A feature selection process was applied to select the most discriminative features extracted from time and spectral domains. The average snore/non-snore detection rate (accuracy) for the design group was 98.4% based on a ten-fold cross-validation technique. When tested on the validation group, the average detection rate was 98.2% with sensitivity of 98.0% (snore as a snore) and specificity of 98.3% (noise as noise).

Conclusions

Audio-based features extracted from time and spectral domains can accurately discriminate between snore and non-snore acoustic events. This audio analysis approach enables detection and analysis of snoring sounds from a full night in order to produce quantified measures for objective follow-up of patients.

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.

Snoring analysis for the screening of Sleep Apnea Hypopnea Syndrome with a single-channel device developed using polysomnographic and snoring databases

Several studies have shown differences in acoustic snoring characteristics between patients with Sleep Apnea-Hypopnea Syndrome (SAHS) and simple snorers. Usually a few manually isolated snores are analyzed, with an emphasis on postapneic snores in SAHS patients. Automatic analysis of snores can provide objective information over a longer period of sleep. Although some snore detection methods have recently been proposed, they have not yet been applied to full-night analysis devices for screening purposes. We used a new automatic snoring detection and analysis system to monitor snoring during full-night studies to assess whether the acoustic characteristics of snores differ in relation to the Apnea-Hypopnea Index (AHI) and to classify snoring subjects according to their AHI. A complete procedure for device development was designed, using databases with polysomnography (PSG) and snoring signals. This included annotation of many types of episodes by an expert physician: snores, inspiration and exhalation breath sounds, speech and noise artifacts, The AHI of each subject was estimated with classical PSG analysis, as a gold standard. The system was able to correctly classify 77% of subjects in 4 severity levels, based on snoring analysis and sound-based apnea detection. The sensitivity and specificity of the system, to identify healthy subjects from pathologic patients (mild to severe SAHS), were 83% and 100%, respectively. Besides, the Apnea Index (AI) obtained with the system correlated with the obtained by PSG or Respiratory Polygraphy (RP) (r=0.87, p<0.05).

Automatic and unsupervised snore sound extraction from respiratory sound signals

In this paper, an automatic and unsupervised snore detection algorithm is proposed. The respiratory sound signals of 30 patients with different levels of airway obstruction were recorded by two microphones: one placed over the trachea (the tracheal microphone), and the other was a freestanding microphone (the ambient microphone). All the recordings were done simultaneously with full-night polysomnography during sleep. The sound activity episodes were identified using the vertical box (V-Box) algorithm. The 500-Hz subband energy distribution and principal component analysis were used to extract discriminative features from sound episodes. An unsupervised fuzzy C-means clustering algorithm was then deployed to label the sound episodes as either snore or no-snore class, which could be breath sound, swallowing sound, or any other noise. The algorithm was evaluated using manual annotation of the sound signals. The overall accuracy of the proposed algorithm was found to be 98.6% for tracheal sounds recordings, and 93.1% for the sounds recorded by the ambient microphone.

Continuous analysis and monitoring of snores and their relationship to the apnea-hypopnea index

OBJECTIVES/HYPOTHESIS

We used a new automatic snoring detection and analysis system to monitor snoring during full-night polysomnography to assess whether the acoustic characteristics of snores differ in relation to the apnea-hypopnea index (AHI) and to classify subjects according to their AHI.

STUDY DESIGN

Individual Case-Control Study.

METHODS

Thirty-seven snorers (12 females and 25 males; ages 40-65 years; body mass index (BMI), 29.65 +/- 4.7 kg/m(2)) participated. Subjects were divided into three groups: G1 (AHI <5), G2 (AHI >or=5, <15) and G3 (AHI >or=15). Snore and breathing sounds were recorded with a tracheal microphone throughout 6 hours of nighttime polysomnography. The snoring episodes identified were automatically and continuously analyzed with a previously trained 2-layer feed-forward neural network. Snore number, average intensity, and power spectral density parameters were computed for every subject and compared among AHI groups. Subjects were classified using different AHI thresholds by means of a logistic regression model.

RESULTS

There were significant differences in supine position between G1 and G3 in sound intensity; number of snores; standard deviation of the spectrum; power ratio in bands 0-500, 100-500, and 0-800 Hz; and the symmetry coefficient (P < .03). Patients were classified with thresholds AHI = 5 and AHI = 15 with a sensitivity (specificity) of 87% (71%) and 80% (90%), respectively.

CONCLUSIONS

A new system for automatic monitoring and analysis of snores during the night is presented. Sound intensity and several snore frequency parameters allow differentiation of snorers according to obstructive sleep apnea syndrome severity (OSAS). Automatic snore intensity and frequency monitoring and analysis could be a promising tool for screening OSAS patients, significantly improving the managing of this pathology.

