Alexa will be able to identify a cardiac arrest listening to the breath of the person

If you are unlucky and you have a heart stops, the chances are small. Of the 400,000 people who face it every year in a particular country, survival of less than 6%. This is the main cause of natural death. However, the probability of survival would be much higher if to provide immediate help: immediate CPR can double or triple the chances. The new tool uses a microphone of the smart column or smartphone for timely detection signals can increase survival rates.

How to save a person in cardiac arrest?

The system, developed by scientists at the University of Washington that uses machine learning to determine the so-called gasping-breathing (also known as agonal breathing), which manifests itself in humans, which is not enough air. This is an early warning sign, which appears in half of all cases of cardiac arrest.

Scientists have trained the system using the recording agonal breathing received when calling in emergency care in king County, Washington. They used 729 calls, which gave a total of 82 hours of recordings. They then taught to other sounds can also be heard in the room, like snoring or sleepy mutterings, to weed out any false positives.

We used two different sets of records: the sounds of sleep collected by 35 volunteers, and the sounds of the 12 patients who participated in the sleep study since he was suffering from snoring and sleep apnea. The last record produced sounds similar to agonal breathing, helping to improve the accuracy of the instrument.

“When we tested it on their system, we found that the level of false positive signals in the group of volunteers was 0.2%, and in the sleep study, and 0.1%,” says Justin Chan, who led the study.

The system was able to correctly identify agonal breathing in 97% of cases at a distance of 6 metres.

While the tool is still at the stage of proof of concept, so before its release to the General public for many years, although they plan to eventually commercialize it. Much has yet to be tested. Most likely, the system will call an ambulance automatically, but will warn people about it, so he could cancel the call.

How many lives will this save the system? Tell us in our chat in Telegram.

Leave a Reply

Your email address will not be published. Required fields are marked *