New AI on CT predicts how COVID-19 will evolve and whether there is a risk of death

In a new paper, a research team led by Hiroyuki Yoshida found that if A.I.

uncontrolledly learn from the results of computed tomography (CT), then he will be able to predict with a high degree of probability how the patient’s disease will progress. 

The model determines the point for each patient,how COVID-19 will progress, as well as the time to enter intensive care. In addition, with the help of AI, patients can be divided into groups of low and high risk of severe disease.

Our results show that predictions fromunsupervised AI models were made with greater accuracy compared to other similar developments. Now you can make predictions about the development of the disease immediately based on CT data. 

Research text

Early versions of AI predicting outcomesdiseases were limited by various subjective assessments, semi-automated prediction schemes or other control methods. In this case, the percentage of fulfilled forecasts decreased. 

The authors of the new work believe that their developmentcan be effectively used not only for the new type of coronavirus, but also for other serious diseases: you just need to adapt the data, and the basis is already there. 

To read Further

By 2100, 95% of the oceans will be uninhabitable

Look at the updated F-15 fighters: they carry 24 air-to-surface missiles

A spaceship several kilometers away: everything that is known about China's new project