The Predictive Role of Subcutaneous Adipose Tissue in the Pathogenesis of Obstructive Sleep Apnoea

Abstract

Introduction: Our aim was to investigate the applicability of artificial intelligence in predicting obstructive sleep apnoea (OSA) and upper airway obstruction using ultrasound (US) measurements of subcutaneous adipose tissues (SAT) in the regions of the neck, chest and abdomen. Methods: One hundred patients were divided into mild (32), moderately severe-severe (32) OSA and non-OSA (36), according to the results of the polysomnography. These patients were examined using anthropometric measurements and US of SAT and drug-induced sleep endoscopy. Results: Using SAT US and anthropometric parameters, oropharyngeal obstruction could be predicted in 64% and tongue-based obstruction in 72%. In predicting oropharyngeal obstruction, BMI, abdominal and hip circumferences, submental SAT and SAT above the second intercostal space on the left were identified as essential parameters. Furthermore, tongue-based obstruction was predicted mainly by height, SAT measured 2 cm above the umbilicus and submental SAT. The OSA prediction was successful in 97% using the parameters mentioned above. Moreover, other parameters, such as US-based SAT, with SAT measured 2 cm above the umbilicus and both-sided SAT above the second intercostal spaces as the most important ones. Discussion: Based on our results, several categories of OSA can be predicted using artificial intelligence with high precision by using SAT and anthropometric parameters.

Obstructive sleep apnea detection during wakefulness: a comprehensive methodological review

“… Some other studies have focused on the ability to use ultrasound or MRI imaging of the tongue for OSA prediction [ 32 , 34 ]. One research [ 34 ] showed the ability of OSA prediction using AI applied to ultrasound imaging of the UA and subcutaneous adipose tissues (SAT) in the regions of the neck, chest, and abdomen measurements [ 35 ]. The data was collected from 100 individuals, 36 without OSA and 64 with different OSA severity (32 mild, 32 moderately severe) based on their overnight PSG scores, while the DISE was used to determine the obstruction location and configuration.…”

“…MRI for detecting OSA results in 90% and LPW-based obstruction in 84% [ 33 ] Endoscopy 43 subjects with AHI ≥ 15 The collapsibility was significant only at the hypopharyngeal level (41.8% during wakefulness and 88.3% in DISE). 18.6% and 4.6% of patients showed laryngeal obstruction during awake and DISE examinations, respectively [ 35 ] Ultrasound 36 with AHI < 5, 32 with 5 ≤ AHI < 15 and 32 with AHI ≥ 15 OSA prediction using the ultrasound parameters achieved a sensitivity of 100% and a specificity of 91.7% [ 34 ] Ultrasound and MRI 36 with AHI < 5 and 64 with AHI ≥ 5 Using tongue parameters and anthropometric values, an ultrasound sensitivity of 94% and a specificity of 98% were achieved while MRI has 56% sensitivity and 92% specificity …”

Investigating the Role of Serum and Plasma IL-6, IL-8, IL-10, TNF-alpha, CRP, and S100B Concentrations in Obstructive Sleep Apnea Diagnosis

“…The AHI represents the total number of apnea and hypopnea events per hour of sleep as recorded during an overnight sleep study. The severity of OSA can be evaluated through the AHI, which categorizes the condition into three levels: mild (5 ≤ AHI < 15), moderate (15 ≤ AHI ˂ 30), and severe (AHI ≥ 30) [ 35 ]. Apneas are characterized by a minimum of 90% reduction in airflow for at least 10 s, while hypopneas involve a decrease in respiratory signals for at least 10 s accompanied by a minimum of 3% oxygen desaturation [ 35 ].…”

“…Laboratory tests offer a multifaceted advantage, providing a non-invasive, easily attainable, and economical approach to assessment, while also playing a pivotal role in diagnosing various medical conditions within routine clinical practice, with notable emphasis on screening procedures and accurate disease diagnostics. Diagnostic biomarkers, including specific molecules, genes, or other biological substances, are critical tools in modern medicine, aiding in the early detection, diagnosis, and management of diseases [ 35 ]. They offer objective, quantifiable information that assists clinicians in making informed decisions about patient care, enabling insights into underlying pathology, early disease identification, monitoring illness progression, and assessing treatment effectiveness.…”

A Machine Learning Prediction Model of Adult Obstructive Sleep Apnea Based on Systematically Evaluated Common Clinical Biochemical Indicators

“… 16–18 There are also many studies that utilize cephalometry, X-ray, computed tomography (CT), magnetic resonance imaging (MRI), ultrasound, and drug-induced sleep endoscopy to measure OSA-related data, including oral and maxillofacial anatomy measurements, the upper airway, respiratory muscles, subcutaneous adipose tissue (SAT), etc., to analyze the relationship between these data and the apnea-hypopnea index (AHI) and determine the upper airway collapsing, thus exploring their diagnostic efficacy for OSA. 19–21 In addition, 3D face features were further extracted in some studies to establish classification algorithms that facilitate the utilization of information regarding linear distances and angles. 22 Nevertheless, the application of these diagnostic methods in routine clinical settings is limited due to factors such as cost, human resources, and exposure to radiation.…”