Seminars and Events

Artificial Intelligence Research for Health

Using Large-Scale Mobility Data To Investigate Population Eating Behaviors and Nutritional Health

Event Details

Poor diets, including those high in fast food, are a leading cause of morbidity and mortality. Exposure to low-quality food environments, such as ‘food swamps’ saturated with fast food outlets (FFO), is hypothesized to negatively impact diet and related disease. However, research linking such exposure to diet and health outcomes has generated mixed findings and led to unsuccessful policy interventions. Furthermore, despite over $1B in investments by federal and local governments, policy interventions to improve food environment quality have failed to demonstrate meaningful impacts on health. A major research limitation has been a predominant focus on static food environments around the home, such as food deserts and swamps, and sparse availability of information on dynamic food environments people are exposed to and food outlets they visit as they move throughout the day. In this work, we leverage population-scale mobility data to examine peoples’ visits to food outlets and FFO in and beyond their home neighborhoods. First, we show that visits to FFO in mobility data provide strong and significant indicators of FF intake and diet-related disease by linking area-based measures of FFO visits to respondents from a health survey of a representative sample of Los Angeles County adults providing self-reported measures of FF intake, obesity, and diabetes. Second, focusing on the mobility data alone, we develop a semi-causal framework using several natural experiments to evaluate how food choice is influenced by features of food environments people are exposed to in their daily routines vs. individual preference. We find that 10% more FFO in an area an individual spends time in (including and beyond the home) increases their odds of visiting a FFO by approximately 20%. This strong influence of the food environment happens similarly during weekends and weekdays and is largely independent of individual income. Using our results, we investigate multiple food environment intervention strategies to promote a reduction in FFO visits. We find that optimal locations for intervention are a combination of where i) the prevalence of FFO is the highest, ii) most decisions about food outlet visits are made, and most importantly, iii) visitors’ food decisions are most susceptible to the environment. Multi-level interventions at the individual behavior- and food environment-level that target areas combining these features could have 1.7x to 4x larger effects than traditional interventions that alter food swamps or food deserts. This is work conducted in collaboration with Esteban Moro and Bernardo Bulle-Bueno, MIT, and Kayla de la Haye, Department of Population and Public Health Sciences, USC.

Speaker Bio

Abigail Horn is a Research Assistant Professor of Industrial and Systems Engineering and Research Lead in the Information Sciences Institute (ISI) at USC, where she is a Co-Director of the AI4Health Center. She previously conducted postdoctoral fellowship training in Health Behavior and Biostatistics in the Department of Population and Public Health Sciences also at USC. She obtained her Ph.D. in Engineering Systems from the Institute for Data, Systems, and Society at MIT and an undergraduate degree in Physics from the College of Creative Studies at the University of California, Santa Barbara. Before coming to USC she completed a joint research fellowship in transport and logistics modeling at the Kuhne Logistics University (Hamburg) and in epidemiology and bioinformatics at the German Federal Institute for Risk Assessment. The general area of her research is the combination of approaches from computational social science, systems modeling, and AI with large-scale data sources to design solutions to pressing public health challenges related to food systems, from food safety to nutrition. Current research includes analyzing big mobility data from smartphones to understand visits to food outlets and impacts on nutritional health, using digital menu data to predict the nutritional quality of restaurant menus, and modeling food supply chain network structure for applications in food borne disease to food security.
YOU ONLY NEED TO REGISTER ONCE TO ATTEND THE ENTIRE SERIES – We will send you email announcements with details of the upcoming speakers.
Register in advance for this webinar: Webinar Registration - Zoom
After registering, you will receive an email confirmation containing information about joining the Zoom webinar.
If speaker approves to be recorded for this AI Seminar talk, it will be posted on our USC/ISI YouTube page within 1-2 business days:
Host: Michael Pazzani, POC: Mable Johnson