Of 120,000 individuals hospitalized in the U.S. annually for food poisoning, about 3,000 die. What if there was a way to track these outbreaks in real time to prevent further illness and death? A National Science Foundation-backed app called nEmesis is hard at work doing just that.
nEmesis takes advantage of the habit that food poisoned-individuals have of taking to Twitter to express their dismay and frustration both about their condition and the restaurants they suspect caused the incident. The app mines tweets to identify those related to instances of food poisoning and cross-references them with geotags to identify hot spots and even specific restaurants where people might be getting sick.
Sign up for our FREE E-Weekly for more coverage like this sent to your inbox!
The team that developed the app tested it in Las Vegas and presented their findings at the 30th Association for the Advancement of Artificial Intelligence conference in Phoenix last month. Most cities randomly decide which restaurants to inspect on a given day, but the team hoped to use a more targeted approach by providing Las Vegas health inspectors with locations they suspected were the source of food poisoning outbreaks.
The system produced an increase in citations issued for health violations in restaurants from 9 percent to 15 percent, according to the researchers.
"This happens to be restaurants, but the method can also be used for bedbugs," Adam Sadilek, a researcher involved with nEmesis who now works with Google, said in a statement. "Similarly, you can look what people tweet about after they visit their doctor or hospital. We're just beginning to scratch the surface of what's possible."