UH Researchers Diagnose Sleep Apnea Using Noncontact Method


(Video and interviews with Ioannis Pavlidis are available upon request.)

Researchers at the University of Houston (UH) and The University of Texas Health Science Center at Houston (UTHSC at Houston) have tested a new method of detecting sleep apnea and hypopnea from a distance, using thermal infrared imaging (TIRI). The method is capable of extracting breathing waveforms and monitoring airflow. This study is the first of its kind to diagnose sleep apnea using noncontact technology. The findings are published in the November issue of the journal SLEEP.

"We are now able to measure breathing function through thermal imaging. This opens the way for eliminating thermistor probes and, thus, freeing the lower part of the patient's face in the sleep studies- a major relief," said co-investigator Ioannis Pavlidis, Eckhard-Pfeiffer Professor, UH department of computer science.

Sleep apnea is a common disorder that causes a person's breathing to pause during sleep, multiple times within an hour.  It affects 9 percent of women and 24 percent of men. An immediate consequence of sleep apnea is sleepiness. Sleepiness is the leading cause of fatal car accidents and is believed to have played a role in disasters such as the Chernobyl and Three Mile Island tragedies. The long-term consequences of sleep apnea include hypertension, heart disease, stroke and diabetes. Diagnosing the condition requires a sleep study, or polysomnography.

"During a sleep study a subject has an average of more than 20 sensors attached to the head and body. It's a very complex procedure where many physiological parameters are simultaneously monitored to help in the diagnosis of sleep disorders. However, these sensors can disturb sleep and contribute to the patient's anxiety," said fellow investigator Jayasimha N. Murthy, M.D., assistant professor of medicine from the Division of Pulmonary Critical Care Sleep Medicine at UTHSC at Houston. "With technologies such as thermal imaging and computational physiology, we hope to ‘unwire' ‘wired subjects' during sleep studies."

 "It's not as simple as paying a visit to the doctor in the morning for an hour and walking away with a prescription. You have to undergo overnight monitoring in a sleep lab. The subject is wired and sleeps there. Sometimes, the subject has to spend more than one night," Pavlidis said.

Pavlidis, Murthy, Ph.D. student Jin Fei and collaborators collected data on 27 subjects at the Memorial Hermann Hospital Sleep Disorders Center, 14 without a history of sleep disordered breathing and 13 patients with a history of sleep apnea. The research team used a thermal infrared camera to capture thermal changes in the air going in the patient's nostrils brought about by inspiring and expiring air.

As the sensing instrument was about eight feet away from the patient with no physical probe attached on the nostrils, the measurement was done on a virtual probe delineated in the imagery. This virtual probe was tracking the patient's movements using computational algorithms- a sort of virtual tethering. The method proved to be as accurate as the traditional methods, albeit contact free. Equally important, the new method can provide a wealth of information not accessible before.

"In contrast to the traditional one-dimensional methods, this new method is an imaging one and thus, multi-dimensional" said Pavlidis. "We now can see how airflow is distributed locally throughout the extent of the nostril. We get not a single, but multiple values for each nostril at every point in time and this makes a lot of difference when it comes to appreciating subtle pathology."

While using TIRI, the investigators did not eliminate all of the contact sensors required during a sleep study. They did keep the nose and mouth area free of probes, which could make sleep studies more comfortable. Murthy and Pavlidis believe, with more clinical trials, this scientific breakthrough could change the way sleep apnea is diagnosed in sleep labs.

"This is the first step in the development of this technology in airflow monitoring," said Murthy. "I can foresee future applications for monitoring airflow in newborns and children, as well as situations such as respiratory isolation for contagious disease or traumatic injuries or the face where contact-free methods are the only option."



This research received support from the National Science Foundation under grant #IIS-0414754 titled "Interacting with Human Physiology" and by the National Institutes of Health Clinical and Translational Sciences Award #UL1RR024148.