Canadian artificial intelligence company BlueDot detected the first signs of a coronavirus infection in China days before the WHO alerted the world. Today, the start-up is working to predict the movement of infected people.
Artificial intelligence is increasingly useful in the field of health. Nowadays, algorithms are starting to manage to detect brain tumors in real time, spot psychotic disorders in patients’ speech, and could even help us better fight the coronavirus epidemic that is currently terrifying the whole world. According to the American media Wiredusing data accessible online and machine learning systems, a Canadian company called BlueDot had detected the first signs of a coronavirus infection in Wuhan on December 31, well before the WHO alerted the whole world to the subject. She then predicted that the infectious agent would pass the following days from the cradle of contamination in Bangkok, Seoul, Taipei and Tokyo.
Founded in 2014, the company aims to “monitor and anticipate the spread of the most dangerous infectious diseases in the world”. “Infectious diseases are a growing global threat in our interconnected world. More frequent and more severe in the past 20 years than at any other time in history, infectious diseases are growing in the face of a new reality: global travel, urbanization and climate change. world. If diseases spread quickly, knowledge can spread even faster,” she explains on her website.
“We can’t always trust governments to give real-time information,” he says. Wired Kamran Khan, former doctor and founder of BlueDot, in reference to the silence of the Chinese authorities during the SARS wave in 2003. something unusual is happening.”
Plan the movements of infected patients
The algorithm therefore takes into account data from online forums, symptom searches on Google, reports, official statements or even health bulletins. It also sifts through information relating to the movement of populations through the sale of plane tickets or the map of air routes.
Once identified and analyzed by the software, the signals are decrypted by epidemiologists who then transmit the main information to the start-up’s customers. Currently, BlueDot is working with the airline data platform ATPCO to predict where residents infected with the coronavirus could go, explains Wired.
If these reports are not accessible to the general public, they are instead transmitted to the heads of public health institutions in a dozen countries, to the airlines and to the hospitals in which the infected people could go.
In 2016, BlueDot had already caused a stir because of the Zika epidemic. According to the British medical journal The Lancetthe software would have been more effective than the algorithm put in place at the time by Google to anticipate the spread of the virus.
.