On January 9, the World Health Organization notified the public of a viral outbreak in China. Several cases of pneumonia had been reported in Wuhan, likely after live animal sellers were exposed to the local fish market.
The CDC (US Centers for Disease Control and Prevention) had released the news of the Coronavirus a few days earlier, on January 6. BlueDot, Canadian health monitoring platform, beat them both by sending the news of the outbreak to its users on December 31st.
How is it possible?
BlueDot uses an algorithm based on artificial intelligence. BlueDot's AI analyzes foreign language news, animal and plant disease information networks and official bulletins. And on December 31 it warned its customers in advance to avoid dangerous areas such as Wuhan.
Speed is crucial in preventing the spread of an epidemic, and Chinese officials have never made great performances on the subject of disease, air pollution and natural disasters.
WHO and CDC rely on these same health officials for their disease monitoring. Not well.
Maybe an artificial intelligence can get there faster. "We know that governments cannot be relied upon to provide information in a timely manner.", he claims Kamran Khan, founder and CEO of BlueDot. "We are able to gather news of possible outbreaks, small murmurs on forums and blogs, indications of unusual events taking place."
Social media? Not very reliable
Khan says the algorithm doesn't use social media posts because the data is too messy. But it has one trick up its sleeve: access to global airline ticketing data that can help predict where and when infected residents will be headed next. BlueDot's AI correctly predicted that the virus would leap from Wuhan to Bangkok, Seoul, Taipei, and Tokyo in the days following its initial appearance.
The BlueDot manager worked as an infectious disease specialist at the Toronto hospital during the 2003 SARS outbreak. That virus departed from provincial China and spread to Hong Kong and then Toronto, where it killed 44 people.
"There's a bit of deja vu right now", Khan says about the coronavirus outbreak today. “In 2003, I saw the virus overwhelm the city and paralyze the hospital. There was a tremendous amount of mental and physical stress and I thought "Let's not do this again". "
After testing several predictive programs, Khan launched BlueDot in 2014 and raised $ 9,4 million in venture capital funding.
The company now has 40 employees: doctors and programmers who develop the disease monitoring program. A "computer monster" that uses natural language processing and machine learning techniques to sift through news in 65 languages, along with airline data and veterinary disease outbreak reports.
Coronavirus, it still serves the human factor
Once AI's automatic data monitoring is complete, human analytics take the lead. Epidemiologists check that the findings make scientific sense and write a report that is sent to clients (government, business and public health).

BlueDot reports are then sent to health officials from a dozen countries (including the United States and Canada), airlines and hospitals where infected patients could end up. BlueDot does not sell its data to the general public, (but is working on it).
- Woolly Mammoth: 2027, the year of resurrectionIt seemed like a boutade, but Colossal has raised the necessary funds and is preparing for the genetic resurrection of the Woolly Mammoth within 4 years.
Google tried BlueDot before, but it failed
BlueDot isn't the first to look for a solution for public health officials, but it hopes to do better than Google. Its Google Flu Trend service, which analyzed and attempted to predict flu trends, was shut down after it "missed" its predictions on the severity of the 140 flu season by 2013%.
Maybe premature times? BlueDot has won where Google has failed. It successfully predicted not only SARS, but also the location of the Zika outbreak in South Florida (in a publication in the British medical journal The Lancet).
It remains to be seen if BlueDot will be successful again, in the Wuhan Coronavirus case.

"The outbreak is probably much bigger than that confirmed by public health officials," says James Lawler, an infectious disease specialist at the University of Nebraska Medical Center, who treated Ebola quarantined patients in 2017 and 2018.
He is not wrong: quarantine cities are now 18, and nearly 60 million people are in quarantine. While waiting for the two "instant" hospitals built in a few days by the authorities to be completed, the health complexes of the Wuhan epicenter are in enormous difficulty.
Lawler and others say the coronavirus outbreak will continue to spread. We still don't know how many people will get sick and how many of them will die before the epidemic subsides.