Technology 4 min read

Researchers Develop First Contactless Cardiac Arrest AI System

In an effort to provide immediate aid to heart attack victims, researchers at the University of Washington developed the world's first contactless cardiac arrest AI system. The new tech was designed to detect signs of a heart attack and call for help when necessary.

Image courtesy of Shutterstock

Image courtesy of Shutterstock

Researchers have developed the world’s first contactless cardiac arrest AI system for smartphones and smart speakers.

Sudden cardiac arrest is the stopping of the heart due to a disruption on its electrical impulses. As a result, the brain and vital organs receive less oxygenated blood, which causes the victim to lose consciousness.

As the name implies, the condition is sudden. In other words, it could occur anywhere, and at any time. Most of the time, it does.

According to recent statistics, 356,461 people in the United States experience cardiac arrest outside the hospital. Furthermore, 25 percent of the individuals that suffered an out-of-hospital cardiac arrest had no previous symptoms.

While immediate CPR can triple the chance of survival, it requires the presence of a bystander. Unfortunately, that’s not always the case.

Cardiac arrests go unwitnessed 51 percent of the time.

A recent study shows that one most common locations for an out-of-hospital cardiac arrest are at home. Most of the time, it occurs in the patient’s bedroom, and no one would be around to provide care.

But there’s a solution. To address this issue, researchers at the University of Washington developed a new tool to monitor people for heart attack.

Now, here’s the exciting part. The algorithm acts as a contactless cardiac arrest AI system. In other words, the tool does the monitoring without touching the patients.

How does it work, you wonder?

Hey Alexa, Am I Having a Heart Attack?

Using your smartphone or smart speaker – like Amazon Alexa or Google Home – not only will the tool monitor agonal breathing, but it’ll also call for help when necessary.

The researchers developed a proof-of-concept tool using real agonal breathing instances from 911 calls. According to the paper in NPJ Digital medicine, the device was able to detect agonal breathing events 97 percent of the time from about 6 meters away.

In a statement, associate professor in the UW’s Paul G. Allen School of Computer Science & Engineering and co-author of the study, Shyam Gollakota, said:

“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 to provide CPR. And then if there’s no response, the device can automatically call 911.”

Detecting Agonal Breathing Using Contactless Cardiac Arrest AI System

According to 911 data, about 50 percent of people who have cardiac arrest experience agonal breathing first, which increases survival chances.

Assistant professor of anesthesiology and pain medicine at the UW School of Medicine and co-author, Jacob Sunshine said:

“This kind of breathing happens when a patient experiences low oxygen levels. 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.”

The researchers collected about 236 recordings of agonal breathing from real 911 calls -from Amazon Alexa, iPhone 5s, Samsung Galaxy S4, and other devices. Using various machine learning techniques, they boosted the dataset to 7,316 positive clips.

The combination of the datasets and machine learning enabled the researchers to create a tool that could detect agonal breathing 97 percent of the time and from a maximum distance of 6 meters.

Next, the researchers had to reduce the tool’s false positives. This involves ensuring that the algorithm can tell the difference between snoring and agonal breathing.

The team believes that the algorithm could function as a skill for Alexa or an app on a smartphone. That way, it’ll run passively in the background while people sleep or go around their daily activities. Sunshine noted:

“Cardiac arrests are a very common way for people to die, and right now many of them can go unwitnessed. Part of what makes this technology so compelling is that it could help us catch more patients in time for them to be treated.”

After perfecting the technology, the researchers intend to commercialize it using a University of Washington spinout, Sound of Life Sciences, Inc.

Read More: Researchers Invent High-Tech Toilet Seat That Can Detect Heart Failure

First AI Web Content Optimization Platform Just for Writers

Found this article interesting?

Let Sumbo Bello know how much you appreciate this article by clicking the heart icon and by sharing this article on social media.


Profile Image

Sumbo Bello

Sumbo Bello is a creative writer who enjoys creating data-driven content for news sites. In his spare time, he plays basketball and listens to Coldplay.

Comments (0)
Least Recent least recent
You
share Scroll to top

Link Copied Successfully

Sign in

Sign in to access your personalized homepage, follow authors and topics you love, and clap for stories that matter to you.

Sign in with Google Sign in with Facebook

By using our site you agree to our privacy policy.