The Predictive Role of the Upper-Airway Adipose Tissue in the Pathogenesis of Obstructive Sleep Apnoea

Abstract

This study aimed to analyse the thickness of the adipose tissue (AT) around the upper airways with anthropometric parameters in the prediction and pathogenesis of OSA and obstruction of the upper airways using artificial intelligence. One hundred patients were enrolled in this prospective investigation, who were divided into control (non-OSA) and mild, moderately severe, and severe OSA according to polysomnography. All participants underwent drug-induced sleep endoscopy, anthropometric measurements, and neck MRI. The statistical analyses were based on artificial intelligence. The midsagittal SAT, the parapharyngeal fat, and the midsagittal tongue fat were significantly correlated with BMI; however, no correlation with AHI was observed. Upper-airway obstruction was correctly categorised in 80% in the case of the soft palate, including parapharyngeal AT, sex, and neck circumference parameters. Oropharyngeal obstruction was correctly predicted in 77% using BMI, parapharyngeal AT, and abdominal circumferences, while tongue-based obstruction was correctly predicted in 79% using BMI. OSA could be predicted with 99% precision using anthropometric parameters and AT values from the MRI. Age, neck circumference, midsagittal and parapharyngeal tongue fat values, and BMI were the most vital parameters in the prediction. Basic anthropometric parameters and AT values based on MRI are helpful in predicting OSA and obstruction location using artificial intelligence.

Obstructive Sleep Apnea Syndrome and Obesity Indicators, Circulating Blood Lipid Levels, and Adipokines Levels: A Bidirectional Two-Sample Mendelian Randomization Study

“…This study corroborates the association between an increased risk of NC enlargement and OSAS, thereby aligning with the research conducted by Altan Onat et al and Viktória Molnár et al 15,18 Altan Onat et al undertook a comprehensive observational study involving 25 patients with severe OSAS (Apnea-Hypopnea Index [AHI] ≥ 30 events per hour) and 19 with non-severe OSAS (AHI < 30 events per hour). Their findings indicated a positive correlation between increased NC and the severity of OSAS.…”

“…15 Similarly, Viktória Molnár et al conducted an analysis utilizing magnetic resonance imaging (MRI) to examine the adipose tissue parameters of the upper airways in 36 non-OSA control subjects, 32 patients with mild OSAS, and 32 with moderately-severe OSAS. 18 By applying artificial intelligence techniques to these MRI data, they identified age, percentage of tongue fat, and NC as crucial predictors of OSAS. Their results demonstrated that an increase in NC was positively correlated with OSAS severity and served as an independent predictor of severe OSAS.…”

Development and Validation of a Nomogram for Predicting Obstructive Sleep Apnea Severity in Children

“…Their investigation found that anthropometric measurements and MRI AT values both reliably predicted OSA; the most significant predictive criteria were body mass index, age, neck circumference, tongue midline, and parapharyngeal fat levels. 27 The above studies demonstrate how most contemporary studies on children’s OSA have extensively depended on statistical analysis of clinical examination or questionnaire data, regardless of the data or research methodology used. Due to the paucity of available data on OSA, it is difficult to accurately determine the severity of the disease and accurately depict the patient’s true clinical state.…”

Achieving Better Understanding of Obstructive Sleep Apnea Treatment Effects on Cardiovascular Disease Outcomes through Machine Learning Approaches: A Narrative Review

“…A number of groups have demonstrated the use of the ML-based analysis of MRI to automatically segment upper-airway structures, including the pharynx, tongue, and soft palate, that may facilitate large-scale epidemiological analyses in OSA patients in the future [ 80 , 81 , 82 ]. Molnar et al [ 83 ] used an AI analysis based on pharyngeal adipose tissue thickness derived from MRI, sex, and neck and waist circumference to separate patients with airway obstruction from those without. In a novel approach to airway measures, ML-supported computational fluid dynamics analysis has been used to predict OSA-related airflows [ 84 ].…”