American Heart Association funds four new projects to evaluate the role of race in predicting heart disease risk

People with heart disease may receive different care because of how race is interpreted in health risk calculators and other tools that help clinicians make treatment decisions. The American Heart Association, a global force for healthier lives for all celebrating 100 years of lifesaving service, awarded four new grants this month to support scientific research that will evaluate the use of race in predicting heart disease risk and in turn help develop tools that are free of bias.

The newly funded principal investigators join six previous awardees who are part of a two-year scientific research strategy funded by a grant from the Doris Duke Foundation to study the complex issue of how race and ethnicity factor into clinical care algorithms and risk prediction tools. The grants are $50,000 each.

Clinical algorithms are formulas used to analyze health data and help determine a person's risk for disease or guide their treatment decisions. Age, weight, information from blood or imaging tests, personal health history and health habits -; like physical activity and smoking -; are among the many types of data used by clinical algorithms. Some algorithms include race or ethnicity in their analysis to account for disproportionate disease rates among individuals of certain races or ethnicities. However, there has been growing scientific interest in reconsidering how race is used in risk calculators because race-corrected algorithms can negatively impact patient care and outcomes.

These innovative research projects are focused on testing many different risk models that include a variety of health variables in an effort to remove racial bias from clinical algorithms. Our hope is that this research helps change the discourse about how race is considered in risk calculation."

Jennifer Hall, Ph.D., FAHA, chief of data science for the American Heart Association

The teams of scientists who received funding for the Debiasing Clinical Care Algorithms Data Grants are from Mayo Clinic in Phoenix, Arizona, University of Miami in Florida, University of Washington in Seattle and Boston University in Massachusetts.

The four research projects launched April 1, 2024, and will end March 31, 2025:

  • Fair opportunistic risk estimation model for ASCVD using routine non-contrast chest computed tomography exams – led by Amara Tariq, Ph.D., at Mayo Clinic in Phoenix, Arizona. This study aims to develop a machine learning model to estimate risk of atherosclerotic cardiovascular disease (ASCVD), including stroke and heart attack, using non-contrast computed tomography (CT) imaging of the chest. A deep learning-based pipeline will be developed to derive imaging biomarkers like coronary artery calcium, thoracic aortic calcium, intrathoracic fat and body composition metrics, from chest CT scans. These biomarkers are known to predict the risk of future ASCVD. This study is particularly focused on ensuring that the developed tool is fair and unbiased for all racial subgroups by incorporating adversarial debiasing techniques during model development. The developed model will be evaluated on diverse patient populations from large academic healthcare institutions.
  • Performance of race-based versus non race-based CVD risk calculators in a multi-racial/ethnic sample – led by Robert A. Mesa, M.P.H., a doctoral candidate in epidemiology at the University of Miami in Miami, Florida. This study will assess the American Heart Association's Predicting Risk of CVD EVENTs (PREVENT) calculator in a multi-ethnic/multi-racial population. Researchers will use data from the Northern Manhattan Study, which is made up of more than 3,000 community-based participants. The group is 37% male and 63% female with 20% identified as non-Hispanic white, 25% non-Hispanic Black and 53% Hispanic background. The team will estimate ASCVD risk among these participants using both the race-specific pooled cohort equation (PCE) and the race-free PREVENT equation. They will then determine which equation better predicts 10-year risk of coronary heart disease or stroke.
  • Re-evaluating the role of race/ethnicity in the multi-ethnic study of atherosclerosis (MESA) and coronary heart disease risk – led by Quinn White, B.A., a Ph.D. student in biostatistics at the University of Washington in Seattle, Washington. This study will examine a race-free version of the Multi-Ethnic Study of Atherosclerosis (MESA) Risk Score. Researchers will update the model to remove race and ethnicity.
  • Assessing the role and importance of race and ethnicity in the clinical algorithm for predicting ASCVD – led by Yixin Zhang, M.S., a biostatistics Ph.D. candidate at Boston University in Massachusetts. This study has two objectives. One objective is to assess whether self-reported race and ethnicity affect atherosclerotic cardiovascular disease (ASCVD) risk prediction. The researchers will compare the Pooled Cohorts Equation, which considers race, with the new AHA Predicting Risk of Cardiovascular Disease Events (PREVENT) calculator that does not consider race. The second objective evaluates the extent to which a combined effect of social and environmental determinants explains the association between race/ethnicity and risk. They will assess whether social determinants of health and social deprivation index can replace race/ethnicity as representations of health disparities.

The American Heart Association has funded more than $5 billion in cardiovascular, cerebrovascular and brain health research since 1949. New knowledge resulting from this funding benefits millions of lives in every corner of the U.S. and around the world.


The opinions expressed here are the views of the writer and do not necessarily reflect the views and opinions of News Medical.
Post a new comment

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.

You might also like...
Research finds sugar tax may lower childhood asthma hospital admission rates by 20.9%