Skip to Main Content
An official website of the United States government

Reevaluating the Use of Race and Ethnicity in Medical Risk Assessments

Principal Investigator

Name
Sharad Goel

Degrees
B.S., M.S., Ph.D.

Institution
Harvard University

Position Title
Professor of Public Policy

Email
sgoel@hks.harvard.edu

About this CDAS Project

Study
NLST (Learn more about this study)

Project ID
NLST-1121

Initial CDAS Request Approval
Sep 5, 2023

Title
Reevaluating the Use of Race and Ethnicity in Medical Risk Assessments

Summary
There is active debate over whether to consider patient race and ethnicity when estimating disease risk. By accounting for race and ethnicity, it is possible to improve the accuracy of risk predictions, but there is concern that their use may encourage a racialized view of medicine. In diabetes risk models, despite substantial gains in statistical accuracy from using race and ethnicity, the gains in clinical utility are surprisingly modest. These modest clinical gains stem from two empirical patterns: first, the vast majority of individuals receive the same screening recommendation regardless of whether race or ethnicity are included in risk models; and second, for those who do receive different screening recommendations, the difference in utility between screening and not screening is relatively small. Our results are based on broad statistical principles, and we believe they are likely to generalize to many other risk-based clinical decisions. Building off our past work on the use of race and ethnicity in diabetes risk assessments, we are interested to see if and how and the clinical utility of race-aware risk assessments varies with new diseases, such as lung cancer.

Aims

- To replicate existing models used to estimate risk of lung cancer (we will train models that use race and ethnicity and others that do not)
- To use the race-aware and race-unaware lung cancer risk predictions to make hypothetical screening decisions for patients in the data
- To use these decisions in conjunction with the observed lung cancer outcomes in the data to derive an estimate of the clinical utility of each model
- Compare the clinical utility of a race-aware and a race-unaware model for lung cancer

Collaborators

Madison Coots, Harvard University
Soroush Saghafian, Harvard University
David Kent, Tufts University
Sharad Goel, Harvard University

Related Publications