Scientists at the University of Washington have developed a new artificial intelligence system that allows smart speakers, like the Amazon Echo and Google Home, to locate and measure both regular and irregular heartbeats.

The system has the smart speaker project inaudible sounds throughout the room. When the speaker's sound waves bounce around the room, they interact with and are transformed by other vibrations, including the subtle motion of the human chest.

Scientists designed their machine learning program -- described Tuesday in the journal Communications Biology -- to recognize the acoustic signatures of both regular and irregular heartbeats.

When researchers tested the system on both healthy volunteers and hospitalized cardiac patients, the heartbeats identified and measured by the smart speakers closely matched those measured by commercial heartbeat monitors.

"Regular heartbeats are easy enough to detect even if the signal is small, because you can look for a periodic pattern in the data," co-senior author Shyam Gollakota said in a press release.

"But irregular heartbeats are really challenging because there is no such pattern. I wasn't sure that it would be possible to detect them, so I was pleasantly surprised that our algorithms could identify irregular heartbeats during tests with cardiac patients," said Gollakota, an associate professor of computer science and engineering at Washington.

Smart watches and other wearable devices are able to monitor a person's heart rate, but cardiologists are often more interested in the rhythm of a person's heart beat.

A regular heart rhythm features an even spacing of beats, while an irregular rhythm might features several seconds of an elevated heart rate followed by a few seconds of a slower heart rate.

"Heart rhythm disorders are actually more common than some other well-known heart conditions. Cardiac arrhythmias can cause major morbidities such as strokes, but can be highly unpredictable in occurrence, and thus difficult to diagnose," said co-senior author Dr. Arun Sridhar.

"Availability of a low-cost test that can be performed frequently and at the convenience of home can be a game-changer for certain patients in terms of early diagnosis and management," said Sridhar, an assistant professor of cardiology at the University of Washington School of Medicine.

To measure a person's heart rhythm, a device must precisely detect each individual beat. Quite a challenge for non-contact monitors, as the movement of a person's chest is several orders of magnitude larger than the movements of a person's heart.

There are other challenges, too.

"The breathing signal is not regular so it's hard to simply filter it out," said lead author Anran Wang, a doctoral student in the Allen School. "Using the fact that smart speakers have multiple microphones, we designed a new beam-forming algorithm to help the speakers find heartbeats."

The system combines all of a speaker's multiple microphones to pick up the signal of a beating chest, and is trained on the job -- learning the room, rather than being trained before deployment.

"This is similar to how Alexa can always find my voice even if I'm playing a video or if there are multiple people talking in the room," Gollakota said. "When I say, 'Hey, Alexa,' the microphones are working together to find me in the room and listen to what I say next. That's basically what's happening here but with the heartbeat."

The initial signals captured by the program don't look all that much like a heart beat patterns, but researchers designed another algorithm to interpret the signal and translate it into a heart beat pattern featuring inter-beat intervals.

"With this method, we are not getting the electric signal of the heart contracting. Instead we're seeing the vibrations on the skin when the heart beats," Wang said.

In tests, the smart speaker system measured the heartbeats of health participants to within 28 milliseconds of a standard monitor and within 30 milliseconds for patients hospitalized for heart conditions.

For now, a person must sit within a couple feet of the speaker to measure their heart rhythm, but scientists hope that the program can eventually be trained to measure a person's heartbeat as they sleep.

The researchers say the type of device they're designing could allow doctors to monitor patients on an extended basis and define patterns specific to each patient.

"For example, we can figure out when arrhythmias are happening for each specific patient and then develop corresponding care plans that are tailored for when the patients actually need them," Sridhar said.

"This is the future of cardiology. And the beauty of using these kinds of devices is that they are already in people's homes," Sridhar said.

Related Links
Space Medicine Technology and Systems

Tweet

Thanks for being here; We need your help. The Space Media Network continues to grow but revenues have never been harder to maintain. With the rise of Ad Blockers, and Facebook - our traditional revenue sources via quality network advertising continues to decline. And unlike so many other news sites, we don't have a paywall - with those annoying usernames and passwords. Our news coverage takes time and effort to publish 365 days a year. If you find our news sites informative and useful then please consider becoming a regular supporter or for now make a one off contribution.
SpaceMediaNetwork Contributor $5 Billed Once credit card or paypal		SpaceMediaNetwork Monthly Supporter $5 Billed Monthly paypal only

Preventing injuries and improving recovery with micro-Doppler radars
University Park PA (SPX) Mar 09, 2021
Micro-Doppler radars could soon be used in clinical settings to predict injury risk and track recovery progress, according to Penn State researchers. Being able to view subtle differences in human movement would allow health care workers to more accurately identify individuals who may be at risk for injury and to track progress precisely while individuals are recovering from an injury. In an effort to find an accurate, reliable and cost-effective way to measure these subtleties in human movement, ... read more