Understanding racial bias in health using the Medical Expenditure Panel Survey data

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.

[1]  A. Ash,et al.  Finding future high-cost cases: comparing prior cost versus diagnosis-based methods. , 2001, Health services research.

[2]  B. Smedley,et al.  Unequal Treatment: Con-fronting Racial and Ethnic Disparities in Health Care , 2002 .

[3]  J. Sommers,et al.  Medical Expenditure Panel Survey - Insurance Component (MEPS-IC) , 2004 .

[4]  Rachel K. E. Bellamy,et al.  AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias , 2018, ArXiv.

[5]  Martine De Cock,et al.  Population Cost Prediction on Public Healthcare Datasets , 2015, Digital Health.

[6]  J. Fleishman,et al.  Using information on clinical conditions to predict high-cost patients. , 2010, Health services research.

[7]  Laura R Wherry,et al.  Using self-reported health measures to predict high-need cases among Medicaid-eligible adults. , 2014, Health services research.

[8]  D. Stryer,et al.  Balancing the nation's health care scorecard: the National Healthcare Quality and Disparities Reports. , 2005, Joint Commission journal on quality and patient safety.

[9]  Toon Calders,et al.  Data preprocessing techniques for classification without discrimination , 2011, Knowledge and Information Systems.

[10]  Arlene S Ash,et al.  Risk-adjusted Payment and Performance Assessment for Primary Care , 2012, Medical care.

[11]  Kensaku Kawamoto,et al.  Supervised Learning Methods for Predicting Healthcare Costs: Systematic Literature Review and Empirical Evaluation , 2017, AMIA.

[12]  Adrienne Y. Stith,et al.  Unequal Treatment: Confronting Racial and Ethnic Disparities in Health Care , 2005 .

[13]  J. Farley,et al.  A comparison of comorbidity measurements to predict healthcare expenditures. , 2006, The American journal of managed care.

[14]  Sendhil Mullainathan,et al.  Dissecting Racial Bias in an Algorithm that Guides Health Decisions for 70 Million People , 2019, FAT.