A Subject-Specific Acoustic Model of the Upper Airway for Snoring Sounds Generation

Usefulness of new acoustic respiratory sound monitoring with artificial intelligence for upper airway assessment in obese patients during monitored anesthesia care

Monitored anesthesia care (MAC) often causes airway complications, particularly posing an elevated risk of aspiration and airway obstruction in obese patients. This study aimed to quantify the levels of aspiration and airway obstruction using an artificial intelligence (AI)-based acoustic analysis algorithm, assessing its utility in identifying airway complications in obese patients. To verify the correlation between the stridor quantitative value (STQV) calculated by acoustic analysis and body weight, and to further evaluate fluid retention and airway obstruction, STQV calculated exhaled breath sounds collected at the neck region, was compared before and after injection of 3 ml of water in the oral cavity and at the start and end of the MAC procedures. STQV measured immediately following the initiation of MAC exhibited a weak correlation with body mass index. Furhtermore, STQV values before and after water injection increased predominantly after injection, further increased at the end of MAC. AI-based analysis of cervical respiratory sounds can enhance the safety of airway management during MAC by quantifying airway obstruction and fluid retention in obese patients. J. Med. Invest. 70 : 430-435, August, 2023.

Predicting upper airway collapse sites found in drug-induced sleep endoscopy from clinical data and snoring sounds in patients with obstructive sleep apnea: a prospective clinical study

STUDY OBJECTIVES

The primary aim was to predict upper airway collapse sites found in drug-induced sleep endoscopy (DISE) from demographic, anthropometric, clinical examination, sleep study, and snoring sound parameters in patients with obstructive sleep apnea (OSA). The secondary aim was to identify the above-mentioned parameters that are associated with complete concentric collapse of the soft palate.

METHODS

All patients with OSA who underwent DISE and simultaneous snoring sound recording were enrolled in this study. Demographic, anthropometric, clinical examination (viz., modified Mallampati classification and Friedman tonsil classification), and sleep study parameters were extracted from the polysomnography and DISE reports. Snoring sound parameters during DISE were calculated.

RESULTS

One hundred and nineteen patients with OSA (79.8% men; age = 48.1 ± 12.4 years) were included. Increased body mass index was found to be associated with higher probability of oropharyngeal collapse (P < .01; odds ratio = 1.29). Patients with a high Friedman tonsil score were less likely to have tongue base collapse (P < .01; odd ratio = 0.12) and epiglottic collapse (P = .01; odds ratio = 0.20) than those with a low score. A longer duration of snoring events (P = .05; odds ratio = 2.99) was associated with a higher probability of complete concentric collapse of the soft palate.

CONCLUSIONS

Within the current patient profile and approach, given that only a limited number of predictors were identified, it does not seem feasible to predict upper airway collapse sites found in DISE from demographic, anthropometric, clinical examination, sleep study, and snoring sound parameters in patients with OSA.

CITATION

Huang Z, Bosschieter PFN, Aarab G, et al. Predicting upper airway collapse sites found in drug-induced sleep endoscopy from clinical data and snoring sounds in obstructive sleep apnea patients: a prospective clinical study. J Clin Sleep Med. 2022;18(9):2119-2131.

Prediction of the obstruction sites in the upper airway in sleep-disordered breathing based on snoring sound parameters: a systematic review

BACKGROUND

Identification of the obstruction site in the upper airway may help in treatment selection for patients with sleep-disordered breathing. Because of limitations of existing techniques, there is a continuous search for more feasible methods. Snoring sound parameters were hypothesized to be potential predictors of the obstruction site. Therefore, this review aims to i) investigate the association between snoring sound parameters and the obstruction sites; and ii) analyze the methodology of reported prediction models of the obstruction sites.

METHODS

The literature search was conducted in PubMed, Embase.com, CENTRAL, Web of Science, and Scopus in collaboration with a medical librarian. Studies were eligible if they investigated the associations between snoring sound parameters and the obstruction sites, and/or reported prediction models of the obstruction sites based on snoring sound.

RESULTS

Of the 1016 retrieved references, 28 eligible studies were included. It was found that the characteristic frequency components generated from lower-level obstructions of the upper airway were higher than those generated from upper-level obstructions. Prediction models were built mainly based on snoring sound parameters in frequency domain. The reported accuracies ranged from 60.4% to 92.2%.

CONCLUSIONS

Available evidence points toward associations between the snoring sound parameters in the frequency domain and the obstruction sites in the upper airway. It is promising to build a prediction model of the obstruction sites based on snoring sound parameters and participant characteristics, but so far snoring sound analysis does not seem to be a viable diagnostic modality for treatment selection.

