Computer Predicts If COVID Will Kill You With 90% Accuracy

Artificial intelligence can foresee if you will die from COVID-19, even before infection.

Artificial intelligence can foresee if you will die from COVID-19, even before infection.

A computer model used by researchers in Denmark can predict whether a person will die before they even get infected with the coronavirus.

Being older and overweight are the main predictors, along with being a man and having high blood pressure.

The model determines the progression of the disease and death showing who should be the first to receive the SARS-CoV-2 vaccine in Denmark.

The model’s prediction of whether a person with no evidence of COVID-19 infection would die or survive was 90 percent accurate.

The model’s prediction of whether a person will be admitted to hospital and Intensive Care Unit (ICU) or require a respirator was 80 percent accurate.

Professor Mads Nielsen, study co-author, said:

“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.”

Since the COVID-19 outbreak, scientists have been working on machine learning (ML) models to predict the severity of the disease before people become ill by using their health records.

The computer program was designed to look for patterns in people’s history of illness and how they fought against COVID-19.

Professor Nielsen said:

“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 study, health risk factors and chronic diseases are the keys to find out whether a COVID-19 patient will need a breathing machine or respirator.

BMI, age, high blood pressure, being male, neurological diseases, Chronic obstructive pulmonary disease (COPD), asthma, diabetes and heart disease were the key parameters in predicting the risk of hospital and ICU admission, use of mechanical ventilation, and death.

Professor Nielsen said:

“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 inflected and eventually ending up on a respirator.”

The research team are hoping to develop a program to help hospitals foresee whether they need respirators several days in advance.

Professor Nielsen said:

“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.

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.”

About the author

Mina Dean is a Nutritionist and Food Scientist. She holds a BSc in Human Nutrition and an MSc in Food Science.

The study was published in the journal Scientific Reports (Jimenez-Solem et al., 2021).

Get FREE email updates to PsyBlog

Hello, and welcome to PsyBlog. Thanks for dropping by.

This site is all about scientific research into how the mind works.

It’s mostly written by psychologist and author, Dr Jeremy Dean.

I try to dig up fascinating studies that tell us something about what it means to be human.

Get FREE email updates to PsyBlog. Join the mailing list.