Home » Facebook uses AI to predict the progress of the coronavirus infection

Facebook uses AI to predict the progress of the coronavirus infection

by admin

From search for effective drugs against coronavirus to the possibility of predict the progress of Covid-19 cases, artificial intelligence has taken the field to offer new, powerful tools to manage large numbers such as those of the pandemic: it does so with neural networks, such as those that at the University of Cambridge have made it possible to discover that as many as 200 existing drugs and on the market, approved for other diseases, could have anti-Covid effects, and it does so with the system that provides for the development of the infection, developed by the Facebook in Paris for Research on Artificial Intelligence.

The research with which a Cambridge, the group headed by Namshik Han has given new impetus to a trend inaugurated over a year ago by the pandemic, is published in Science Advances: using a neural network they managed to identify a network of 1573 proteins induced by the coronavirus and compared them with the characteristics of molecules contained in already approved drugs to treat other diseases. This has led the artificial intelligence to identify 200 existing drugs, divided into two large groups, which prevent the virus from replicating and which help the immune system to react to the infection.

Tinder and Meetic

So vaccines changed dating apps (too)

by Emanuele Capone


In France the Fair Facebook has used an artificial intelligence system to come up with a model that can predict future cases in a particular context, using data on recent cases in statistically similar areas, and the organization is making all predictive models open-source, so that researchers can use them: “Starting from the United States, we found that social connection is an important aspect in this mechanism – explained by Facebook – For our analysis we use the Social Connectedness Index, a project released through Facebook’s Data for Good initiative, which measures the strength of connection between two geographic areas, as represented by the bonds of friendship on the social network. Our results show that the social connection of statistically similar areas is two to 8 times higher in our model than that of unrelated areas. “

See also  Two drops of this natural remedy would be enough to relieve the symptoms of colds and seasonal ailments

The ranking

Most popular social networks, the revenge of Facebook and the surprise of YouTube

by Emanuele Capone



The work is based on the US scenario, but also looks to Europe: since the beginning of the pandemic, the team of Biocom-S of the Universitat Politècnica de Catalunya, which works together with the University of Vienna and collaborates with the Fair, has provided the European Commission with comprehensive reports and forecasts on the spread of the disease.

.

You may also like

Leave a Comment

This site uses Akismet to reduce spam. Learn how your comment data is processed.

This website uses cookies to improve your experience. We'll assume you're ok with this, but you can opt-out if you wish. Accept Read More

Privacy & Cookies Policy