Using patient information, artificial intelligence can make a 90 percent precise evaluation of whether an individual will pass away from COVID-19 or not, according to new research study at the University of Copenhagen. Body mass index (BMI), gender and high blood pressure are amongst the most greatly weighted aspects. The research can be used to forecast the number of patients in medical facilities, who will require a respirator and determine who ought to be initially in line for a vaccination.

Artificial intelligence has the ability to anticipate who is most likely to die from the coronavirus. In doing so, it can also help decide who need to be at the front of the line for the precious vaccines now being administered throughout Denmark.

The outcome is from a recently published research study by scientists at the University of Copenhagen’s Department of Computer Science. Because the COVID pandemic’s very first wave, scientists have actually been working to develop computer models that can predict, based on disease history and health data, how terribly individuals will be impacted by COVID-19.

Based upon client information from the Capital Area of Denmark and Area Zealand, the results of the research study show that artificial intelligence can, with approximately 90 percent certainty, determine whether an uninfected person who is not yet infected will pass away of COVID-19 or not if they are unfortunate sufficient to become contaminated. Once admitted to the hospital with COVID-19, the computer system can anticipate with 80 percent accuracy whether the individual will require a respirator.

“We began dealing with the designs to assist healthcare facilities, as during the very first wave, they feared that they did not have adequate respirators for intensive care patients. Our brand-new findings could likewise be used to thoroughly recognize who needs a vaccine,” discusses Teacher Mads Nielsen of the University of Copenhagen’s Department of Computer technology.

Older men with high blood pressure are highest at danger

The scientists fed a computer system program with health data from 3,944 Danish COVID-19 clients. This trained the computer system to recognize patterns and connections in both patients’ previous diseases and in their bouts versus COVID-19.


“Our outcomes show, unsurprisingly, that age and BMI are the most definitive parameters for how seriously an individual will be impacted by COVID-19. However the likelihood of passing away or ending up on a respirator is likewise increased if you are male, have hypertension or a neurological illness,” describes Mads Nielsen.

The illness and health aspects that, according to the study, have the most affect on whether a client ends up on a respirator after being infected with COVID-19 are in order of top priority: BMI, age, hypertension, being male, neurological illness, COPD, asthma, diabetes and heart problem.

“For those affected by one or more of these parameters, we have discovered that it might make sense to move them up in the vaccine line, to prevent any threat of them ending up being inflected and eventually ending up on a respirator,” says Nielsen.

Predicting respiratory requirements is a need to

Scientists are currently dealing with the Capital Region of Denmark to benefit from this fresh batch of lead to practice. They hope that expert system will quickly be able to assist the country’s hospitals by continuously anticipating the need for respirators.

“We are working towards an objective that we ought to be able to anticipate the requirement for respirators 5 days ahead by giving the computer system access to health information on all COVID positives in the area,” says Mads Nielsen, adding:

“The computer system will never be able to replace a physician’s evaluation, but it can assist physicians and healthcare facilities see many COVID-19 contaminated patients simultaneously and set continuous concerns.”

Nevertheless, technical work is still pending to make health information from the area available for the computer and afterwards to calculate the risk to the infected clients. The research was carried out in partnership with Rigshospitalet and Bispebjerg and Frederiksberg Medical Facility.