A little after midnight on Dec. 30, artificial intelligence platform BlueDot picked up on a cluster of "unusual pneumonia" cases happening around a market in Wuhan, China, and flagged it.
BlueDot had spotted what would come to be known as COVID-19, nine days before the World Health Organization released its statement alerting people to the emergence of a novel coronavirus.
The novel respiratory illness COVID-19 has since spread to 58 countries and infected more than 87,000 people globally with 104 deaths outside of China. On Feb. 25, WHO Director General Tedros Adhanom Ghebreyesus said that COVID-19 "absolutely" has the potential to become a pandemic, defined as the worldwide spread of a new disease.
But in December, "we didn't know at that moment that this was going to become something of this magnitude," Kamran Khan, founder and CEO of BlueDot and professor of medicine and public health at the University of Toronto, tells CNBC Make It.
What if this outbreak gets bigger? And what if it's bigger than we think it is right now? Khan says he wondered.
It was exactly the type of situation Khan imagined when he had the idea for his company BlueDot: "Spread knowledge faster than the diseases spread themselves," he says.
Inspired by SARS
Khan describes himself as an "accidental entrepreneur" — he never went to business school or had any experience coding. It was his experience as an epidemiologist and physician treating patients in Toronto during the severe acute respiratory syndrome (SARS) outbreak in 2003 that inspired him to start BlueDot.
"Certainly none of us knew what SARS was until it literally showed up in our cities and hospitals," he says. He recalls the "mental and emotional fatigue" of the SARs outbreak, which went on for six months and killed a total of 774 people in 29 countries, including many of his fellow healthcare workers. It also cost an estimated $40 billion globally, according to the Centers for Disease Control.
"What I learned during SARS is, let's not get caught flatfooted, let's anticipate rather than react," Khan says. He also learned that "if we rely on government agencies to report information about infectious disease activity, we may not always get that in the most timely way or as quickly as we would like." The internet, for example, has become an interesting medium for epidemiologists to gather information about infectious disease activity that may not come through official channels.
Compelled to develop better technology to handle infectious disease outbreaks, for more than a decade Khan studied how diseases spread globally. Then six years ago took "a leap of faith" and founded BlueDot. (The name is inspired by scientist Carl Sagan's description of Earth captured in a photo from NASA's Voyager 1 in 1990. "We felt that there was a certain degree of humility in the fact that we are all in this together when we're dealing with infectious diseases," Khan says.)
BlueDot is proprietary software-as-a-service designed to track, locate and conceptualize infectious disease spread. The company, which received a total of $9.4 million in funding in 2019 (including seed funding from Horizons Ventures and a $7 million Series A financing round led by The Co-operators and BDC Capital's Women in Technology Venture Fund), now employs diverse team of 40 people including veterinarians, doctors, epidemiologists, engineers, data scientists and software developers. It sends out alerts — brief synopses of anomalous disease outbreaks that its AI has discovered and the risks they may pose — to health care, government, business, and public health clients.
The key to BlueDot is big data. It uses natural language processing and machine learning to cull data from hundreds of thousands of sources, including statements from official public health organizations, digital media, global airline ticketing data, livestock health reports and population demographics. It's able to rapidly process tons of information every 15 minutes, 24 hours a day.
From there a group of physicians and computer programmers review the AI findings, do a gut check and create the reports that are sent out. "We don't use artificial intelligence to replace human intelligence, we basically use it to find the needles in the haystack and present them to our team," Khan says.
Beyond just detecting infectious disease threats as early as possible, BlueDot's goal is to understand how diseases might disperse to different parts of the world, and then determine the potential consequences of it spreading.
In the case of COVID-19, in addition to sending out an alert, BlueDot was also able to correctly identify the cities that were highly connected to Wuhan using things like global airline ticketing data to help anticipate where the infected might be traveling. The international destinations that BlueDot anticipated would have the highest volume of travelers from Wuhan were: Bangkok, Hong Kong, Tokyo, Taipei, Phuket, Seoul, and Singapore. In the end, 11 of the cities at the top of their list were the first places to receive COVID-19 cases.
Beyond COVID-19
Khan admits similarities to SARS in COVID-19's spread gave him "a bit of angst." "Are we going to go through something similar to what we did 17 years ago?" he said.
Time will tell exactly will become of COVID-19. It also remains to be seen what kind of impact BlueDot will have on tracking the spread of disease on a larger scale.
So far, BlueDot has been used to successfully predict that the Zika virus would spread to Florida in 2016, six months before it happened. The software was also able to determine that the 2014 Ebola outbreak would leave West Africa — that was the outbreak that eventually reached the U.S. BlueDot can also be used for things like meningitis, yellow fever, and anthrax.
A major benefit of using AI is the ability to keep tabs on other outbreaks that are happening around the clock while people's attention is on coronavirus, Khan says. For example, there's currently an uptick in Lassa fever in West Africa. While this Lassa spike and others might not lead to a global pandemic or major outbreak, they are still affecting communities and populations that health officials should be aware of, he says.
"Where humans can easily get distracted," he says, "we can have a machine continuously keeping an eye on everything else that's going on."
Like this story? Subscribe to CNBC Make It on YouTube!
Don't miss:
