Email Print Share

"Heartspeakers" -- The Discovery Files

The Discovery Files
Audio Play Audio
The Discovery Files podcast is available through iTunes or you can add the RSS feed to your podcast receiver. You can also access the series via AudioNow® by calling 641-552-8180 on any telephone.

Researchers at the University of Washington have developed a new tool to monitor people for cardiac arrest while they're asleep without touching them. The tool has the ability to scan sound recordings for signs of agonal breathing using a machine learning algorithm, which potentially could be installed in smartphones or smart speakers like Amazon Alexa. Agonal breathing, a sign of cardiac arrest, is when people suddenly become unresponsive and either stop breathing or gasp for air.

Credit: NSF/Karson Productions

Audio Transcript:


I'm Bob Karson with the Discovery Files, from the National Science Foundation.

Smart speakers perform many life-easing tasks. Now, from researchers at the University of Washington what could be a life-saving task: monitoring people for cardiac arrest while they sleep. The team has created an algorithm that allows smart speakers to ID signs of "agonal" breathing.

During cardiac arrest, when people's oxygen levels are very low, they may switch to a pattern known as agonal breathing. (Sound effect: agonal breathing sounds) Widely spaced, forced gutteral gasping gulps for air. A good indicator of cardiac arrest -- as-long-as there's a bystander to hear it -- human or smart speaker.

The UW team taught their program what to listen for by exposing it to recordings of agonal breathing collected from actual 9-1-1 calls. (Sound effect: 911 dispatcher) Sound clips that trained the algorithm to correctly identify it 97 percent of the time from up to 20 feet away.

The researchers envision their algorithm running locally either on a smart speaker's processor -- no need to send anything to the cloud -- or on a smartphone app. It knows the difference between snoring or other heavy breathing and will alert a close family member or call 9-1-1 for help.

(Sound effect: heartbeat) ôSmart Speaker? This is more like, "Heart Speaker" technology.

"The discovery files" covers projects funded by the government's National Science Foundation. Federally sponsored research -- brought to you, by you! Learn more at or on our podcast.

General Restrictions:
Images and other media in the National Science Foundation Multimedia Gallery are available for use in print and electronic material by NSF employees, members of the media, university staff, teachers and the general public. All media in the gallery are intended for personal, educational and nonprofit/non-commercial use only.

Images credited to the National Science Foundation, a federal agency, are in the public domain. The images were created by employees of the United States Government as part of their official duties or prepared by contractors as "works for hire" for NSF. You may freely use NSF-credited images and, at your discretion, credit NSF with a "Courtesy: National Science Foundation" notation. Additional information about general usage can be found in Conditions.

Also Available:
Download the high-resolution JPG version of the image. (66.6 KB)

Use your mouse to right-click (Mac users may need to Ctrl-click) the link above and choose the option that will save the file or target to your computer.

MP3 icon
NSF podcasts are in mp3 format for easy download to desktop and laptops, as well as mobile devices capable of playing them.