This New AI Tool Can Predict Who Will Die from COVID-19

Submit

The COVID-19 virus is something that has scared the world, and for all the right reasons. While vaccination trials around the world are taking place, scientists have gone ahead and created a new artificial intelligence tool that can predict who is prone to death by COVID-19 and the most impressive part here is that the tool can make predictions that are up to 90% accurate.

New AI Tool Can Find Out if a Person is Susceptible to Dying from COVID-19

Researchers have done this by using data from almost 4,000 COVID-19 patients and then used their data to train their AI tools in order to find the relevant patterns in the data.

YouTube Has Now Banned Vaccine Misinformation

Professor Mads Nielsen of the University of Copenhagen states that the new tool could be used to try and predict who should receive the vaccination before others based on the mortality rate. In addition to that, the data could also be used to make sure that adequate resources are redirected to the hospitals that need them the most.

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.

The researchers suggest that a person's BMI as well as their age have the biggest impact on whether or not the person is going to survive the virus or not. Other medical conditions such as asthma, heart disease, and diabetes are also notable in this.

Nielsen further states:

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.

For those who are interested in reading more about this, you can head over here and get all the information.

Submit