AI-Assisted Tool Has 90 Percent Chance of Figuring Out Whether Covid Will Kill You


SARS-CoV-2, the virus that causes Covid-19, has plagued the planet for over a year now, wreaking havoc on the world’s health care systems, plunging economies into crises, and killing an estimated 2.33 million people.

Researchers from the University of Copenhagen have developed a piece of artificial intelligence-enhanced software they believe can almost certainly predict the chances of a person dying from the new coronavirus after being infected.

The scientists, whose research appeared in Scientific Reports, a peer-reviewed journal published by Nature, say their program, which calculates the chances of a fatal Covid-19 outcome based on a range of patient data, has a 90 percent accuracy rate.

Researchers used data from Denmark’s Capital Region, which includes Copenhagen, as well as Region Zealand, situated to its south, collecting information from 3,944 patients with a confirmed Covid-19 diagnosis. The program was then trained to find patterns between patients’ prior maladies and their reaction to the coronavirus infection. Scientists processed the data using the Computerome, the University of Copenhagen supercomputer for life sciences.

Along with the 90 percent accuracy in determining potentially fatal outcomes, the program is said to be 80 percent accurate in finding out whether a patient will need access to a respirator.

“Our results demonstrate, unsurprisingly, that age and BMI are the most decisive parameters for how severely a person will be affected by COVID-19. But the likelihood of dying or ending up on a respirator is also heightened if you are male, have high blood pressure or a neurological disease,” Dr. Mads Nielsen, study coauthor and professor at the University of Copenhagen’s department of computer science, says.


No votes yet.
Please wait...


Please enter your comment!
Please enter your name here