Posted on 7 February 2020
On the 9th of January, the World Health Organization (WHO) notified the world about a new flu like virus outbreak in China’s Wuhan province. The Center for Disease Control (CDC) in the United States was a bit ahead of The Who and head announced the arrival of the novel coronavirus just three days earlier on the 6th of January. But a Canadian AI based infectious disease monitoring company BlueDot was able to predict the coronavirus outbreak more than a week prior to the CDC, and two weeks prior to the WHO by warning its customers on the 31st of December.
BlueDot uses a natural language processing (NLP) AI-driven algorithm that scours foreign-language news reports, animal and plant disease networks, and official proclamations. Doctors, scientists, and epidemiologists working at BlueDot further analyse the reports generated by the AI to remove any false positives, and critically assess the threat level. BlueDot’s reports are then sent to public health officials in a dozen countries (including the US and Canada), airlines, and frontline hospitals where infected patients might end up.
We know that governments may not be relied upon to provide information in a timely fashion. We can pick up news of possible outbreaks, little murmurs or forums or blogs of indications of some kind of unusual events going on.Kamran Khan, BlueDot’s founder and CEO speaking with the Eric Niiler in Wired Magazine
Hopefully soon it will be routine for novel machine learning techniques to detect highly infectious pathogens while they are contained in small localities, and long before they become a global pandemic.