Technology set to revolutionise lives of baby boomers
MELBOURNE: : Digital assistance is on the verge of becoming the new standard bearer of quality care.
Digital assistants such as Amazon’s Alexa could soon be rescuing people suffering cardiac arrest.
Researchers have created a prototype system, underpinned by artificial intelligence, that detects the characteristic gasping breaths of a person whose heart has just stopped beating.
The technology, underpinned by artificial intelligence, could be built into smart speaker devices such as Amazon’s Echo or Google Home.
Cardiac arrest victims often gasp for air, a symptom known as agonal breathing. Immediate cardiopulmonary resuscitation (CPR) can double their chances of survival. But one of the most common locations, outside of hospital, for a cardiac arrest is in the bedroom, where people are often alone.
The new system which could also be incorporated into a smartphone, detected agonal breathing events 97 per cent of the time from up to six meters away.
This kind of breathing happens when a patient experiences really low oxygen levels,” Dr Jacob Sunshine, of the University of Washington, one of the study’s authors, said
In a cardiac arrest the heart suddenly stops pumping blood, often because of a problem with electrical signals.
Shyam Gollakota, of the University of Washington, said: “A lot of people have smart speakers in their homes, and these devices have amazing capabilities that we can take advantage of.”
The system could be set to alert anyone nearby with CPR skills, or call the emergency services. It would “continuously and passively monitoring” the bedroom for telltale sounds, he added.
Sounds of agonal breathing were collected from real emergency calls made in recordings captured by bystanders in Seattle. Patients often fall unconscious, bystanders are asked to put the phone close to the patient’s mouth so that the dispatcher can determine whether CPR is needed. These calls were used to train a machine-learning system to recognise the sounds associated with cardiac arrest.
The algorithm incorrectly categorised another sound as agonal breathing just 0.14 per cent of the time.
Technology companies expect smart devices to revolutionise healthcare, with devices detecting diseases long before people themselves are aware.
A departure from the norm – such as a persistent sniffle – might prompt a digital home assistant to order suitable cold medicine online. Other researchers are looking at possible early markers for dementia such as subtle changes in vocabulary or a person getting lost more often than normal.
Dr. Sunshine said, “Cardiac arrests are a very common way for people to die, and right now many of them can go unwitnessed.”
