The computer model can determine whether you will die from COVID-19

Artificial intelligence is able to predict who is most likely to die from coronavirus. In doing so, it can also help you decide who should be on the front lines for the precious vaccines being administered across Denmark.

The result is a recently published study by researchers in the Department of Computer Science at the University of Copenhagen. Since the first wave of the COVID-19 pandemic, researchers have been working to develop computer models that can predict, based on disease history and health data, how severely people will be affected by COVID-19.

Based on patient data from the Capital Region of Denmark and Region of Zealand, the study results demonstrate that artificial intelligence can, with up to 90 percent certainty, determine whether an uninfected person who is not yet infected will die of COVID -19 or not if they are unfortunate to be infected. Once admitted to the hospital with COVID-19, the computer can predict with 80 percent accuracy whether a person will need a respirator.

“We started to work on the models of assistance to hospitals, because in the first wave they feared they would not have enough respirators for patients in intensive care. Our new findings could also be used to carefully identify who needs a vaccine, ”explains Professor Mads. Nielsen from the Department of Computer Science at the University of Copenhagen.

Older men with high blood pressure are at higher risk

The researchers fed a computer program with health data on 3,944 Danish patients with COVID-19. This trained the computer to recognize patterns and correlations in patients’ previous illnesses and their struggles with COVID-19.

“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 increased if you are male , blood pressure or a neurological disease “, explains Mads Nielsen.

The diseases and health factors that, according to the study, most influence if a patient ends up on a respirator after becoming infected with COVID-19 are in order of priority: BMI, age, hypertension, being male, neurological diseases, COPD, asthma, diabetes and heart disease.

“For those affected by one or more of these parameters, we found that it might make sense to move them up the vaccine row, to avoid any risk of inflection and eventually end up on a respirator,” says Nielsen.

Predicting respiratory needs is critical

The researchers are currently working with the Capital Region of Denmark to take advantage of this new batch of results in practice. They hope that artificial intelligence will soon be able to help hospitals in the country, continuously predicting the need for respirators.

“We are working to anticipate the need for respirators five days in advance, giving the computer access to health data for all positive COVIDs in the region,” said Mads Nielsen, adding:

“The computer will never be able to replace a doctor’s assessment, but it can help doctors and hospitals see many patients infected with COVID-19 at once and set ongoing priorities.”

However, there is still a lack of technical work to make the region’s health data available to the computer and, from there, calculate the risk to infected patients. The research was carried out in collaboration with Rigshospitalet and Bispebjerg and Frederiksberg Hospital.