AI used in COVID-19 Part 2

Another usage of AI during the pandemic is BlueDot. BlueDot is a software service designed to locate, track, and predict infectious disease spread. In the past, BlueDot has been effective in predicting outbreaks of the Zika Virus and Ebola. This year, BlueDot was the first to warn the world of the deadly virus, predicting COVID-19 outbreaks 9 days before the WHO released its statement about the dangers of the then-new virus. Additionally, BlueDot successfully predicted the next 11 cities that the virus would hit.

BlueDot has an engine that gathers data on over 150 diseases around the world, searching every 15 minutes, 24 hours a day. This data can be very structured, coming from official health care sources, but the data gathered also comes from outside of health officials, which gives BlueDot much of its predictability features. BlueDot’s specialists will then manually classify the data, developing a taxonomy so relevant keywords could be scanned efficiently, and then applying machine learning and natural language processing to train the system. As a result, only a handful of cases are flagged for human experts to analyze. When predicting the spread of COVID-19, the system flagged Chinese articles 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. Many of these destinations, as BlueDot predicted, ended up seeing some of the first COVID-19 cases outside of China.

Now, BlueDot’s disease analytics platform is being used to support the modelling and monitoring of COVID-19 in Canada, helping to guide the government in decision-making. Overall, BlueDot is and has been a successful usage of AI in healthcare, especially during this pandemic.