An AI algorithm detected the coronavirus outbreak a week before the CDC

By Andrea Park for Becker’s Hospital Review

Six days before the CDC’s Jan. 6 alert of a flulike outbreak in China, and nine days before the World Health Organization’s Jan. 9 notice, an artificial intelligence-powered platform had already detected and sent warning of the coronavirus outbreak, Wired reports.

BlueDot, a global health monitoring platform based in Canada, reportedly notified its clients of the outbreak on Dec. 31. Per Wired, rather than relying on national health officials for outbreak information, as government health agencies must, BlueDot’s AI algorithm analyzes global news reports, animal and plant disease networks, airline ticketing data and official announcements to predict and detect potential epidemics.

“We know that governments may not be relied upon to provide information in a timely fashion,” Kamran Khan, BlueDot’s founder and CEO, told Wired. “We can pick up news of possible outbreaks, little murmurs or forums or blogs or indications of some kind of unusual events going on.”

In the case of the coronavirus outbreak, the algorithm reportedly used airline ticketing information to accurately predict the virus’ rapid spread from Wuhan, China, to Bangkok, Seoul, Taipei and Tokyo.

BlueDot’s algorithm uses machine learning and natural language processing technology to detect signs of potential disease outbreaks from the collected information. Human epidemiologists then review and verify the AI’s findings before sending a report to the company’s clients in government, industry and public health, as well as other public health officials, airlines and hospitals in the affected regions.