In the chaos the coronavirus has unleashed on our world, a news story about a Canadian start-up completely captivated the data analyst in me.
On 31 December 2019, the start-up sent an alert to clients warning of a mystery virus emerging from the Chinese city of Wuhan. It further went on to correctly predict many of the countries that are most at risk.
Bearing in mind that the alert came days before major health authorities started releasing official statements, the enormity of what BlueDot accomplished becomes clear.
BlueDot is the brainchild of 49-year-old Kamran Khan, an epidemiologist by training, who first had the idea to launch BlueDot after the SARS epidemic of 2002-03.
The company has developed an artificial intelligence (AI)-powered system that combs through data on animal and plant disease networks, news reports Web sites in 65 languages, available government documents and a myriad of other online sources. Using machine learning and natural language processing techniques, large amounts of data are incorporated, in real-time, with air traffic information. This allowed the company to correctly highlight those countries most at risk in the initial days of the pandemic.
That got me thinking about how else data may be used to effectively fight this disease and others like it.
As the largest social media platform in the world, Facebook has access to unprecedented amounts of personal information. Together with researchers at Harvard University's School of Public Health and the National Tsing Hua University, in Taiwan, Facebook is sharing anonymised data about people's movements. Combined with high-resolution population density maps, this is helping researchers forecast the spread of the virus.
Right from the start, those in authority in Taiwan understood the importance of being able to track and trace.
Taking it one step further, the social network is also helping partners understand how people are talking about the issue online, via tools such as Crowdtangle.
Crowdtangle is a content discovery and social monitoring platform which tracks how content spreads around the Web.
Taiwan sits just 130km off the coast of mainland China and shuttles thousands of passengers to and from the mainland daily. Primarily due to its proximity to China, computer scientists modelling the outbreak ranked Taiwan the region with the second highest risk of importation of the virus. However, as of 11 March, fewer than 50 cases of the coronavirus had been confirmed on the island. Compare this to South Korea, which had confirmed nearly 8 000 cases.
Right from the start, those in authority in Taiwan understood the importance of being able to track and trace. Chih-Hung Jason Wang, director of the Centre for Policy, Outcomes and Prevention at Stanford University, said Taiwan was able to stop a lot of the transmission early due to a “very detailed mapping of who got it from whom”.
Many countries have been caught entirely on the back foot though. No one fully expected or understood the power and contagiousness of this disease. As such, many healthcare systems are under enormous strain. Not enough beds, not enough staff, not enough of the equipment needed to give lifesaving help.
So how can data, analysis, algorithms and AI help humanity?
Google’s DeepMind division has been using the latest AI algorithms and its computing power to understand the proteins that might make up the virus. BenevolentAI also uses AI systems to build drugs that can fight the world’s toughest diseases. Within weeks of the outbreak, both resources were successfully utilising its predictive capabilities to propose existing drugs that might be useful.
Controversially, China’s sophisticated surveillance system used facial recognition technology and temperature detection software from SenseTime to identify people who might have a fever and be more likely to have the virus.
The cloud computing resources and supercomputers of several major tech companies such as Tencent, DiDi and Huawei are being used by researchers to fast-track the development of a cure or vaccine for the virus. The speed these systems can run calculations and model solutions is much faster than standard computer processing.
In a global pandemic such as COVID-19, technology, AI and data science have become critical to helping societies effectively deal with the outbreak.
On a more personal note, there is a saying: “May you live in interesting times.” Quite often used as a curse, I think in this instance it is both a curse and a blessing. Our world faces huge health and economic uncertainty. The nature of humanity is to either rise above or descend into chaos. I hope we rise above. With compassion and empathy. See you all on the other side of this.
Share