A new AI model for diagnosing sleep apnea has been developed by a research team at Seoul National University’s Bundang Hospital.
The deep learning model analyzes cephalograms, focusing on the tongue and its surrounding structures, which are strongly associated with sleep apnea.
Based on a press release, the model was developed using head and neck X-ray image data from 5,591 SNUBH patients. It was then tested in a study, which found it to be very accurate in detecting sleep apnea.
WHY IS IT IMPORTANT
It is estimated that approximately one billion people aged 30 and over worldwide suffer from sleep apnea, and this number is not far from decreasing. Its prevalence and growth are linked to increased detection and other risk factors, such as obesity and craniofacial and upper respiratory abnormalities.
According to the SNUBH research team, there are limitations to the current screening tests available on the market for detecting sleep apnea. Some have low accuracy rates, while others may not be suitable for use in multi-person environments.
For this reason, they developed their AI model to further improve the early diagnosis and treatment of sleep apnea while being simple and inexpensive.
MARKET OVERVIEW
A Japanese research team is also using AI to study sleep disorders and identify digital biomarkers linked to them. Four H and Aculys Pharma embarked on this research with the goal of building a comprehensive sleep ecosystem to improve people’s quality of sleep.
Meanwhile, a mobile phone sleep apnea test called SleepCheckRx by Australian company ResApp received 510(k) clearance from the US FDA last year. The app detects apnea by analyzing recordings of breath sounds and snoring.
Also, the Singaporean smartwatch brand BUZUD recently added oxygen saturation measurement to its smartwatches, providing the ability to measure and track sleep patterns to identify sleep apnea.