IoT snoring sound detector prototype as a model of future participatory healthcare

BACKGROUND

Traditional healthcare is centred around providing in-hospital services using hospital owned medical instruments. The COVID-19 pandemic has shown that this approach lacks flexibility to insure follow-up and treatment of common medical problems. In an alternative setting adapted to this problem, participatory healthcare can be considered centred around data provided by patients owning and operating medical data collection equipment in their homes.

OBJECTIVE

In order to trigger such a shift reliable and price attractive devices need to become available. Snoring, as a human sound production during sleep, can reflect sleeping behaviour and indicate sleep problems as an element of the overall health condition of a person.

METHODS

The use of off-the-shelf hardware from Internet of Things platforms and standard audio components allows the development of such devices. A prototype of a snoring sound detector with this purpose is developed.

RESULTS

The device, controlled by the patient and with specific snoring recording and analysing functions is demonstrated as a model for future participatory healthcare.

CONCLUSIONS

Design of monitoring devices following this model could allow market introduction of new equipment for participatory healthcare, bringing a care complementary to traditional healthcare to the reach of patients, and could result in benefits from enhanced patient participation.

Overnight airway obstruction severity prediction centered on acoustic properties of smart phone: validation with esophageal pressure

OBJECTIVE

Obstructive sleep apnea is characterized by a number of airway obstructions. Esophageal pressure manometry (EPM) based estimation of consecutive peak to trough differences (ΔPes) is the gold standard method to quantify the severity of airway obstructions. However, the procedure is rarely available in sleep laboratories due to invasive nature. There is a clinical need for a simplified, scalable technology that can quantify the severity of airway obstructions. In this paper, we address this and propose a pioneering technology, centered on sleep related respiratory sound (SRS) to predict overnight ΔPes signal.

APPROACH

We recorded streams of SRS using a bedside iPhone 7 smartphone from subjects undergoing diagnostic polysomnography (PSG) studies and EPM was performed concurrently. Overnight data was divided into epochs of 10 s duration with 50% overlap. Altogether, we extracted 42 181 such epochs from 13 subjects. Acoustic features and features from the two PSG signals serve as an input to train a machine learning algorithm to achieve mapping between non-invasive features and ΔPes values. A testing dataset of 14 171 epochs from four new subjects was used for validation.

MAIN RESULTS

The SRS based model predicted the ΔPes with a median of absolute error of 6.75 cmH2O (±0.59, r = 0.83(±0.03)). When information from the PSG were combined with the SRS, the model performance became: 6.37cmH2O (±1.02, r = 0.85(±0.04)).

SIGNIFICANCE

The smart phone based SRS alone, or in combination with routinely collected PSG signals can provide a non-invasive method to predict overnight ΔPes. The method has the potential to be automated and scaled to provide a low-cost alternative to EPM.

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

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

Relationship between Vowel Sound Features and Pharyngeal Airway Cross-Sectional Area during Normal Breathing

Assessment of the pharyngeal airway is becoming important for delivering personalized treatment and better management of sleep apnea. However, evaluation of the pharyngeal airway area is difficult in the current state of the art. It is essential to use simple and accessible technology to measure the pharyngeal airway area. As vowel sounds are generated by vocal cords vibration and characterized by the pharyngeal airway, vowel sounds have the potential to evaluate the pharyngeal airway area. The objective of this study was to investigate the relationship between acoustic features of vowel sounds and the pharyngeal airway cross-sectional area (PAXSA) between soft palate and glottis. Twenty subjects were included in this study whose PAXSA was measured by acoustic pharyngometry. Vowel sounds were recorded with a microphone while lying supine. Vowel sound average power was calculated in different frequency ranges of 100-3000 Hz, 100-500 Hz, 500-1000 Hz, 1000-1500 Hz, 1500-2000 Hz, 2000-2500 Hz and 2500-3000 Hz. Statistical analysis showed that the decreases in the PAXSA were strongly correlated with the higher average power of vowel sounds in all frequency ranges. These results showed that individuals with low PAXSA might articulate the vowel in higher intensity. Clinical Relevance - This study demonstrates that the pharyngeal airway cross-sectional area during normal breathing has a significant effect on vowel articulation. Thus, vowel sound features can be used to estimate the resting pharyngeal airway cross-sectional area.

