Ultrasonographic Detection of Airway Obstruction in a Model of Obstructive Sleep Apnea

A gated recurrent unit model based on ultrasound images of dynamic tongue movement for determining the severity of obstructive sleep apnea

Obstructive sleep apnea (OSA) presents as a respiratory disorder characterized by recurrent upper pharyngeal airway collapse during sleep. Dynamic tongue movement (DTM) analysis emerges as a promising avenue for elucidating the pathophysiological underpinnings of OSA, thereby facilitating its diagnosis. Recent endeavors have utilized artificial intelligence techniques to categorize OSA severity leveraging electrocardiography and blood oxygen saturation data. Nonetheless, the integration of ultrasound (US) imaging of the tongue remains largely untapped in the development of machine learning models aimed at determining the severity of OSA. This study endeavors to bridge this gap by capturing US images of DTM dynamics during wakefulness, encompassing transitions from normal breathing (NB) to the performance of the Müller maneuver (MM) in a cohort of 53 patients. Leveraging the modified optical flow method (MOFM), the trajectories of patients' DTM were tracked, facililtating the extraction of 27 parameters vital for model training. These parameters encompassed nine-point lateral movement, nine-point axial movement, and nine-point total displacement of the tongue, resulting in a dataset of 186,030 samples. The gated recurrent unit (GRU) method, renowned for its efficacy in motion tracking, was employed for model development in this study. Validation of the developed model was conducted via stratified k-fold cross-validation (SCV). The systems' overall performance in classifying OSA severity, as quantified by mean accuracy (MA), yielded a value of 43.49%. This pilot investigation marks an exploratory endeavor into the utilization of artificial intelligence for the classification of OSA severity based on US images and dynamic movement patterns. This novel model holds potential to assist clinicians in categorizing OSA severity and guiding the selection of pertinent treatment modalities tailored to the individual needs of patients afflicted with OSA.

Advanced Diagnostic Techniques in Obstructive Sleep Apnea

Optimal surgical and medical management of obstructive sleep apnea requires clinically reliable identification of patterns and sites of upper airway obstruction. A wide variety of modalities have been used to evaluate upper airway obstruction. Drug-induced sleep endoscopy (DISE) and cine MRI are increasingly used to identify upper airway obstruction sites, to characterize airway obstruction patterns, to determine optimum medical and surgical treatment, and to plan individualized surgical management. Here, we provide an overview of the applications of DISE and cine MRI in assessing upper airway obstruction in children and adults with obstructive sleep apnea.

Advanced Diagnostic Techniques in Obstructive Sleep Apnea

Optimal surgical and medical management of obstructive sleep apnea (OSA) requires clinically reliable identification of patterns and sites of upper airway obstruction. A wide variety of modalities has been used to evaluate upper airway obstruction. Drug-induced sleep endoscopy (DISE) and cine MRI are increasingly used to identify upper airway obstruction sites, to characterize airway obstruction patterns, to determine optimum medical and surgical treatment, and to plan individualized surgical management. Here, the authors provide an overview of the applications of DISE and cine MRI in assessing upper airway obstruction in children and adults with OSA.

Application of the new 'XU-line' in the dynamic ultrasonographic evaluation of the spatial displacement of anterior cervical tissues for airway management: protocol for a prospective observational study

INTRODUCTION

Patients with cervical spondylosis have a high incidence of difficult airway, and unpredicted difficult intubation may be life-threatening. Traditional predictors and imaging data may suggest a difficult airway, but these data have limited predictive value, with low sensitivity and specificity. Ultrasonography is a non-irradiating, reproducible, inexpensive and simple tool that provides good imaging of the cervical soft tissue for airway assessment. This study will use the new 'XU-line' in the dynamic ultrasonographic airway evaluation of the spatial displacement of the anterior cervical tissues to determine whether preoperative ultrasonographic assessment of the neck anatomy can predict difficult airway.

