Algorithm can predict if a person will die from COVID-19, new study finds
INDIANAPOLIS (WISH) – Artificial intelligence can determine if a person will die should they contract the coronavirus with a 90 percent accuracy rate, according to scientists from the University of Copenhagen.
Researchers entered data from 3,944 Danish coronavirus patients into a computer modeling system designed to detect health patterns between March 1, 2020 and June 16, 2020. The algorithm assessed previous health history from electronic records including demographics, comorbidities (such as high blood pressure, heart disease and diabetes) and medications.
Out of the 3,944 patients assessed, 324 did not survive. Of those patients, men between 73 and 87 years old, with high blood pressure (above 120/80) are at greatest risk of dying from COVID-19. The average body mass index (BMI)–a measure of whether a person is overweight–also affected survival rates as well as pre-existing neurological disorders.
“Our results demonstrate, unsurprisingly, that age and BMI are the most decisive factors for how severely a person will be affected by COVID-19,” authors said in a news release. “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 disorder.”
Additionally, data revealed variables that have the most influence on if a person will end up on respirator post-infection and–in order of the most to least influential–variables include: BMI, age, high blood pressure, being male, having a neurological disease, chronic obstructive pulmonary disease, diabetes and heart disease.
This data, they say, should be used to help health policy officials prioritize who should be first in line to get vaccinated.
“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 infected and eventually ending up on a respirator [or dying],” authors conclude.
News 8’s medical reporter, Dr. Mary Elizabeth Gillis, D.Ed., is a classically trained medical physiologist and biobehavioral research scientist. She has been a health, medical and science reporter for over 6 years. Her work has been featured in national media outlets. You can follow her on Facebook @DrMaryGillis and Instagram @reportergillis.