Artificial intelligence can accurately predict if you’ll live or die from COVID-19

COPENHAGEN, Denmark — Even with multiple vaccines in production and safety measures curbing the spread, there is still plenty scientists don’t know about COVID-19. Some of those mysteries include which patients will suffer a severe infection and who needs a vaccine first. Now, researchers in Denmark say artificial intelligence can peer into this grim future and find the answers. Their study finds a new computer program can accurately predict who will live and who will die of COVID-19 before they even contract the illness.

A team from the University of Copenhagen finds AI can predict with the likelihood someone will die of COVID with 90 percent accuracy. The algorithm bases this prediction on key factors, including body mass index (BMI), blood pressure, and gender. AI can even determine if someone will need a respirator during their hospital stay with 80 percent accuracy.

Researchers note this information can also help doctors manage hospital resources better and decide which high-risk citizens should receive a vaccination first. The team from Copenhagen’s Department of Computer Science has been working on the development of computer models to analyze COVID data since the beginning of the pandemic.

“We began working on the models to assist hospitals, as during the first wave, they feared that they did not have enough respirators for intensive care patients. Our new findings could also be used to carefully identify who needs a vaccine,” explains Professor Mads Nielsen in a university release.

Who is at the greatest risk of dying?

Study authors fed their AI program with health data from nearly 4,000 Danish COVID-19 patients. This allowed the computer to learn and recognize patterns in each patient’s prior illnesses and their fight with coronavirus.

“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,” Nielsen reports.

According to the study, these are the top factors which determine if a COVID patient will end up on a respirator:

  1. BMI
  2. Age
  3. High blood pressure
  4. Being male
  5. Neurological diseases
  6. COPD
  7. Asthma
  8. Diabetes
  9. Heart disease

“For those affected by one or more of these parameters, we have found that it may make sense to move them up in the vaccine queue, to avoid any risk of them becoming inflected and eventually ending up on a respirator,” Nielsen adds.

Predicting patient needs may prevent overwhelmed hospitals

Researchers are continuing to work with the Capital Region of Denmark of gather new patient data for their computer predictions. The team hopes AI will help hospitals in Europe predict how many respirators they’ll need before patients even arrive.

“We are working towards a goal that we should be able to predict the need for respirators five days ahead by giving the computer access to health data on all COVID positives in the region,” Nielsen concludes. “The computer will never be able to replace a doctor’s assessment, but it can help doctors and hospitals see many COVID-19 infected patients at once and set ongoing priorities.”

The study appears in the journal Scientific Reports.

Leave a Reply

Your email address will not be published.