Computer can determine whether you'll die from COVID

February 05, 2021

Using patient data, artificial intelligence can make a 90 percent accurate assessment of whether a person will die from COVID-19 or not, according to new research at the University of Copenhagen. Body mass index (BMI), gender and high blood pressure are among the most heavily weighted factors. The research can be used to predict the number of patients in hospitals, who will need a respirator and determine who ought to be first in line for a vaccination.

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

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

Based on patient data from the Capital Region of Denmark and Region Zealand, the results of the study 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 enough to become infected. Once admitted to the hospital with COVID-19, the computer can predict with 80 percent accuracy whether the person will need a respirator.

"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 of the University of Copenhagen's Department of Computer Science.

Older men with high blood pressure are highest at risk

The researchers fed a computer program with health data from 3,944 Danish COVID-19 patients. This trained the computer to recognize patterns and correlations in both patients' prior illnesses and in their bouts against 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 heightened if you are male, have high blood pressure or a neurological disease," explains Mads Nielsen.

The diseases and health factors that, according to the study, have the most influence on whether a patient ends up on a respirator after being infected with COVID-19 are in order of priority: BMI, age, high blood pressure, being male, neurological diseases, COPD, asthma, diabetes and 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," says Nielsen.

Predicting respiratory needs is a must

Researchers are currently working with the Capital Region of Denmark to take advantage of this fresh batch of results in practice. They hope that artificial intelligence will soon be able to help the country's hospitals by continuously predicting the need for respirators.

"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," says Mads Nielsen, adding:

"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."

However, technical work is still pending to make health data from the region available for the computer and thereafter to calculate the risk to the infected patients. The research was carried out in collaboration with Rigshospitalet and Bispebjerg and Frederiksberg Hospital.
-end-
Facts:
  • Data is processed on Computerome, a secure supercomputer for personal data, and under the permission of the Danish Patient Safety Authority, data owners and other relevant authorities.
  • Artificial intelligence predicts with 90 percent accuracy whether an infected patient will die of COVID-19.
  • Once a person is hospitalized with COVID-19, artificial intelligence can predict whether the person should be on a respirator with 80 percent accuracy.
  • BMI, age, high blood pressure, being male, neurological diseases, COPD, asthma, diabetes and heart disease are factors that artificial intelligence weigh`s most to with the risk of getting into the respirator.
  • The computer models are based on health data from 3,944 COVID-19 patients from the Capital Region and Region Zealand.
  • The article is published in the scientific journal Scientific Reports.
  • The study is supported by the Novo Nordisk Foundation and the Innovation Fund.

    Contact

    Mads Nielsen
    Professor
    Department of Computer Science
    University of Copenhagen
    Mobile: + 45 24 600 599
    madsn@di.ku.dk

    Michael Skov Jensen
    Journalist
    The Faculty of Science
    University of Copenhagen
    Mobile: + 45 93 56 58 97
    msj@science.ku.dk

    University of Copenhagen - Faculty of Science

    Related High Blood Pressure Articles from Brightsurf:

    High blood pressure linked to baroreflex in rats
    Researchers describe a newly observed phenomenon in the way blood pressure is maintained in certain rats.

    Children who take steroids at increased risk for diabetes, high blood pressure, blood clots
    Children who take oral steroids to treat asthma or autoimmune diseases have an increased risk of diabetes, high blood pressure, and blood clots, according to Rutgers researchers.

    High blood pressure treatment linked to less risk for drop in blood pressure upon standing
    Treatment to lower blood pressure did not increase and may decrease the risk of extreme drops in blood pressure upon standing from a sitting position.

    Changes in blood pressure control over 2 decades among US adults with high blood pressure
    National survey data were used to examine how blood pressure control changed overall among U.S. adults with high blood pressure between 1999-2000 and 2017-2018 and by age, race, insurance type and access to health care.

    Wealthier men are more likely to develop high blood pressure
    Working men with higher incomes are more likely to develop high blood pressure, reports a study presented at the 84th Annual Scientific Meeting of the Japanese Circulation Society (JCS 2020).

    Regular exercise helps prevent high blood pressure, even in areas of high air pollution
    Regular physical activity is a healthy way to prevent and reduce high blood pressure, even in places where pollution levels are relatively high.

    Could high blood pressure at night have an effect on your brain?
    Most people's blood pressure 'dips' during the night. But for some people, especially those with high blood pressure, their nighttime pressure stays the same or goes up, called 'reverse dipping.' A new study shows that these people may be more likely to have small areas in the brain that appear damaged from vascular disease and associated memory problems.

    All women should be educated after childbirth about high blood pressure
    After childbirth, it is not uncommon for women to experience high blood pressure.

    Brain blood flow sensor discovery could aid treatments for high blood pressure & dementia
    A study led by researchers at UCL has discovered the mechanism that allows the brain to monitor its own blood supply, a finding in rats which may help to find new treatments for human conditions including hypertension (high blood pressure) and dementia.

    New strategy for treating high blood pressure
    The key to treating blood pressure might lie in people who are 'resistant' to developing high blood pressure even when they eat high salt diets, shows new research published today in Experimental Physiology.

    Read More: High Blood Pressure News and High Blood Pressure Current Events
  • Brightsurf.com is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to Amazon.com.