As part of a focused effort to evaluate current cardiovascular treatment algorithms for racial bias, the American Heart Association, the largest nonprofit supporter of heart and brain health research in the U.S., is funding three new research projects at $50,000 each.
Clinical algorithms are formulas, charts, and computerized “calculators” that work behind the scenes to analyze health data and help determine a person’s heart disease risk or guide treatment decisions. Age, weight, blood test information, personal health history, health habits -; such as physical activity and smoking -; are among the data types used by clinical algorithms. Some algorithms include race or ethnicity in their analysis, but recent evidence suggests that race is often an inadequate proxy for genetics.
“By inappropriately incorporating race as a surrogate for biological characteristics, algorithms can inadvertently perpetuate disparities in care,” said Nav Persaud, MD, M.Sc., co-chair of the American Heart Association’s De-biasing Clinical Care Algorithms (DECCA) Expert Advisory. panel and physician in the Department of Family and Community Medicine at St. Michael’s Hospital in Toronto, Ontario, and Assistant Professor of Medicine at the University of Toronto.
Studying how race is incorporated into algorithms is an important endeavor for health equity by disentangling race from the social determinants of health that drive the relationship between race and disease.”
Judy Wawira Gichoya, MD, MS, American Heart Association volunteer and assistant professor in the Department of Radiology and Imaging Sciences at Emory University School of Medicine and an interdisciplinary researcher studying medical informatics
Gichoya co-chairs DECCA’s expert advisory panel with Persaud.
The teams of scientists who received funding for Assessing Race in Clinical Research Designs are from the Stanford University School of Medicine in Stanford, California, the Mayo Clinic in Jacksonville, Florida, and the University of Texas Southwestern Medical Center in Dallas. Support for these studies is part of a two-year research strategy, funded in part by a grant from the Doris Duke Foundation, to explore the complex issue of how race and ethnicity factor into clinical care algorithms and risk prediction tools.
Specifically, researchers are tasked with (1) assessing potential bias in risk models and identifying drivers of bias (eg, sampling bias, selection bias, missing data values, and potential risk factors); (2) developing statistical methods and advanced models that correct or mitigate algorithm bias to support equitable care and treatment.
The three research projects, which started on 1 July 2023 and are funded for up to two years each, include:
- Evaluation of cardiovascular risk algorithms among nonmarital and multiracial/multiethnic Asians – led by Adrian Bakong, Ph.D., MPH, postdoctoral researcher at Stanford University School of Medicine and associate program director of the Stanford Center for Asian Health Research and Education Team Science Fellowship in Stanford, California. In a three-part project, this team will examine the use of heart disease calculators for Asian Americans who identify as “Asian only” and those who identify as multiracial. They will first determine the predictive accuracy of Asian-specific heart disease calculators for people who self-identify as Asian. Second, they will test which race adjustment (Asian or white) better predicts heart disease risk among Asian Americans who identify as more than one race. Third, they will determine which clinical or lifestyle factors best predict heart disease among Asian Americans. The team expects that their findings can be used to create a more accurate heart disease risk calculator for Asian Americans.
- Evaluating the impact of race-specific generalized risk equations for predicting cardiovascular risk on clinical outcomes – led by Ramla Kasozi, MBCh.B., MPH, family medicine physician and senior associate consultant in the Department of Family Medicine and assistant professor of family medicine at the Mayo Clinic College of Medicine and Sciences in Jacksonville, Florida. This study sought to assess the potential influence of race on the performance of the pooled cohort equation (PCE) of atherosclerotic cardiovascular disease (ASCVD) in a study population that is different from the original population that led to the creation of the PCE. They will estimate cardiovascular disease risk outcomes in the study population by gender and other races when using the race-specific PCE. They will also determine whether the use of the race-specific PCE in other races has influenced clinical care. They expect to provide answers about the utility of including race in PCE.
- Machine learning-based models with social determinants of health to improve prediction of incident atrial fibrillation – co-led by Ambarish Pandey, MD, MS, assistant professor in the department of internal medicine at UT Southwestern Medical Center in Dallas, and Matthew Segar, MD, MS, fellow in cardiology at the Texas Heart Institute in Dallas. Researchers are exploring new ways to predict heart disease risk. Using machine learning and data from five large community-based cohort studies, they will build and test new models that incorporate social determinants of health (SDOH) instead of race to predict new onset atrial fibrillation (AF). They will compare the new model with current risk models to assess deviations. The researchers suggest that including SDOH may improve the accuracy of the model and hope to determine which factors contribute most to the development of AF.
The American Heart Association has funded more than $5 billion in cardiovascular, cerebrovascular, and brain health research since 1949. The new knowledge resulting from this funding benefits the lives of millions in every corner of the US and around the world.
source:
American Heart Association