Report: Race in Clinical Prediction Models

By V.S. Santoni

Predicting outcomes of health has long been an important part of medicine. Debates have long centered around the usefulness of race as a variable in those models. In a new study, Atheendar Venkataramani, a Senior Fellow at the University of Pennsylvania’s Leonard Davis Institute; Northwestern University economist Charles Manski; and University of Wisconsin economist John Mullahy look at race and clinical prediction models.

Some of the important outcomes of the research show that race as a measure continues to hold usefulness in outcomes across all races. In the study, Venkatarmani et al. do note that if better measures are created such as “impact of structural racism” then race may not be as useful as a more precise measure.

The study found that the utilization of race in treatment did improve clinical outcomes. “By comparing different scenarios, the investigators found that observing more patient attributes allowed clinicians to improve their predictions of treatment outcomes, enabling them to choose the most beneficial treatment courses for each individual patient. The framework suggests that, as long as measures of race have some predictive power, outcomes for patients of all races are optimized when patient race is considered.”

The study also noted the more measures incorporated in to the model the more predictive It became. According to Venkataramani et al. “The model allows for clinicians to consider as many patient attributes as possible—including gender, socioeconomic status, health history, genetic information, and biomarkers—to improve the accuracy of their predictions. To reflect real-world care, they did not assume that clinicians can predict patient outcomes with certainty. “

The ultimate goal of the research is to inform policy debates around race as a measure, and the best utilization for clinical research models. The hope is to inform debates on the local, regional and national levels. Going forward more precise measures such as level of exposure to systemic racism might prove more accurate in predicting outcomes.