People with sudden cardiac arrest will suddenly lose their reaction, either stop breathing or breathless. This requires the presence of a bystander to perform CPR immediately, which can double or triple the patient's chance of survival. But many cardiac arrests occur in their sleep and people can't detect them.
Research data show that about half of patients with cardiac arrest have non-directional breathing, while patients with non-directional breathing tend to have better survival. In general, non-directional breathing occurs when the patient's respiratory oxygen level is very low. This is a wheezing sound on the throat, and its uniqueness makes it a good audio biomarker that can be used to identify a person with a cardiac arrest.
Researchers at the University of Washington have developed a new tool to monitor their heartbeats while people are sleeping without touching them. It detects the detection of non-directional breathing within 6 meters.
Shyam Gollakota, an associate professor at the School of Computer Science and Engineering at the University of Washington, said: "We envision a non-contact system that continuously and passively monitors non-contact breathing events in the bedroom and reminds anyone nearby to do CPR. If there is no response, the device will automatically dial 911."
Since patients with cardiac arrest are often unconscious, bystanders record the sound of non-directional breathing by placing the phone on the patient's mouth so that the dispatcher can determine if the patient needs immediate CPR.
The team used different smart devices (Amazon Alexa, iPhone 5s, and Samsung Galaxy s4) to capture the sounds and play them at different distances to simulate what it would sound like if the patient was in a different position in the bedroom.
In addition, they added different disturbing sounds, such as the sound of cats and dogs, the sound of car horns, the sound of air conditioners, and the sounds that are usually heard at home.
The team used machine learning to create a tool that detected non-directional breathing in 97% of cases when the smart device was placed 6 meters away from the speaker that produced the sound. In addition, the team tested the algorithm to ensure that it does not classify different types of breathing, such as snoring, into zoneless breathing.
Gollakota said: "This technology has been proven to be a good application in the Seattle metropolitan area. But we need to get more 911 alarm calls related to cardiac arrest so that we can further improve the accuracy of the algorithm and ensure It can be promoted on a larger scale."
In addition, researchers plan to commercialize the technology. Part of the reason why this technology is so compelling is that it helps us discover more patients in time and get them treated.
Reference materials:
[1] 'Alexa, monitor my heart': Researchers develop first contactless cardiac arrest AI system for smart speakers
Source: Bio-Exploration
Pod Pepper,Natural Spice Chilies Pod Pepper,Dried Red Pepper Pod Pepper,Dehydrated Pod Pepper
Guizhou Guisanhong Food Co., Ltd , https://www.guisanhong.com