METHODS AND ANALYSIS

This prospective, observational study will be conducted in a single centre. Four hundred and eleven patients scheduled for anterior cervical decompression and fusion under general anaesthesia will be recruited. The parallel trunk reference line through the mentum is defined as the XU-line, and the spatial displacement of the anterior cervical soft tissue relative to the XU-line at six anatomical levels in the transverse plane and two distances in the sagittal plane will be measured on ultrasonography with the patient in the supine position and the sniff position. The spatial displacement distances of soft tissue structures relative to the XU-line will be compared between the 'easy intubation' and 'difficult intubation' groups (in accordance with the Cormack-Lehane classification). Receiver operating characteristic curves will be used to determine the sensitivity and specificity of the 'difficulty prediction capability' of each ultrasonographic and physical measurement. Multiple logistic regression analysis will be performed to determine the independent predictors of difficult intubation.

ETHICS AND DISSEMINATION

Ethical approval for this study has been obtained from the Peking University Third Hospital Medical Science Research Ethics Committee. The results of this study will be disseminated via a peer-reviewed publication and national and international conferences and workshops.

TRIAL REGISTRATION NUMBER

ChiCTR2000034446.

Ultrasound assessment of upper airway dilator muscle contraction during transcutaneous electrical stimulation in patients with obstructive sleep apnoea

Background

Electrical current can be used to stimulate upper airway dilator muscles to treat obstructive sleep apnoea (OSA). Ultrasound devices are widely available and may be used to detect contraction of the upper airway dilator muscles assessing the functionality of electrical stimulation (ES) used for this treatment.

Methods

In a physiological sub-study of a randomised controlled trial, patients with OSA underwent ultrasound examination to assess contraction of the upper airway dilator muscles in response to transcutaneous ES. Ultrasound scans were scored according to the picture quality (poor = '0', acceptable = '1' and good = '2'). Tongue base thickness was assessed in mid-sagittal and coronal planes with (D2, A2) and without ES (D1, A1), while awake and seated. The primary outcome was to determine the increase in tongue thickness during ES in both views (D2 - D1 = ΔD), as well as any increase in the cross-sectional area (CSA) in the coronal view (A2 - A1 = ΔA). Data were presented as mean and standard deviation (SD).

Results

Fourteen patients [eight male, age 57.5 (9.8) years, body mass index (BMI) 29.5 (2.8) kg/m²] with OSA [Apnea-Hypopnea Index (AHI) 19.5 (10.6) × hour^-1] were studied. Quality of the ultrasound scans was acceptable or good with 1.5 (0.5) points. In the mid-sagittal plane, ΔD was +0.17 (0.07) cm in midline and +0.21 (0.09) cm in the widest diameter, a percentual change of 12.2% (4%) and 12.8% (5.2%) (P<0.001, respectively). In the coronal plane, ΔD was +0.17 (0.04) cm, an increase of 12.3% (4.6%) (P<0.001, respectively), ΔA in the CSA increased by +18.9% (3.0%) with stimulation (P<0.001). There was a negative correlation between age and ΔA (r= -0.6, P=0.03), but no significant associations were found with gender, BMI, neck circumference, Epworth Sleepiness Scale (ESS), AHI, skin and subcutaneous tissue in the submental area.

Conclusions

Ultrasound can visualise upper airway dilator muscle contraction during transcutaneous ES in awake patients with OSA. Contraction is best detected in the CSA of the tongue base in the coronal plane.

Point-of-Care Ultrasound for Obstructive Sleep Apnea Screening: Are We There Yet? A Systematic Review and Meta-analysis

BACKGROUND

Perioperative diagnosis of obstructive sleep apnea (OSA) has important resource implications as screening questionnaires are overly sensitive, and sleep studies are expensive and time-consuming. Ultrasound (US) is a portable, noninvasive tool potentially useful for airway evaluation and OSA screening in the perioperative period. The objective of this systematic review was to evaluate the correlation of surface US with OSA diagnosis and to determine whether a point-of-care ultrasound (PoCUS) for OSA screening may help with improved screening in perioperative period.

