NEW DELHI: With doctors across the world struggling to save patients from succumbing to covid-19, Artificial Intelligence (AI), using patient data, can help forecast mortality, a research at the University of Copenhagen has shown.
While AI is able to predict who is most likely to die from coronavirus, the research, published in journal Scientific Reports, said it can also help decide who should be at the front of the line for the precious covid-19 vaccines.
Based on patient data from the capital region of Denmark and New Zealand, the results of the study demonstrated that artificial intelligence can, with up to 90% accuracy, determine whether a person will die of covid-19. Once admitted to the hospital with covid-19, it can predict with 80% accuracy whether the person will need a respirator.
Since the first wave of the pandemic, researchers have been working to develop computer models that can forecast, based on disease history and health data, how badly a person will be affected by covid-19.
“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,” said Professor Mads Nielsen of the University of Copenhagen’s department of computer science.
Researchers fed a computer programme with health data from 3,944 Danish covid-19 patients. They said body mass index (BMI), gender and high blood pressure are among the most heavily weighted factors.
“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,” said Nielsen.
In order of priority BMI, age, high blood pressure, being male, neurological diseases, COPD, asthma, diabetes, and heart disease are the factors, according to the study, that have the most influence on whether a patient ends up on a respirator after being infected with covid-19.
“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,” Nielsen added.
