How Canadian AI start-up BlueDot spotted Coronavirus before anyone else had a clue
- An AI-based infectious disease surveillance system that searches the world around-the-clock for possible pandemics should have your attention.
On December 30, 2019, BlueDot, a Toronto-based startup that uses a platform built around artificial intelligence, machine learning and big data to track and predict the outbreak and spread of infectious diseases, alerted its private sector and government clients about a cluster of “unusual pneumonia” cases happening around a market in Wuhan, China.
That was the first recognition of the novel coronavirus that has come to be known asCOVID-19. It would be another nine days before the World Health Organization released its statement alerting people to the emergence of a novel coronavirus. As of the date of this story, more than 114,700 cases have been reported worldwide accompanied by more than 4,000 deaths.
How did BlueDot do it?
A little history is important.
When Dr. Kamran Kahn returned to his native Toronto in 2003 after completing his training in infectious diseases, preventive medicine, and public health at Cornell, Columbia, and Harvard, the city was only weeks away from a massive outbreak of Severe Acute Respiratory Syndrome (SARS). As an epidemiologist and practicing physician Kahn immediately found himself on the frontline of an epidemic that went on for six months and killed a total of 774 people in 29 countries. It cost an estimated $40 billion globally, according to the Center for Disease Control.
Said Dr. Kamran in an interview:
It was really an eye-opening experience that demonstrated that our world is rapidly changing. And, inevitably we’re going to be seeing more of these threats in the future…One of the challenges is not just that we are seeing the emergence of new diseases at a pace we’ve never seen before but that we are spreading those diseases around incredibly quickly. Each year, about 4 billion people board commercial flights and travel almost seven trillion kilometers around the globe.That’s about 20,000 round trips to and from the sun. Obviously, we needed better technology if we were going to keep up with the accelerating spread of diseases.
Over the next decade while working as a practicing infectious disease physician and an Associate Professor of Medicine with the Division of Infectious Diseases at the University of Toronto, Khan studied how diseases spread globally and worked to develop better technology to predict, track and mitigate contagious outbreaks.
Bolstered by advances in big data and artificial intelligence, Khan took a “leap of faith” in 2013 and launched BlueDot with the goal of combining public health and medical expertise with advanced data analytics to build the world’s first global early warning system to track and contextualize infectious disease risks.
For assistance, he turned to Toronto Innovation Acceleration Partners (TIAP), a not-for-profit organization (formerly called MaRS Innovation) formed in 2008 through an agreement among 14 of Toronto’s top academic research institutions - including University of Toronto and affiliated teaching hospitals, Ryerson, York, and OICR - to create a vehicle that could provide commercialization traction for their research. Over the last decade, TIAP has established a strong track record by enabling its portfolio companies to raise over $400M and create more than 1,000 direct and indirect STEM jobs in Canada.
How does Bluedot work?
BlueDot is proprietary software-as-a-service designed to locate, track and predict infectious disease spread. The BlueDot engine gathers data on over 150 diseases and syndromes around the world searching every 15 minutes, 24 hours a day. This includes official data from organizations like the Center for Disease Control or the World Health Organization. But, the system also counts on less structured information.
Much of BlueDot's predictive ability comes from data it collects outside official health care sources including, for example, the worldwide movements of more than four billion travelers on commercial flights every year; human, animal and insect population data; climate data from satellites; and local information from journalists and healthcare workers, pouring through 100,000 online articles each day spanning 65 languages.
BlueDot’s specialists manually classified the data, developed a taxonomy so relevant keywords could be scanned efficiently, and then applied machine learning and natural language processing to train the system. As a result, it says, only a handful of cases are flagged for human experts to analyze.
BlueDot sends out regular alerts to health care, government, business, and public health clients. The alerts provide brief synopses of anomalous disease outbreaks that its AI engine has discovered and the risks they may pose.
In the case of COVID-19, the system flagged articles in Chinese that reported 27 pneumonia cases associated with a market that had seafood and live animals in Wuhan. In addition to the alert, BlueDot correctly identified 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 see COVID-19 cases.
COVID-19 was not BlueDot’s first hit. The engine has been used to successfully predict that the Zika virus would spread to Florida in 2016, six months before it happened. The software also determined that the 2014 Ebola outbreak would leave West Africa.
The company 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) and now employs a diverse team of 44 people including veterinarians, doctors, epidemiologists, engineers, data scientists and software developers.
Khan is careful not to claim that AI is the total solution to the problem of infectious disease transmission:
By no means would we claim that AI has got this problem solved. It’s just one of the tools in the toolbox. 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 for further investigation and analysis.
But, as the COVID-19 and the Zika discoveries illustrate, finding that needle is no easy or ordinary feat. BlueDot’s automated infectious disease surveillance platform is an invaluable early warning system that can provide a time critical heads-up to health professionals around the world and potentially save thousands of lives. That, IMHO, is a very good use of AI’s disruptive power.