This article is more than 5 years old. Information may no longer be current.
Social media predicted Disneyland measles outbreak 2 years earlier
Click Here to Manage Email Alerts
Using artificial intelligence and a mathematical model to examine Google searches and geocoded tweets, researchers said they could detect signals in data from California that predicted the 2014-2015 Disneyland measles outbreak 2 years before it happened.
Chris T. Bauch, PhD, professor of applied mathematics at the University of Waterloo in Canada, and colleagues said their method can be used to anticipate “tipping points” in vaccine scares — or intensified resistance to vaccination — that may precipitate an infectious disease outbreak.
Their findings were published this week in the Proceedings of the National Academy of Sciences of the United States of America.
“What this study tells us is that the same mathematical theories used to predict tipping points in phenomena such as changing climate patterns can also be used to help predict tipping points in public health,” Bauch said in a news release. “By monitoring people’s attitudes toward vaccinations on social media, public health organizations may have the opportunity to direct their resources to areas most likely to experience a population-wide vaccine scare and prevent it before it starts.”
In their study, Bauch and colleagues write that vaccine refusal “can lead to renewed outbreaks of previously eliminated diseases and even delay global eradication.” Vaccine refusal has frequently been linked to infectious disease outbreaks, including a recent measles outbreak in Minnesota that was fueled by antivaccine rhetoric. A surge in European measles cases has been blamed on gaps in vaccination coverage.
For their study, Bauch and colleagues collected and geocoded tweets about the measles-mumps-rubella vaccine, using machine-learning algorithms to classify their sentiment, and extracted data on measles-related Google searches. They identified warning signs from California that signaled a tipping point 2 years before the outbreak. Other signals correctly predicted that people’s fears about the disease would move the population away from the tipping point and make vaccination more favorable, bringing the outbreak to an end.
“Knowing someone is a smoker cannot tell us for sure whether someone will have a heart attack, but it does tell us that they have increased risk of heart attack,” Bauch explained. “In the same way, detecting these early warning signals in social media data and Google search data can tell us whether a population is at increased risk of a vaccine scare, potentially years ahead of when it might actually happen. With the ability to predict these areas where immunity is most at risk due to behavioral factors, we may be able to help eradicate diseases such as measles and polio.” – Gerard Gallagher
Disclosures: The authors report no relevant financial disclosures.
Click Here to Manage Email Alerts