Understanding racial bias in health using the Medical Expenditure Panel Survey data
This addresses bias in healthcare algorithms for affected populations, but is incremental as it applies known methods to a specific dataset.
The study tackled racial bias in health indicators within the Medical Expenditure Panel Survey data, showing that predictive models inherit this bias, and demonstrated that simple mitigation techniques can significantly reduce it.
Over the years, several studies have demonstrated that there exist significant disparities in health indicators in the United States population across various groups. Healthcare expense is used as a proxy for health in algorithms that drive healthcare systems and this exacerbates the existing bias. In this work, we focus on the presence of racial bias in health indicators in the publicly available, and nationally representative Medical Expenditure Panel Survey (MEPS) data. We show that predictive models for care management trained using this data inherit this bias. Finally, we demonstrate that this inherited bias can be reduced significantly using simple mitigation techniques.