CAMBRIDGE, MA—Infectious disease outbreaks often have consequences beyond the numbers of people who become sick, including an anxious population, economic instability and sometimes even outbreaks of violence. Using social media, Draper engineers have laid the groundwork for a near real-time warning system that can identify the social response—and in severe epidemics, the panic—associated with disease outbreaks.
“When you can predict the social effects of an epidemic, you can be more aggressive in your prevention strategy,” said Natasha Markuzon, Ph.D., a Principal Member of the Technical Staff in Draper’s Information and Cognition group. “A warning system to anticipate the social consequence of epidemics could help public health decision makers and relief workers to better allocate resources and improve responses.”
Extreme panic responses can hamper the responders’ ability to combat the disease, or even result in violent attacks against health workers, as recently observed with the Ebola epidemic in West Africa and in various conflicts around the globe as reported in the International Journal of Health Policy and Management. Ultimately, severe disease outbreaks can affect national security.
Social media and news data streams are increasingly used to forecast events ranging from election results and financial market fluctuations to urban crime and civil unrest. Draper’s model reviewed internet-based sources of information on disease epidemics to provide forecasts of the social response.
The model, described in the journal Annals of Operations Research, evaluated primary data from HealthMap. In operation since 2006, HealthMap aggregates epidemic intelligence from multiple data sources, including online news, social media, crowdsourced intelligence and formal reports from health agencies. Markuzon and her team developed the near real-time data-driven model using HealthMap’s data on 16 different diseases in 72 locations around the world, ranging from measles in Australia to cholera in Cuba.
Previous analysis of infectious disease outbreaks has shown that severe social responses happen most frequently when pathogens are clinically severe or are unfamiliar to local experts. Countries with low levels of health care spending and high levels of armed conflict and child mortality may be especially susceptible.
Draper’s work expanded on that, showing that internet-based news is a good data source for predicting social responses several weeks in advance of outbreak of an epidemic, especially when the outbreak is covered extensively in online media. By identifying ongoing social response and alerting decision makers and biosurveillance experts to probable social response in the near future, this warning system can provide responders with the information they need to both combat the disease and its potential social impact.
The research on social response to infectious diseases reflects Draper’s deep understanding of modeling and machine learning. Draper has developed applications ranging from detecting online terror networks to predicting cognitive decay in Alzheimer’s disease.
Draper has continued to advance the understanding and application of human-centered engineering to optimize the interaction and capabilities of the human’s ability to better understand, assimilate and convey information for critical decisions and tasks. Through its Human-Centered Solutions capability, Draper enables accomplishment of users’ most critical missions by seamlessly integrating technology into a user’s workflow. This work leverages human-computer interaction through emerging findings in applied psychophysiology and cognitive neuroscience. Draper has deep skills in the design, development, and deployment of systems to support cognition – for users seated at desks, on the move with mobile devices or maneuvering in the cockpit of vehicles – and collaboration across human-human and human-autonomous teams.
Draper combines specific domain expertise and knowledge of how to apply the latest analytics techniques to extract meaningful information from raw data to better understand complex, dynamic processes. Our system design approach encompasses effective organization and processing of large data sets, automated analysis using algorithms and exploitation of results. To facilitate user interaction with these processed data sets, Draper applies advanced techniques to automate understanding and correlation of patterns in the data. Draper’s expertise encompasses machine learning (including deep learning), information fusion from diverse and heterogeneous data sources, optimized coupling of data acquisition and analysis and novel methods for analysis of imagery and video data.