- A group of scientists is developing AI technology that could be used on smartphones and smart speakers, such as Amazon‘s Alexa device, to detect whether someone is having a heart attack.
- The technology would listen out for the unique sounds that people make when suffering from a cardiac arrest and alert the emergency services to send help.
- The testing is already underway but the scientists say that the algorithm needs more work to ensure that the emergency services are not unnecessarily alerted.
- Visit Business Insider’s home page for more stories.
Researchers at the University of Washington are developing new AI technology that could be used on smartphones and smart speakers to detect whether someone is having a heart attack by listening out for unique sounds, Press Association reported on Wednesday.
People suffering from a cardiac arrest initially struggle with irregular gasps of breath, which is known as agonal breathing, Press Association wrote.
“This kind of breathing happens when a patient experiences really low oxygen levels,” Dr Jacob Sunshine, assistant professor of anesthesiology and pain medicine at the University of Washington School of Medicine said.
“It’s sort of a guttural gasping noise, and its uniqueness makes it a good audio biomarker to use to identify if someone is experiencing a cardiac arrest,” he said.
The devices will be trained to detect this specific sound and contact the emergency services to send someone to help.
Testing is currently being done with real-life agonal breathing recordings from emergency calls to Seattle’s Emergency Medical Services. These sounds are played back with added background noise and from different distances to make sure that the technology can pick out the breathing amongst other sounds.
So far, it has reportedly been able to detect the agonal breathing correctly 97% of the time. The researchers say that the algorithm needs more work to prevent any unnecessary calls to emergency services.
“We don’t want to alert either emergency services or loved ones unnecessarily, so it’s important that we reduce our false positive rate,” Justin Chan, a Ph.D. student at the University of Washington said.