Effects of Increased Pharyngeal Tissue Mass Due to Fluid Accumulation in the Neck on the Acoustic Features of Snoring Sounds in Men

STUDY OBJECTIVES

Snoring sounds are generated by the vibration of pharyngeal tissue due to the upper airway narrowing. While recorded by a microphone placed over the neck, snoring can pass through the pharyngeal tissue surrounding the upper airway. Thus, changes in the pharyngeal tissue content may change the acoustic properties of the snoring sounds. Rostral fluid shift and the consequent increases in neck fluid volume (NFV) and neck circumference (NC) can increase pharyngeal tissue mass. Therefore, the goal of this study was to investigate the relationship between increases in pharyngeal tissue mass, as assessed by increased NFV and NC, and snoring sounds features.

METHODS

We obtained data from a previous study where 20 males who were not obese participated in a daytime polysomnography and their NC and NFV were measured before and after sleep. During sleep, snoring sounds were recorded with a microphone placed over the neck. Spectral centroid of the snoring sounds was estimated. Then, the first five snoring segments were selected from the first and last 30 minutes of stage N2 sleep.

RESULTS

We found a significant decrease in the snoring spectral centroid from the beginning to end of sleep. We also found that spectral centroid from the end of sleep in frequency ranges below 200 Hz was inversely correlated with the increases in NFV and NC from before to after sleep.

CONCLUSIONS

These results suggest that snoring spectral centroid can be used as a noninvasive and convenient method to assess variations in the pharyngeal tissue mass.

Numerical study of dynamic glottis and tidal breathing on respiratory sounds in a human upper airway model

BACKGROUND

Human snores are caused by vibrating anatomical structures in the upper airway. The glottis is a highly variable structure and a critical organ regulating inhaled flows. However, the effects of the glottis motion on airflow and breathing sound are not well understood, while static glottises have been implemented in most previous in silico studies. The objective of this study is to develop a computational acoustic model of human airways with a dynamic glottis and quantify the effects of glottis motion and tidal breathing on airflow and sound generation.

METHODS

Large eddy simulation and FW-H models were adopted to compute airflows and respiratory sounds in an image-based mouth-lung model. User-defined functions were developed that governed the glottis kinematics. Varying breathing scenarios (static vs. dynamic glottis; constant vs. sinusoidal inhalations) were simulated to understand the effects of glottis motion and inhalation pattern on sound generation. Pressure distributions were measured in airway casts with different glottal openings for model validation purpose.

RESULTS

Significant flow fluctuations were predicted in the upper airways at peak inhalation rates or during glottal constriction. The inhalation speed through the glottis was the predominating factor in the sound generation while the transient effects were less important. For all frequencies considered (20-2500 Hz), the static glottis substantially underestimated the intensity of the generated sounds, which was most pronounced in the range of 100-500 Hz. Adopting an equivalent steady flow rather than a tidal breathing further underestimated the sound intensity. An increase of 25 dB in average was observed for the life condition (sine-dynamic) compared to the idealized condition (constant-rigid) for the broadband frequencies, with the largest increase of approximately 40 dB at the frequency around 250 Hz.

CONCLUSION

Results show that a severely narrowing glottis during inhalation, as well as flow fluctuations in the downstream trachea, can generate audible sound levels.

Associations of Overweight, Obesity and Related Factors with Sleep-Related Breathing Disorders and Snoring in Adolescents: A Cross-Sectional Survey

Background: Sleep-related breathing disorders (SRBD) have been identified as a major public health problem closely related to adolescent obesity. We aimed to estimate the prevalences of SRBD and snoring in adolescents in Changchun City, Northeastern China, and to evaluate the associated factors in this population. Methods: In total, 1955 adolescents aged 11–18 years were recruited in Changchun City using stratified cluster sampling. Parents and caretakers of children completed the questionnaires, which included demographic characteristics, anthropometric parameters and a pediatric sleep questionnaire (SRBD scale). Logistic regression was used to analyze the relationship between SRBD, snoring and other factors. Results: The prevalences of SRBD and snoring in our population were 3.7% and 3.3%, respectively, and the prevalences of overweight and obesity were 12.6% and 4.9%. Multivariate logistic regression showed that urban residence (OR = 2.356, 95%CI: 1.251–4.435) and post-term birth (OR = 3.275, 95%CI: 1.396–7.683) were significantly associated with SRBD. Preterm birth (OR = 2.255, 95%CI: 1.021–4.980) and parental education level of university and above (OR = 0.265, 95%CI: 0.083–0.850) were significantly associated with snoring. Overweight (OR = 2.063, 95%CI: 1.062–4.006) was also related to snoring. Conclusions: The prevalences of SRBD and snoring were similar to those reported in previous studies. Urban residence and post-term birth were important influencing factors for SRBD; overweight, highest parental education level (university and above) and preterm birth were key factors affecting snoring in adolescents.