Assessing racial bias in type 2 diabetes risk prediction algorithms

Risk prediction models for type 2 diabetes can be useful for the early detection of individuals at high risk. However, models may also bias clinical decision-making processes, for instance by differential risk miscalibration across racial groups. We investigated whether the Prediabetes Risk Test (PRT) issued by the National Diabetes Prevention Program, and two prognostic models, the Framingham Offspring Risk Score, and the ARIC Model, demonstrate racial bias between non-Hispanic Whites and non-Hispanic Blacks. We used National Health and Nutrition Examination Survey (NHANES) data, sampled in six independent two-year batches between 1999 and 2010. A total of 9,987 adults without a prior diagnosis of diabetes and with fasting blood samples available were included. We calculated race- and year-specific average predicted risks of type 2 diabetes according to the risk models. We compared the predicted risks with observed ones extracted from the US Diabetes Surveillance System across racial groups (summary calibration). All investigated models were found to be miscalibrated with regard to race, consistently across the survey years. The Framingham Offspring Risk Score overestimated type 2 diabetes risk for non-Hispanic Whites and underestimated risk for non-Hispanic Blacks. The PRT and the ARIC models overestimated risk for both races, but more so for non-Hispanic Whites. These landmark models overestimated the risk of type 2 diabetes for non-Hispanic Whites more severely than for non-Hispanic Blacks. This may result in a larger proportion of non-Hispanic Whites being prioritized for preventive interventions, but it also increases the risk of overdiagnosis and overtreatment in this group. On the other hand, a larger proportion of non-Hispanic Blacks may be potentially underprioritized and undertreated

Diabetes mellitus · Disease · Environmental health · Framingham Risk Score · National Health and Nutrition Examination Survey · Overdiagnosis · Population · Prediabetes · Risk assessment · Type 2 diabetes · Demography · Diabetes, Cardiovascular Risks, and Lipoproteins · Genetic Associations and Epidemiology · Health Promotion and Cardiovascular Prevention · Medicine · Endocrinology · Gerontology · Internal Medicine

• Algorithmic bias in public health AI

  Open Access•Jeena Joseph•Frontiers in Public Health•2025

  Añadir item

• The bias algorithm

  Syed Atiq Hussain, Mary Bresnahan et al.•Ethnicity and Health•2025

  Añadir item

• Comparison of Random Forest and Parametric Imputation Models for Imputing Missing Data Using Mice

  Open Access•Anoop D Shah, Jonathan Bartlett et al.•American Journal of Epidemiology•2014

  Añadir item

• Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs

  Varun Gulshan, Lily Peng et al.•JAMA•2016

  Añadir item

• Dissecting racial bias in an algorithm used to manage the health of populations

  Open Access•Ziad Obermeyer, Brian Powers et al.•Science•2019

  Añadir item

• Multiple Imputation for Nonresponse in Surveys

  Open Access•Donald B Rubin•Multiple Imputation for…•1987

  Añadir item

• Place matters

  Open Access•Barbara A Laraia, Barbara Laraia et al.•Social Science & Medicine•2012

  Añadir item