Unsupervised classification of respiratory sound signal into snore/no-snore classes

In this study, an automatic and online snore detection algorithm is proposed. The respiratory sound signals were recorded simultaneously with Polysomnography (PSG) data during sleep from 20 patients (10 simple snorers and 10 OSA patients). The sound signals were recorded by two tracheal and ambient microphones. The potential snoring episodes were identified using Vertical Box (V-Box) algorithm. The normalized 500Hz sub-band energy features of each episode were calculated. Principal component analysis (PCA) was applied to a 10-dimensional feature space to reduce it to a new 2-dimensional feature space. An unsupervised K-means clustering algorithm was then deployed to label the sound episodes as either snore or no-snore class. The performance of the algorithm was evaluated using manual annotation of the sound signals. The overall accuracy of the system was found to be 98.2% for the tracheal recordings and 95.5% for the sounds recorded by the ambient microphone.

Formant analysis of breath and snore sounds

Formant frequencies of snore and breath sounds represent resonance in the upper airways; hence, they change with respect to the upper airway anatomy. Therefore, formant frequencies and their variations can be examined to distinguish between snore and breath sounds. In this paper, formant frequencies of snore and breath sounds are investigated and automatically grouped into 7 clusters based on K-Means clustering. First, formants clusters of breath and snore sounds of all subjects were investigated together and their union were calculated as the most probable ranges of the formants. The ranges for the first four formants which span the main frequency components of breath and snore sounds were found to be [20-400]Hz, [270-840]Hz, [500-1380]Hz and [910-1920]Hz. These ranges were then used as priori information to recalculate the formants of snore and breath sounds separately. Statistical t-test showed the 1(st) and 3(rd) formants to be the most characteristic features in distinguishing the breath and snore sounds from each other.

The acoustics of snoring

Snoring is a prevalent disorder affecting 20-40% of the general population. The mechanism of snoring is vibration of anatomical structures in the pharyngeal airway. Flutter of the soft palate accounts for the harsh aspect of the snoring sound. Natural or drug-induced sleep is required for its appearance. Snoring is subject to many influences such as body position, sleep stage, route of breathing and the presence or absence of sleep-disordered breathing. Its presentation may be variable within or between nights. While snoring is generally perceived as a social nuisance, rating of its noisiness is subjective and, therefore, inconsistent. Objective assessment of snoring is important to evaluate the effect of treatment interventions. Moreover, snoring carries information relating to the site and degree of obstruction of the upper airway. If evidence for monolevel snoring at the site of the soft palate is provided, the patient may benefit from palatal surgery. These considerations have inspired researchers to scrutinize the acoustic characteristics of snoring events. Similarly to speech, snoring is produced in the vocal tract. Because of this analogy, existing techniques for speech analysis have been applied to evaluate snoring sounds. It appears that the pitch of the snoring sound is in the low-frequency range (<500 Hz) and corresponds to a fundamental frequency with associated harmonics. The pitch of snoring is determined by vibration of the soft palate, while nonpalatal snoring is more 'noise-like', and has scattered energy content in the higher spectral sub-bands (>500 Hz). To evaluate acoustic properties of snoring, sleep nasendoscopy is often performed. Recent evidence suggests that the acoustic quality of snoring is markedly different in drug-induced sleep as compared with natural sleep. Most often, palatal surgery alters sound characteristics of snoring, but is no cure for this disorder. It is uncertain whether the perceived improvement after palatal surgery, as judged by the bed partner, is due to an altered sound spectrum. Whether some acoustic aspects of snoring, such as changes in pitch, have predictive value for the presence of obstructive sleep apnea is at present not sufficiently substantiated.

Normal probability testing of snore signals for diagnosis of obstructive sleep apnea

Obstructive Sleep Apnea (OSA) is a highly prevalent disease in which upper airways are collapsed during sleep, leading to serious consequences. The standard method of OSA diagnosis is known as Polysomnography (PSG), which requires an overnight stay in a specifically equipped facility, connected to over 15 channels of measurements. PSG requires (i) contact instrumentation and, (ii) the expert human scoring of a vast amount of data based on subjective criteria. PSG is expensive, time consuming and is difficult to use in community screening or pediatric assessment. Snoring is the most common symptom of OSA. Despite the vast potential, however, it is not currently used in the clinical diagnosis of OSA. In this paper, we propose a novel method of snore signal analysis for the diagnosis of OSA. The method is based on a novel feature that quantifies the non-Gaussianity of individual episodes of snoring. The proposed method was evaluated using overnight clinical snore sound recordings of 86 subjects. The recordings were made concurrently with routine PSG, which was used to establish the ground truth via standard clinical diagnostic procedures. The results indicated that the developed method has a detectability accuracy of 97.34%.