Artificial Intelligence Can Tell If An Uninfected Person Would Die From COVID-19 With 90 Percent Accuracy

A new artificial intelligence algorithm developed by the University of Copenhagen can tell with startling accuracy whether or not a person would die if infected with the novel coronavirus.

According to Eurek Alert!, the assessment has an accuracy rate of around 90 percent after analyzing the data of almost 4,000 Danes who suffered from COVID-19.

Health experts hope to use the tool in order to understand which members of the population should receive the vaccine first and make a more effective roll-out in the midst of second waves occurring across the globe.

In addition, the model was also able to predict with around 80 percent accuracy which patients would need a respirator if infected. This information could help doctors better care for patients by knowing almost immediately who will be requiring the machines and hopefully save lives in the process. Health experts hope that combining infection rate patterns with the population's health data will be able to predict which hospitals should be sent respirators to avoid shortages in the event of a sudden outbreak.

"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," explained Professor Mads Nielsen of the University of Copenhagen's Department of Computer Science.

The artificial intelligence ended up relying on some factors that are already well-known to be risks for serious COVID-19 infection, such as weight and age. However, there were some less obvious risk factors as well.

"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 added.

Lab Technicians are manufacture the Astra Zeneca Covid-19 vaccine.
Getty Images | Heathcliff O'Malley

The order of importance of what affected mortality rate was BMI, age, high blood pressure, being male, the presence of neurological diseases, COPD, asthma, diabetes and heart disease.

That said, Nielsen warned that the artificial intelligence will not be able to replace doctors' assessments, though he believes it will be a substantial help.

The coronavirus has infected over 106 million people around the world and claimed around 2.3 million lives. In latest COVID-19 news, an Israeli hospital has expressed its hope that it has found a cure for the disease after seeing a 95 percent survival rate for those who were given an experimental medication, per The Inquisitr.