Are computers better than epi at identifying foodborne illness? Gumshoes will always be needed

A new computer model that uses machine learning and de-identified and aggregated search and location data from logged-in Google users was significantly more accurate in identifying potentially unsafe restaurants when compared with existing methods of consumer complaints and routine inspections, according to new research led by Google and Harvard T.H. Chan School of Public Health. The findings indicate that the model can help identify lapses in food safety in near real time.

“Foodborne illnesses are common, costly, and land thousands of Americans in emergency rooms every year. This new technique, developed by Google, can help restaurants and local health departments find problems more quickly, before they become bigger public health problems,” said corresponding author Ashish Jha, K.T. Li Professor of Global Health at Harvard Chan School and director of the Harvard Global Health Institute.

The study will be published online November 6, 2018 in npj Digital Medicine.

Foodborne illnesses are a persistent problem in the U.S. and current methods by restaurants and local health departments for determining an outbreak rely primarily on consumer complaints or routine inspections. These methods can be slow and cumbersome, often resulting in delayed responses and further spread of disease.

To counter these shortcomings, Google researchers developed a machine-learned model and worked with Harvard to test it in Chicago and Las Vegas. The model works by first classifying search queries that can indicate foodborne illness, such as “stomach cramps” or “diarrhea.” The model then uses de-identified and aggregated location history data from the smartphones of people who have opted to save it, to determine which restaurants people searching those terms had recently visited.

Health departments in each city were then given a list of restaurants that were identified by the model as being potential sources of foodborne illness. The city would then dispatch health inspectors to these restaurants, though the health inspectors did not know whether their inspection was prompted by this new model or traditional methods. During the period of the study, health departments continued to follow their usual inspection procedures as well.

In Chicago, where the model was deployed between November 2016 and March 2017, the model prompted 71 inspections. The study found that the rate of unsafe restaurants among those detected by the model was 52.1% compared with 39.4% among inspections triggered by a complaint-based system. The researchers noted that Chicago has one of the most advanced monitoring programs in the nation and already employs social media mining techniques, yet this new model proved more precise in identifying restaurants that had food safety violations.

In Las Vegas, the model was deployed between May and August 2016. Compared with routine inspections performed by the health department, it had a higher precision rate of identifying unsafe restaurants.

When the researchers compared the model with routine inspections by health departments in Las Vegas and Chicago, they found that the overall rate across both cities of unsafe restaurants detected by the model was 52.3%, whereas the overall rate of detection of unsafe restaurants via routine inspections across the two cities was 22.7%.

The study showed that in 38% of all cases identified by this model, the restaurant potentially causing foodborne illness was not the most recent one visited by the person who was searching keywords related to symptoms. The authors said this is important because previous research has shown that people tend to blame the last restaurant they visited and therefore may be likely to file a complaint for the wrong restaurant. Yet clinically, foodborne illnesses can take 48 hours or even longer to become symptomatic after someone has been exposed, the authors said.

The new model outperformed complaint-based inspections and routine inspections in terms of precision, scale, and latency (the time that passed between people becoming sick and the outbreak being identified). The researchers noted that the model would be best leveraged as a supplement to existing methods used by health departments and restaurants, allowing them to better prioritize inspections and perform internal food safety evaluations. More proactive and timely responses to incidents could mean better public health outcomes. Additionally, the model could prove valuable for small and mid-size restaurants that can’t afford safety operations personnel to apply advanced food safety monitoring and data analysis techniques.

“In this study, we have just scratched the surface of what is possible in the realm of machine-learned epidemiology. I like the analogy to the work of Dr. John Snow, the father of modern epidemiology, who in 1854 had to go door to door in Central London, asking people where they took their water from to find the source of a cholera outbreak. Today, we can use online data to make epidemiological observations in near real-time, with the potential for significantly improving public health in a timely and cost-efficient manner,” said Evgeniy Gabrilovich, senior staff research scientist at Google and a co-author of the study.

Topeka changes name to Google, Kansas, in bid to win new fiber cables

I’ve been to Truth or Consequences, New Mexico. Amy and I were driving south through NM on our way to Tuscon, Arizona, and had to pee, so why not in a town that changed its name to honor the NBC radio program in 1950. We stopped in at the local historical society or museum, and were endlessly asked if we were going to stay overnight.

No. Where’s the bathroom.

Topeka, the state capital of Kansas, has changed its name to Google, Kansas, for a month, in hopes to get some new fiber optic cables to replace the stagecoaches.

The unusual move comes as several U.S. cities elbow for a spot in Google’s new "Fiber for Communities" program. The Web giant is going to install new Internet connections in unannounced locations, giving those communities Internet speeds 100 times faster than those elsewhere, with data transfer rates faster than 1 gigabit per second.

As 79-year-old Topeka mayor, Bill Bunten, told CNN, the name change will not be permanent, adding,

"Oh, heavens no, Topeka? We are very proud of our city and Topeka is an Indian word which means ‘a good place to grow potatoes.’ We’re not going to change that."

Do people grow potatoes in Topeka these days?

"I don’t think we grow that many potatoes anymore. The crops we have out here are wheat and corn and soybeans and alfalfa. And, did I say soybeans?"

He’s the first to say outsiders probably view Topeka as "another Midwestern town with not a lot going on," but he’s been making efforts to change that. He’s trying to revitalize downtown with a bar and music scene.

Google would add to all that, making the city more attractive to youngsters, he said.

Now if Manhattan (Kansas) will officially change its name to (Little) Apple, maybe we’ll all get free iPhones.

H1N1=wash your hands

Doug introduced me to Google Alerts a few weeks ago and my email inbox hasn’t been the same since. I get approximately 50-100 email hits on handwashing everyday. Most of them are relevant to washing hands, but some are about handwashing clothes and dishes.

The reason for sharing my numerous emails: wash your hands.

The World Health Organization (WHO) recently announced raising the alert level to phase 6, the pandemic phase. The severity of the virus, H1N1, is moderate, claims the WHO. Across the world there are newly suspected cases of so-called swine flu. In the US alone, there have been 17,800 confirmed cases, 1600 hospitalized, and 44 deaths; all are attributed to H1N1 flu.

Every reported case in the news or other blogs is typically accompanied with a campaign for their readers to wash their hands. I, of course, couldn’t pass up the opportunity to inform BarfBlog readers to do the same.

Handwashing can reduce sickness by an estimated 25%. Hands should be washed before and after handling food, using the bathroom, coughing, sneezing, and blowing ones nose. Also, people should avoid touching their face (eyes, nose, and mouth) to reduce their risk.

Google Flu Trends – early warning system for foodborne illness outbreaks?

Google Flu Trends is a new Web tool that Google.org, the company’s philanthropic unit, unveiled on Tuesday, just as flu season was getting under way in the United States.

The N.Y. Times reports that Google Flu Trends is based on the simple idea that people who are feeling sick will probably turn to the Web for information, typing things like “flu symptoms” or “muscle aches” into Google. The service tracks such queries and charts their ebb and flow, broken down by regions and states.

Early tests suggest that the service may be able to detect regional outbreaks of the flu a week to 10 days before they are reported by the Centers for Disease Control and Prevention.

We’ve thought of doing something like this with surveillance of foodborne illnesss, or even restaurant inspection and complaints. But we don’t have the resources of Google.

Google Flu Trends (www.google.org/flutrends) is the latest indication that the words typed into search engines like Google can be used to track the collective interests and concerns of millions of people, and even to forecast the future.