Coronavirus cases can be detected with the sound of a cough



[ad_1]

US scientists have developed a new model to detect new types of coronavirus cases (Kovid-19) affecting the whole world. In a statement released by experts from the Massachusetts Institute of Technology (MIT), he said that people who don’t show symptoms are less likely to get tested because they don’t show obvious physical symptoms of the coronavirus, so they can spread the infection to others without knowing it. .

THE HUMAN EAR DOES NOT DISTRIBUTE

Working on this problem, MIT experts found that asymptomatic people have different cough patterns than healthy individuals. He found that this difference is indistinguishable from the human ear but detected by artificial intelligence.

ASYMPTOMATIC PATIENTS DETERMINED WITH A RATE OF 100 PERCENTAGE

Experts trained the AI ​​model on tens of thousands of cough sound and word sound samples sent voluntarily by individuals. After this training, when the AI ​​model was fed new cough records, it correctly identified 98.5% of the people confirmed to be Kovid-19 and 100% of the asymptomatic Kovid-19 patients.

WILL BE USED EVERYWHERE IF APPROVED

If the artificial intelligence model developed by MIT is approved by the FDA, asymptomatic people can use this model as a free and useful pre-screening tool.

Every day and every hour, the user will be able to find out instantly and quickly if a coronavirus is present by coughing into the application on their phone or into the device to put at the entrance of a business.

.

[ad_2]
Source link