METHODS

A search of all electronic databases including Medline, Embase, and Cochrane Database of Systematic Reviews was conducted from database inception to September 2017. Inclusion criteria were observational cohort studies and randomized controlled trials of known or suspected OSA patients undergoing surface US assessment. Article screening, data extraction, and summarization were conducted by 2 independent reviewers with ability to resolve conflict with supervising authors. Diagnostic properties and association between US parameters (index test) and OSA diagnosis using sleep study (reference standard) were evaluated. The US parameters were divided into airway and nonairway parameters. A random-effects meta-analysis was planned, wherever applicable.

RESULTS

Of the initial 3865 screened articles, 21 studies (7 airway and 14 nonairway) evaluating 3339 patients were included. Majority of studies were conducted in the general population (49%), respirology (23%), and sleep clinics (12%). No study evaluated the use of US for OSA in perioperative setting. Majority of included studies had low risk of bias for reference standard and flow and timing. Airway US parameters having moderate-good correlation with moderate-severe OSA were distance between lingual arteries (DLAs > 30 mm; sensitivity, 0.67; specificity, 0.59; 1 study/66 patients); mean resting tongue thickness (>60 mm; sensitivity, 0.85; specificity, 0.59; 1 study/66 patients); tongue base thickness during Muller maneuver (MM; sensitivity, 0.59; specificity, 0.78; 1 study/66 patients); and a combination of neck circumference and retropalatal (RP) diameter shortening during MM (sensitivity, 1.0; specificity, 0.65; 1 study/104 patients). Nonairway US parameters having a low-moderate correlation with moderate-severe OSA were carotid intimal thickness (pooled correlation coefficient, 0.444; 95% confidence interval [CI], 0.320-0.553; P value = .000, 8 studies/727 patients) and plaque presence (sensitivity, 0.24-0.75; specificity, 0.13-1.0; 4 studies/1183 patients).

CONCLUSIONS

We found that a number of airway and nonairway parameters were identified with moderate to good correlation with OSA diagnosis in the general population. In future studies, it remains to be seen whether PoCUS screening for a combination of these parameters can address the pitfalls of OSA screening questionnaires.

Domiciliary use of transcutaneous electrical stimulation for patients with obstructive sleep apnoea: a conceptual framework for the TESLA home programme

Obstructive sleep apnoea (OSA) is a global health problem of increasing prevalence. Effective treatments are available with continuous positive airway pressure (CPAP) therapy and mandibular advancement devices (MAD). However, there is limited long-term adherence to therapy, as CPAP and MAD require permanent usage to avoid recurrence of the symptoms and adverse ill health. Alternative treatments would aid in the treatment cascade to manage OSA effectively whenever standard therapy has been trialled and failed. Hypoglossal nerve stimulation (HNS), an invasive approach to stimulate the pharyngeal dilator muscles of the upper airway during sleep, has been approved for the treatment of OSA by several healthcare systems in recent years. In parallel to the development of HNS, a non-invasive approach has been developed to deliver electrical stimulation. Transcutaneous electrical stimulation in obstructive sleep apnoea (TESLA) uses non-invasive electrical stimulation to increase neuromuscular tone of the upper airway dilator muscles of patients with OSA during sleep. Data from previous feasibility studies and randomised controlled trials have helped to identify a subgroup of patients who are "responders" to this treatment. However, further investigations are required to assess usability, functionality and task accomplishment of this novel treatment. Consideration of these factors in the study design of future clinical trials will strengthen research methodology and protocols, improve patient related outcome measures and assessments, to optimise this emerging therapeutical option. In this review, we will introduce a conceptual framework for the TESLA home programme highlighting qualitative aspects and outcomes.