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.
