An international research team led by the Technion–Israel Institute of Technology has developed an innovative, AI-based software to detect obstructive sleep apnea (OSA), a condition in which people stop breathing for about 10 seconds or more while they are asleep.
The prevalence of this syndrome increases with age and affects more than one in five individuals in the general adult population — particularly males and those who are overweight.
OSA is characterized by halts in breathing during the night and lower oxygen levels in the blood. The syndrome causes fatigue and sleepiness during the day, which can lead to inefficiency and accidents while working, and in some cases, to traffic accidents. OSA also increases the risk of developing diabetes and cardiovascular disease.
“The model we developed is a reliable and effective tool for identifying sleep apnea in large populations,” said Dr. Joachim Behar, a member of the Technion’s Faculty of Biomedical Engineering who led the study. It could help mass screen for the condition, he said in a phone interview.
This model can in the longer term be used to develop a suitable mobile application, and eventually be part of a smart watch or bracelet that includes an oximeter to extract the necessary biomarkers and perform an accurate self-examination for OSA, he said.
The researchers’ findings were published in The Lancet Group’s open-access journal EClinicalMedicine. The team included researchers from Oxford University in the UK, Federal University of São Paolo, Emory University and Georgia Tech University in Atlanta, US.
“Sleep apnea can be treated effectively, but many sufferers remain undiagnosed,” said Behar.
The technology used to diagnose the syndrome in sleep labs, called polysomnography, records brain waves and oxygen level in the blood, as well as heart rate, breathing, and eye and leg movements during sleep.
Although polysomnography is effective in diagnosing the condition, it is not widely available because of its prohibitive costs. OSA diagnosis may also be carried out with home monitoring equipment, though this option is not without cost, nor is it easily accessible to the general population at risk. Less expensive diagnostic methods, based on questionnaires and upper-respiratory morphology, are not accurate enough, the researchers said.
The technology that Behar and his team developed is based on data and biomarkers obtained from 887 subjects from the general adult population in Sao Paulo, Brazil.
The data included information about a number of factors, including oxygen saturation levels of the patients during sleep, demographic information (such as age, height, and weight) and anthropometric information such as neck dimension.
After sifting through the information, the system was able to successfully identify all the clinical cases of medium or severe OSA, the researchers said.
Standardized sleep apnea diagnosis questionnaires, by comparison, missed more than 15% of severe cases, while the use of pulse oximetry — a noninvasive way to monitor a person’s oxygen saturation — only detected the severe cases but failed to identify some of the medium OSA cases, the researchers said.
The model the team developed is called OxyDOSA, and the researchers have made it available for further research.
Some companies, like Israel’s Itamar Medical, have already developed a medical device to monitor sleep apnea. The device measures the flow of blood in the arteries to determine how hard the heart is working during sleep. The technology, called PAT – Peripheral Arterial Tone – gauges arterial function and the speed and health of blood flow, and the device, called the WatchPAT, sets off an alarm when blood flow increases to a level that indicates that the heart is overworking as an individual sleeps, indicating the presence and degree of sleep apnea based on algorithms developed by the company.
The software developed by the Technion-led team would be complementary to such devices, said Behar.
Behar heads the Artificial Intelligence in Medicine Laboratory (AIMLab) in the Technion. The lab’s research focuses on the use of artificial intelligence in medicine.