Researchers at the University of Washington (UW) in the US, stated that scientists have developed a new artificial intelligence (AI) system to monitor people for cardiac arrest while they are asleep without touching them. People who are experiencing cardiac arrest will suddenly become unresponsive and either stop breathing or gasp for air, a sign known as agonal breathing.

A new skill for a smart speaker -- like Google Home and Amazon Alexa -- or smartphone which lets the device detect the gasping sound of agonal breathing and call for help.

Immediate Cardiopulmonary resuscitation (CPR) can double or triple someones chance of survival, but requires a bystander to be present. CPR is an emergency procedure which combines chest compressions mostly with artificial ventilation in an effort to manually preserve intact brain function.

Current research have suggested that one of the most common locations for an out-of-hospital cardiac arrest is in a patients bedroom, where no one is around or awake to respond and provide care.

This new proof-of-concept tool, developed using real agonal breathing instances captured from 911 calls, can detect agonal breathing events 97 per cent of the time from up to six meters away.

Shyam Gollakota, an associate professor at UW said that many people have smart speakers in their homes, and these devices have remarkable capabilities of taking advantage of. He also said they 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 if theres no response, the device can automatically call 911.

Agonal breathing is present in almost 50 per cent of people who experience cardiac arrests, and patients who take agonal breaths have a better chance of surviving. The researchers had gathered sounds of agonal breathing from real 911 calls to Seattles Emergency Medical Services.

Cardiac arrest patients are often unconscious; hence bystanders recorded the agonal breathing sounds by putting their phones up to the patients mouth so that the dispatcher could determine whether the patient needed immediate CPR. The researchers had collected 162 calls between 2009 and 2017 and extracted 2.5 seconds of audio at the start of each agonal breath to come up with a total of 236 clips.

They also captured the recordings on different smart devices and used various machine learning techniques to boost the dataset to 7,316 positive clips. These clips contained typical sounds which people make during sleep, such as snoring or obstructive sleep apnea.

From these datasets, the team used machine learning to create a tool which could detect agonal breathing 97 per cent of the time when the smart device was placed up to six metres away from a speaker generating the sounds. The team then tested the algorithm to make sure that it wouldnt accidentally classify a different type of breathing, like snoring, as agonal breathing.

The team envisions that this algorithm could function like an app or a skill for Alexa which runs passively on a smart speaker or smartphone while people sleep.