Project Will Create First Digital Health Dataset That Includes Traditionally Underrepresented Groups
July 28, 2020
An initiative to create the first large-scale digital health dataset of Americans that is fully representative across all socio-demographic groups—including ethnic and economic groups usually underrepresented—has been launched by the University of Southern California Schaeffer Center for Health Policy & Economics, the RAND Corporation, and Evidation Health.
The ultimate goal of the project is to use digital technologies to create precision public health interventions that will focus on reducing health disparities among underrepresented populations—including racial-ethnic minorities and those who are socioeconomically disadvantaged—by focusing on their unique needs.
“Leaving out a large portion of the population in these studies inevitably leads to the creation of health disparities,” said Ritika Chaturvedi, the study's principal investigator. “Creating this novel panel assures that underrepresented groups are fully represented as digital health studies go forward.”
Chaturvedi is a research scientist at the USC Schaeffer Center and an adjunct policy researcher at RAND.
The project will enroll a nationally representative sample of individuals from an existing survey panel and provide them with Fitbit devices that will collect information on items such as physical activity, sleep and heart rate. Participants also will take monthly surveys about health-related topics.
In addition, the researchers will couple this data with Evidation's Achievement network to develop generalizable data science methodologies that account for all socio-demographic groups, including the historically underserved.
The project, called the the American Life in Real-time dataset (ALiR), is supported by a $1.2 million, four-year grant from the National Institutes of Health and will initially focus on identifying disparities related to sleep health.
Information collected by internet-enabled devices such as fitness trackers and smart watches increasingly are being used to study the public's health, but thus far such information only has been collected from people who purchase the devices on their own. Those people tend to be younger, healthy, affluent and female.
“Our goal is to understand how different populations have different health behaviors and experience different social determinants of health,” said Wendy Troxel, a RAND senior behavioral scientist and member of the research team. “With that information we hope to create precision public health interventions that meet individual needs, rather than relying on our current one-size-fits-all approach.”
The digital health project intends to enroll several thousand members of the survey panel beginning in early 2021 and collect data over the course of a full year. While the new panel will be nationally representative, it will include an oversampling of participants from underrepresented groups.
This project is supported by the National Library of Medicine of the National Institutes of Health under award number R01LM013237.
The RAND Social and Economic Well-Being division seeks to actively improve the health, and social and economic well-being of populations and communities throughout the world.