The RTI Rarity™ Project: Next-Generation Health Equity Measurement & Analysis
Gathering deep insights into communities from advanced data science methods and geospatial analytics
Public health officials at the federal and state levels have called for a better way to measure, predict, and adjust for social factors in health care and population health. The RTI Rarity project takes an “artificially intelligent” approach to inform decisions concerning community-level social, behavioral, environmental, and economic factors for quality health care. By curating a national database of more than 200 area-level social determinants of health (SDoH) measures within ten domains at the Census tract, ZIP code, and county levels across the U.S., the RTI Rarity tool provides high-resolution insights into factors that strongly influence health outcomes.
The RTI Rarity tool uses supervised machine learning, including random forests and other state-of-the-art predictive methods, to create local social inequity (LSI) scores drawing on the SDoH measures. The health equity analysis tool and its underlying data allow for the development of both within-state and cross-state summary scores and ten domain-specific sub scores informed by our conceptual framework. The scores yield meaningful insights into the neighborhood-level factors driving local health outcomes.
Download the RTI Rarity Overview
View the RTI Rarity conceptual framework and learn more about the health data used in the RTI Rarity tool that come from 38 different publicly available federal, state, and nonprofit/academic resources, including the American Community Survey, USDA’s Food Environment Atlas, CDC’s Wide-ranging ONline Data for Epidemiologic Research (WONDER), HUD, Child Opportunity Index, Opportunity Atlas, and more.
The Impact of LSI Scores on Health Equity
The RTI Rarity LSI scores have been benchmarked against three existing area-based composite measures related to SDoH: the Area Deprivation Index (ADI), the Social Deprivation Index (SDI), and the Social Vulnerability Index (SVI). In terms of life expectancy at birth, the LSI leads in explaining 67% of the variance across the US, whereas the SVI only explains 26%, the SDI explains 29%, and the ADI explains 43%. In other words, the LSI measure accounts for substantially more of the disparity between the neighborhoods with the highest and lowest life expectancies across the U.S.
The RTI Rarity LSI scores can also be linked with individual-level data to improve predictions of individual outcomes. In population-based analyses, these scores can be used to:
- understand the impact of health care innovations, payment models, and interventions on SDoH in high-risk communities;
- identify neighborhoods and areas at highest risk of poor outcomes for better targeting of interventions and resources;
- account for factors outside of providers’ control for more fair and equitable performance/quality measurement and reimbursement.
Improving Health Equity and Outcomes via RTI Rarity LSI Scores
With the data LSI scores provide, organizations can draw insights to inform factors that can strongly influence and improve health outcomes. The RTI Rarity project merges AI and data science in a risk adjustment framework with high-resolution SDoH data, all through a health equity lens. We aim to provide the local context that will enable researchers, policy makers, and health care systems to better account for, and address, SDoH across the life course.
The RTI Rarity Dashboard
Explore all four of our current risk scores—including, Local social inequity in Life Expectancy (LSI-LE) scores, Local social inequity in cancer mortality (LSI-Ca) scores, Local social inequity in drug overdose (LSI-DO) scores, and Local social inequity in sexual and reproductive health (LSI-SRH) scores—along with other information such as the locations of Title X family planning clinics and substance use recovery resources.
The RTI Rarity Tool on the Healthy Intersections Podcast (HIP)
HIP, August 2023 | The Drug Overdose Epidemic
In this episode of HIP, Dr. Lisa Lines, Dr. Amanda Onwuka from RTI International, and Jeremy Ney, author of American Inequality, talk about mental health, opioid prescribing rates, and multi-level interventions to prevent addiction and overdose. (This podcast was originally published on The Medical Care Blog.)
HIP, July 2023 | RTI Rarity Interactive State Map: Florida
In this episode of HIP, Dr. Lisa Lines and Lauren Pierce, a public health consultant who previously worked with the Florida Department of Health for 15 years, use the RTI Rarity tool to look at Local Social Inequity in Life Expectancy scores for Leon County, FL, where the state capitol, Tallahassee, is located. (This podcast was originally published on The Medical Care Blog.)
HIP, May 2023 | RTI Rarity Interactive State Map: Oklahoma
On this episode of HIP, Dr. Carol Schmitt and Dr. Lisa Lines look at the Rarity interactive map for Oklahoma to discuss how local-social inequity (LSI) scores for specific communities, including tribal nations, compare to larger state averages to highlight the importance of these county-level data. (This podcast was originally published on The Medical Care Blog.)
HIP, April 2023 | RTI Rarity Interactive State Map: Illinois
The April episode of HIP, sponsored by the American Public Health Association’s Medical Care Section and hosted on The Medical Care Blog, discusses the local-social inequity and life expectance (LSI-LE) scores of several areas in Illinois based on the interactive Rarity map with experts Dr. Carol Schmitt and Dr. Lisa Lines.