A Danish research team has developed artificial intelligence with 90 percent prediction accuracy.
A team of researchers from the University of Copenhagen claim to have developed AI software capable of predicting a person’s risk of death from COVID-19 with 90 percent accuracy.
The program was fed 3,944 Danish coronavirus patient files to build its prediction algorithms.
The AI software received non-identifying information in the patient files including their health data such as underlying medical conditions. The program was then “trained” to recognize patterns in the medical histories of the patients. What they discovered was that the highest risk factors included BMI, age, high blood pressure, and being male.
Once a patient has been admitted to a hospital following a COVID-19 diagnosis, the program was also able to predict a patient’s likelihood for requiring a respirator to an accuracy level of 80 percent, said the report on the study conducted by the researchers.
The AI software was initially developed to help hospitals while developing predictive models.
“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,” explained Professor Mads Nielsen from the Department of Computer Science at the University of Copenhagen. “Our new findings could also be used to carefully identify who needs a vaccine.”
Nielsen also went on to say that, “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.”
According to the research, the following conditions are the most determining factors for whether a patient will require a respirator following a COVID-19 infection. They are listed in order of largest impact first: BMI, age, high blood pressure, being male, neurological diseases, chronic obstructive pulmonary disease, asthma, diabetes and heart disease.
Nielsen stated that based on what was gleaned from the AI software, it would make sense to make a vaccination priority of people who are affected by “one or more of these parameters.”
