Smartphone data reveals link between fast food outlets and diet-related diseases

How many fast-food joints do you encounter throughout the day and what does this have to do with your health? Too muchsays Abigail Horn, a leading scientist at USC’s Information Sciences Institute (ISI).

Horn led a multidisciplinary team that included researchers from three USC schools in Turkey (Viterbi School of Engineering; Dornsife College of Letters, Arts, and Sciences; and Keck School of Medicine), MIT, and Sabancı University; and worked in collaboration with the LA County Department of Public Health. They set out to determine whether smartphone mobility (i.e. location) data could provide a way to measure the dynamic food environments experienced by individuals across large and diverse populations and a variety of physical environments.

The question was: Can we use mobility data to measure people’s visits to food outlets? Because that’s a good indicator of eating at that store. “And then, can we go one step further and see whether visits to food outlets observed in mobility data are predictive of people’s rates of diet-related disease?”

Abigail Horn, principal scientist at the USC Information Sciences Institute

Location, location, location

“It is well established that the physical environment can influence people’s eating decisions and therefore diet-related health outcomes, but we do not know to what extent this is true,” said Research Assistant Professor Horn. Daniel J. Epstein, USC Viterbi School of Engineering, Department of Industrial and Systems Engineering.

Physical food environments are the actual spaces where people obtain food. “Food outlets in their neighborhood, around their workplace, or anywhere along their daily commute. Things like grocery stores, restaurants, or corner markets,” Horn explained.

These environments have been shown to affect people’s diets and therefore their health outcomes, including diet-related diseases, in a variety of ways. First, Horn said: “When people have low physical access to healthy foods, this can lead to unhealthy choices out of convenience or necessity.” Second, “People can take cues from their food environment. For example, if you see fast food restaurants repeatedly throughout the day, this may signal or trigger certain behaviors” (e.g., eating more fast food).

There are numerous studies examining the food environments in people’s homes and relating them to food choices and diet-related diseases. But the findings are mixed, as are the results of public health initiatives focused on food environments in home neighborhoods.

“Over the last decade, more than a billion dollars have been invested in public health interventions for home food environments. This could mean building a grocery store in a food desert,” Horn explained. [a home neighborhood with limited access to nutritious food] or stocking that neighborhood corner store with fresh fruits and vegetables.” But he continued: “There was no measurable impact on increasing people’s healthy food purchases or health outcomes. So what’s going on here?”

Kayla de la Haye is one member of the research team who may help answer this question. De la Haye is Director of the Institute for Food System Equity at the USC Dornsife Center for Economic Research and has a background in public health, nutrition, and psychology. “One of my roles in this research was to provide expertise on how people make decisions about what to eat and the consequences of food environments that flood people with unhealthy options and put them at risk for many diet-related diseases, such as obesity and diabetes.”

Looking beyond the farmer’s market

De la Haye has worked with families in Los Angeles, from Lancaster to the east side of Los Angeles, helping them with strategies to avoid unhealthy foods and adopt healthier eating habits. “So I brought this real-world knowledge of the challenges Angelenos face with healthy eating to our research project,” she said.

The team knew from their own experience and the experiences of the families they worked with in healthy eating programs that people weren’t just eating in their own neighborhoods. But they needed data to prove this on a population scale. “We thought the lack of data showing where people go to eat and where they spend the most time might explain why we didn’t see a relationship between the neighborhood food scene and people’s dietary health outcomes,” Horn said.

So they turned to smartphones for data.

For most of us, our smartphone is always tracking our location, and we probably share that data with various apps. Location data companies collect this data, called “mobility data,” and sell it for advertising purposes. However, it is increasingly being made available for research by organizations such as Spectus.ai through the Social Impact Program from which this study’s data was obtained.

Esteban Moro led the team at MIT that will help access and analyze this data. “Our group has great experience analyzing and using mobility data on problems such as segregation, transportation, urban planning, and business activity,” said Moro, a Research Scientist at MIT Connection Science. “We specialize in turning them into insightful tools for urban problems. So our main role in this research was to provide and analyze population-wide mobility data on food consumption.”

We bring all the data together

Using census block data to indicate Los Angeles County residential neighborhoods and massive mobility data to track daily trajectories, researchers were able to see people’s entire proximity to food outlets throughout the day — their “exposure.”

The team specifically examined fast food outlets because fast food is widely consumed and is strongly linked to disease risk. Using “point of interest” data, they identified fast-food outlets in LA County. They accessed survey data from the LA County Health Department to uncover the health piece of the puzzle.

“The Los Angeles County Health Department conducts a health survey of the Los Angeles population every three years. We established a collaboration with them and they were able to share with us anonymized individual data regarding socio-demographics, obesity rates, diabetes rates, and personal data that is very representative of the LA population.” One example is frequency of fast food intake,” Horn said.

Researchers analyzing the data confirmed that the neighborhood you live in matters when it comes to your risk of diet-related diseases; But your commute to work, the route you take to carry out your daily business, and how you get from point A to point B are equally important. and the path in your day to point Z and what those points are.

Results?

“We know there is a relationship between visits to fast-food outlets and fast-food intake, as well as between fast-food intake and diet-related diseases, but wow, this data source does a really good job of capturing that!” said Horn.

Moro explained: “The most surprising result was that the mobility data worked like an ‘honest signal’, meaning that visits to fast-food outlets were a better predictor of individuals’ obesity and diabetes than their self-reported fast food intake of other known risks.”

De la Haye emphasized: “This study shows that large-scale mobility data is actually a valuable indicator of where and what people eat and their risk of diet-related disease.”

Why is this so important?

De la Haye explained: “It’s really hard to measure what people eat. In fact, many major public health surveys and surveillance tools have stopped asking people about their food intake because the data is often unreliable (in part because people often forget the details of what they eat) and also because researchers “Because they don’t always want to say they make less healthy food choices. This gives us a new tool to track dietary patterns, such as eating fast food, for large populations, such as residents of city districts or the entire country.”

What’s next?

“What excites me as a researcher is that this opens up mobility data for all kinds of research on the food environment,” Horn said. “Things like: Where do people get food at different times of the day? Who are these people? What are the choices they’re given (or not)?” Horn said. “We can really investigate this with big mobility data because it allows us to look at eating behaviors in broad new dimensions: across the population, across different population groups across the board, across different environmental environments, and over long periods of time.”

De la Haye underlines the importance of this: “Data on the dietary habits of the population is a powerful tool needed to establish public health programs and policies and ultimately reduce health risks from unhealthy diets, which are one of the leading causes of disease and death in the United States.”