A recent startup in Canada used Artificial intelligence to map the progress and behavior of the Chinese Coronavirus. They were amongst the first ones to raise an alarm about the risk of the virus outbreak.
The relatively new startup, BlueDot, has designed an algorithm that can filter through countless reports a day alongside air traffic data so as to recognize and screen the spread of infectious diseases.
Based in Toronto, the software sent a warning to customers on December 31 about the new coronavirus flare-up—a couple of days before the health authorities released the official statements to the public. Likewise, it accurately anticipated the nations wherein the danger of infection was generally intense.
According to Kamran Khan, the company’s founder, “What we are trying to do is to really push the boundaries—to be using data and analytics and technology to keep moving faster”. He further continued, “Ultimately when you’re dealing with an outbreak, time and timing is everything.”
The startup was initially planned to be started after the SARS breakout of 2002-2003. The idea was born when the 49-year-old epidemiologist saw large numbers of patients swarming the hospitals following the epidemic. Khan was specializing in infectious diseases at Toronto Hospital during that time.
He talked about the outbreak, saying, “A number of health care workers were infected including one of my colleagues. We had a number of health care workers who died. This was a really eye-opening experience and was the motivation behind everything that we’re doing at BlueDot.”
In 2014, Khan launched BlueDot, which currently has 40 representatives—a group of doctors, veterinarians, disease transmission experts, information researchers, and programming engineers. Together, they worked out a constant notice of real-time warning framework dependent on regular language handling and AI.
Like clockwork nonstop, the organization’s algorithm examines official reports, proficient discussions, and online news sources, scanning for keywords and expressions. BlueDot can, currently, peruse message in 65 dialects and can follow 150 distinct types of diseased.
Khan said, “We call it the needles in the haystack. There’s a massive amount of data and the machine is finding the needles and presenting it to the human experts, who then review it and train the machine to understand if that information corresponds to an actual threat.”
If the threat seems legit, it is transferred to a database and is used to analyze the possible location of the epidemic, close by airports and ‘commercial air travel itineraries from around the world’. Weather and climate information, national well-being framework databases, and even the presence of mosquitoes or creatures that transmit maladies to people are also considered.
When that examination is finished, BlueDot sends a notification to its customers—government organizations, airlines, emergency clinics—where most of those passengers may land. The objective is to allow specialists to plan for the worst: a significant illness episode.