The heart of tech is coming to the heart of the Mediterranean. Join TNW in València this March 🇪🇸

This article was published on September 16, 2020

This AI spots local COVID-19 outbreaks before they’ve spun out of control

The system predict how long it will take for cases to double in different US counties

This AI spots local COVID-19 outbreaks before they’ve spun out of control
Thomas Macaulay
Story by

Thomas Macaulay

Writer at Neural by TNW Writer at Neural by TNW

Researchers have developed a new machine learning-based tool that detects potential COVID-19 outbreaks in individual US counties.

The system makes its assessments by analyzing reported COVID-19 cases and deaths, rates of positive tests, face mask rules, social distancing policies, and changes in testing.

It also incorporates the Centers for Disease Control and Prevention’s Social Vulnerability Index, which assesses how individual communities are prepared for hazardous events based on factors including poverty and population density.

It then predicts how fast the virus is spreading by estimating how many days it will take for the number of cases to double.

The forecasts are displayed on an interactive heat map that shows each county’s doubling rate. Users can also see the area’s population, new cases, and average daily cases, all of which is updated two-to-three times per week.

[Read: Are EVs too expensive? Here are 5 common myths, debunked]

The system was developed by researchers from Massachusetts General Hospital, Harvard Medical School, Georgia Tech, and Boston Medical Center. Jagpreet Chhatwal, an assistant professor at Harvard Medical School, said it could reduce the spread of infections by identifying COVID-19 hotspots to isolate from their neighbors:

While earlier mitigation responses focused on state-level measures — such as a lockdown of an entire state — detecting local outbreaks will allow policymakers to implement measures at the county level — such as closing restaurants in a single county — to effectively contain the pandemic. The model is able to detect many of the prior outbreaks within a matter of days.

In tests, the tool verified an outbreak last week in Johnson county Iowa, which was linked to a surge in cases at the University of Iowa. It also identified several counties where potential outbreaks could be happening now, including Harrisonburg County in Virginia, Wheeler County in Georgia, Monroe County in Indiana, and Whitman County in Washington.

You can see how things are looking in your home county by checking out the COVID-19 Outbreak Detection Tool.

So you’re interested in AI? Then join our online event, TNW2020, where you’ll hear how artificial intelligence is transforming industries and businesses.

Get the Neural newsletter

Greetings Humanoids! Did you know we have a newsletter all about AI? You can subscribe to it right here.

Also tagged with

Back to top