Heart disease and heart-related problems are the major cause of death around the world. A huge contributory factor is that cardiac arrests often happen at night, during sleep, to people who live alone. In short, they often go “unwitnessed.”
So, what if there were an un-invasive technological solution that could be set up to diagnose heart trouble and advise loved ones or medical professionals in the case of an emergency?
That was the problem that researchers at the University of Washington—particularly Shyam Gollakota, associate professor in the UW’s Paul G. Allen School of Computer Science & Engineering—decided to address. It’s long been known that people experiencing a heart attack either struggle to breathe or stop breathing altogether, and the immediate delivery of CPR can “double or triple someone’s chance of survival.”
So, Gollakota and his team have developed a tool to detect the laboured, guttural-style breathing unique to heart failure. They’re confident that smartphones or smart speakers—technology that is always listening, in case it is called into use with an ‘Alexa’ or ‘Hey Siri’—could be converted into a “cardiac monitoring system” that sits near someone’s bed and analyses their breathing.
Gollakota and the team hope that the technology could become an app or as an inbuilt skill for speakers like Alexa; Sound Life Sciences plans on commercialising the technology.
“A lot of people have smart speakers in their homes, and these devices have amazing capabilities that we can take advantage of,” said Gollakota. “We envision a contactless system that works by continuously and passively monitoring the bedroom for an ‘agonal breathing event’, and alerts anyone nearby to come provide CPR. And then if there’s no response, the device can automatically call 911.”
The technology trained by studying calls made to the emergency services in recent years, testing the ability to assess breathing even with the interference of normal domestic sounds, such as pets, cars or the hum of air conditioning. They’ve found that the technology will work at a distance of up to six metres and is also smart enough to distinguish between normal, irregular breathing, and dangerous tendencies.