The Chicago Department of Public Health (CDPH) has developed an innovative strategy to rapidly identify foodborne illness outbreaks and locate their sources. The approach involves collaboration between public health professionals and the public, via social media.
The CDPH launched FoodBorne Chicago, which tracks Twitter messages using a supervised learning algorithm. The algorithm parses tweets originating from Chicago that include “food poisoning” to identify specific instances of persons with complaints of foodborne illness.
The open-source app then responds to the person who sent the original tweet, saying, “That doesn’t sound good. Help us prevent this and report where you ate,” and includes a link to an online form for reporting the details.
The efficacy of the technology is described by Jenine K. Harris et al. in an article published August 15 in the Morbidity and Mortality Weekly Report, published by the US Centers for Disease Control and Prevention.
Harris et al. reported that since the project was initiated in March 2013, FoodBorne Chicago staff members have responded to 270 Tweets. A total of 193 complaints were then submitted through the website, leading to unannounced health inspections at 133 restaurants. Of these, 21 (15.8%) failed inspection and were closed, while 33 (24.8%) passed with conditions indicating critical or serious violations. Eight tweets and 19 complaint forms to FoodBorne Chicago described individuals seeking medical treatment.
Harris et al. conclude that social media and other technologies can be used by health departments to engage with the public to improve foodborne illness surveillance. The New York City Department of Health and Mental Hygiene currently screens online restaurant reviews to identify foodborne illness complaints.
“We know that the majority of cases of foodborne outbreaks really never end up getting reported to the local health department anywhere in the country,” study co-author Bechara Choucair told Reuters.
“People might not pick up the phone and call the doctor, but they might go to Twitter and complain to the world that they got food poisoning from eating out,” he said.
Ben Chapman, a food safety researcher at North Carolina State University who was not involved in the study, told Reuters “I think it’s really progressive of health departments to start looking at signals online to figure out where to put their resources.” He added that it is important to focus on identifying outbreaks that are not detected by hospitals or reportable disease databases.
Chapman says there is a movement for health departments to integrate their inspection reports directly into websites like Yelp, so that people can take that information into consideration when they’re searching for restaurants. For developers who would like to contribute to the open-source software, it is available on GitHub.