New tech promises better way to diagnose sleep problems

Lack of sleep is the cause of not only grumpy attitudes and a deficit of patience. It’s been connected to maladies and diseases of all kinds, from heart attacks to diabetes to obesity, depression to insanity, and even death. Current technology to determine the causes of insomnia involve a slew of sensors, machinery, and lots of wires.

Much easier, researchers at Ben-Gurion University say, is to use a new technique they invented that dispenses with polysomnography (PSG) equipment and other expensive and complicated machinery to diagnose insomnia. Instead, a small device with a microphone – perhaps, in the future, even a smartphone – could, using the BGU-developed breath sound analysis (BSA) system – help determine the causes of lack of sleep.

One of the main goals of sleep medicine today is to improve early diagnosis and treatment of the “flood” of subjects presenting with sleep disorders, says Prof. Yaniv Zigel Ph.D., head of the Biomedical Signal Processing Research Lab in BGU’s Department of Biomedical Engineering.

“We’ve developed a non-contact ‘breathing sound analysis’ algorithm that provides a reliable estimation of whole-night sleep evaluation for detection of sleep quality, snoring severity and Obstructive Sleep Apnea (OSA),” he said. :It has the potential to reduce the cost and management of sleep disorders compared to PSG, the current standard of treatment, and could be used at home.”

The Biomedical Signal Processing Research Laboratory was established in 2007 by Zigel. The lab’s team are experts in physiological signal processing and pattern recognition. The Unit for the Study and Diagnosis of Sleep Disorders was established in 1994 by Prof. Ariel Tarasiuk. The unit’s team of experts evaluate sleep disorders in children and adults and operates in conjunction with specialists in respiratory diseases, neurology, ENT, and gastrointestinal diseases.

When a patient can’t sleep, or suffers from OSA, where breathing is interrupted during sleep, doctors will often recommend a polysomnogram, which entails attaching a patient to various sensors and machines that measure breathing, heart rate, level of snoring, blood pressure, and other data. The tests usually take place in a sleep center, with the patient attached to various wires, sensors, microphones and machines that aim to shed light on their sleep disorder.

While the motivation for a patient to go through the tests is high, at least initially, the routine can get tiring after a week, which doctors may need to make a proper diagnosis. In addition, testing in a sleep center may not take into account environmental factors in the home, so several rounds of tests may be necessary in order to draw conclusions. The tests, of course, are expensive to run, as they require the deployment of expensive equipment, monitoring by staff for an entire overnight shift, and analysis and evaluation. “This procedure is time-consuming, tedious and costly due to complexity and the need for technical expertise; the market is begging for a better solution,” says Eliran Dafna who conducted this study as part of his Ph.D. research.

Far simpler, easier, and cheaper is the new solution offered by Ben-Gurion researchers, said Zigel, based on a study that compared BSA with PSG for sleep disorder analysis. The researchers measured whole-night breathing sounds from 150 patients using both ambient microphones to test the BSA method; at the same time, PSG equipment was used to check the patients’ sleep quality. The tests took place in a sleep lab. Eighty of the patients were given the tests, while the other 70 were a control group, used to develop sleep quality parameters that could later be compared to the results of the PSG/BSA tests.

The tests clearly showed that BSA was at least as good an indicator of sleep parameter measurement as PSG. Measuring 150,000 individual time segments (epochs), the BSA epoch-by-epoch accuracy rate 83.3 percent, compared with 92.2 percent sensitivity for the PSG indicators, meaning that the simple use of a microphone and an analysis app provided results that were almost as accurate as a room full of expensive equipment.

And that’s just with BSA technology in its infancy, said Ariel Tarasiuk of BGU’s Department of Physiology and head of the Sleep-Wake Disorders Unit, at Soroka University Medical Center. “The results showed that sleep/wake activity and sleep quality parameters can be reliably estimated solely using breathing sound analysis. This study highlights the potential of this innovative approach to measure sleep in research and clinical circumstances.”