AI-Driven Computer Model Uses Patient Data to Predict Who is More Likely to Die from COVID-19 with 90% Accuracy

Using patient data, artificial intelligence (AI) can make a 90% accurate assessment of whether a person will die from COVID-19 or not, according to new research.

The results of a newly published study by researchers at the University of Copenhagen (Copenhagen, Denmark) demonstrate that based on patient data, AI can, with up to 90% 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% accuracy whether the person will need a respirator. 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.

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. 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. The researchers hope that AI will soon be able to help 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,” said Professor Mads Nielsen of the University of Copenhagen’s Department of Computer Science. “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.”

Related Links:
University of Copenhagen