AI Can Help Manage Coronavirus
What is becoming clear about the coronavirus situation is it will not be contained. The question is what to do about it. The answer requires knowing where the virus will spread and when. The good news is artificial intelligence (AI) can provide answers now, and even more accurately in the future.
Dr. Kamran Khan, a 49-year-old Canadian epidemiologist and infectious disease specialist in Toronto, was working at a hospital during the SARS epidemic of 2003. The SARS virus started in provincial China and spread to Hong Kong and then to Toronto, where it killed 44 people. Khan concluded there must be a better way to track diseases. With that goal in mind, Khan founded a company in 2014 called BlueDot.
BlueDot has developed an algorithm that can sift through hundreds of thousands of news stories and airline traffic information everyday. The goal is to detect and monitor the spread of infectious diseases. BlueDot applies AI technologies to create alarms about impending virus attacks. Its first success was accurately predicting the spread of Zika from Brazil to south Florida in 2016. Early on, it predicted the spread of coronavirus on December 31, 2019.
BlueDot has 40 employees including data scientists, epidemiologists, physicians, veterinarians, and software developers. Using natural language processing and machine learning, the BlueDot team has developed a real-time warning system based on the vast amount of data it analyzes. The data is retrieved every 15 minutes around the clock from scans of official reports, online news sources, professional forums and information retrieved from key word and phrase searches.
The Economic Times reported BlueDot, “Can read text in 65 languages and can track 150 different types of diseases.” Mr. Khan told The Times, “We call it the needles in the haystack”. After the AI software has analyzed the data, it presents the findings to human experts who tag information they believe is related to a threat.
“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 AI to understand if the information corresponds to an actual threat. The Times reported, “If the threat looks real, the AI software then looks further for nearby airports and commercial air travel itineraries from around the world. Climate data, national health system databases, and even the presence of mosquitoes or animals that transmit diseases to humans are all taken into account.”
Once BlueDot is confident it has valid data, it sends an alert to its clients including airlines, hospitals, and government agencies informing them where the majority of the airline passengers might disembark. The recipients of the alerts can then prepare for a major disease outbreak.
The Times reported, “So on December 31, in the early morning, the BlueDot system picked up an article in Mandarin that mentioned 27 people suffering from pneumonia, all linked to a wet market in Wuhan.” The virus was not yet identified but the data contained some similarities to the SARS outbreak. BlueDot AI technology predicted the virus would likely spread from Wuhan to Bangkok, Hong Kong, Singapore, Taipei, and Tokyo, all of which have since reported cases of the novel coronavirus.
Other startup companies, government laboratories, Harvard Medical School, and numerous other centers of excellence are using AI to study massive amounts of data. They are using tools which were not available ten years ago. AI is being used to examine large numbers of chemical molecules to determine if they might be therapeutic toward coronavirus. Long term, it is likely there will be new diseases appearing. The good news is AI is getting smarter and smarter every day, and will eventually be able to predict outbreaks earlier and develop cures and vaccines much more quickly than is currently possible.