Artificial intelligence can detect Covid-19 with 80% accuracy

Hyperaxion May 11, 2020

Using mathematical models, American and British scientists have developed technology capable of indicating, without testing, whether people are infected or not.

Researchers at King’s College London, UK, Massachusetts General Hospital in the United States, and health science company ZOE have developed artificial intelligence (AI) technology that can predict whether or not someone has Covid-19. The discovery was shared on Monday (11) in an article published in the journal Nature Medicine.

Artificial intelligence can detect Covid-19 with 80% accuracy
(Credit: Wikimedia Commons).

The AI compares people’s symptoms with data from the Covid Symptom Study app, which gathers symptoms presented by those who tested positive for Sars-CoV-2. More than 3.3 million people worldwide have downloaded the app and are using it to report their health status on a daily basis, whether they feel good or have symptoms such as persistent cough, fever, fatigue, and loss of taste or smell.

The team investigated which symptoms of Covid-19 were most likely to be associated with a positive diagnosis for the infection. They then created a mathematical model that predicts with almost 80% accuracy whether an individual is infected with the new coronavirus or not.

The technology takes into account age, sex, and a combination of four main symptoms: loss of taste or smell, severe or persistent cough, fatigue, and loss of appetite. The model is still in the testing phase, but the researchers believe that combining AI with widespread adoption of the application will help prevent Covid-19.

“Our results suggest that loss of taste or smell is a key early warning sign of COVID-19 infection and should be included in routine screening for the disease,” said Tim Spector, one of the project’s developers, in a statement. “We strongly urge governments and health authorities everywhere to make this information more widely known, and advise anyone experiencing sudden loss of smell or taste to assume that they are infected and follow local self-isolation guidelines.”

Comments

Subscribe
Notify of
guest
0 Comments
Inline Feedbacks
View all comments