It’s a special occasion when your company is mentioned, and positively too, in the halls of the U.S. Congress. That’s what happened to Hypermind on March 5, 2020, when the U.S. House of Representatives Committee on Science, Space, and Technology held hearings on “Coronaviruses: Understanding the Spread of Infectious Diseases and Mobilizing Innovative Solutions“.
Among the experts invited to testify was one of our clients, Dr. Tara Kirk Sell, a senior scholar at the Center for Health Security of the Johns Hopkins Bloomberg School of Public Health. In her opening statement, she briefly described the crowd-forecasting platform that Hypermind developed for her team, and testified to the power of collective intelligence to predict the onset and spread of infectious diseases such as the coronaviruses. Here’s a brief video extract from C-Span (1m47s):
Thank you Dr. Sell, for allowing some of Hypermind’s work to enter into the congressional record! It means a lot to us.
Here’s the transcript of the video above:
Thank you for inviting me to speak about research on crowd-forecasting and misinformation, in the context of Covid-19, and ways to support research that improve outbreak response.
Traditional disease surveillance is critical during infectious disease outbreaks. However this information can be enhanced with tools to support decision-making. One such tool is crowd-forecasting. Crowd-forecasting consolidates the diverse opinions of many into hard probabilities for future outcomes. This is helpful in gauging the most likely outcome, and also for understanding the uncertainty about that outcome.
Over the past year my research team, in partnership with a group called Hypermind, developed a crowdsourced disease-prediction platform and asked forecasters to make predictions about outbreaks.
For instance, we asked about the growth of Ebola in the democratic republic of Congo, the spread of Measles in the United-States, and how many U.S. counties might see cases of Eastern Equine Encephalitis. On most occasions forecasters provided accurate predictions about three weeks ahead of time.
Recently we focused our forecasting platform on Covid-19. We asked about the number of countries that would have cases of Covid-19, and the number of cases that would be seen around the world and in the United-States. For global cases, forecasts showed high confidence that there would be a rapid and explosive spread.
On a few occasions our predictions were incorrect. We think this is probably because forecasters didn’t have enough information to make accurate forecasts. Essentially, there is no magic here. If disease surveillance is lacking or is delayed, forecasters don’t have any information to go on. This underscores an essential research need for the current Covid-19 outbreak: that surveillance both within the united-states and globally is essential.
