Medicare Bayesian Improved Surname Geocoding (MBISG) Algorithm to Predict Race, Ethnicity of People with Medicare Now Available

CMS is pleased to announce the availability of a new Research Identifiable File (RIF) that utilizes the Medicare Bayesian Improved Surname Geocoding (MBISG) algorithm to predict the race and ethnicity of Medicare beneficiaries. This data file is available for public use through the Chronic Conditions Warehouse (CCW).

CMS developed the MBISG algorithm to enhance existing race and ethnicity data to better understand the Medicare population.

How does it work?

The availability of the MBISG in the CCW gives researchers an opportunity to have more accurate indirect estimates of the race and ethnicity data on the Medicare population for analysis. The MBISG data includes a set of probabilities that the person is a member of six racial and ethnic groups: American Indian or Alaska Native (AI/AN), Asian American and Native Hawaiian or Other Pacific Islander (AA and NHPI), Black, Hispanic, Multiracial, or White. MBISG probabilities are based on U.S. Census Bureau data on race and ethnicity distributions by surname and Census block group, as well as CMS’s race and ethnicity administrative data and additional administrative elements including first name, demographics, and coverage characteristics.

To better understand the likelihood a person would prefer materials in Spanish, the MBISG data also includes a Spanish Preference Category. This categorizes the predicted probability that each person with Medicare would prefer Spanish language material.

The MBISG data consists of a single file that contains the race and ethnicity probabilities of people with Medicare enrolled on March 1, 2023. This dataset is separate from CCW’s Master Beneficiary Summary File (MBSF), which is partitioned by calendar year. Researchers should note the MBISG dataset will overlap with MBSF files, but the cohort of people included in the MBISG dataset will not match exactly to any given MBSF calendar year dataset.

Get more information

CMS is committed to advancing health equity, including the availability, use, and accuracy of health equity data. To learn more about CMS efforts about health equity, review the CMS Framework for Health Equity and to find out more specifically about efforts around health equity data, review The Path Forward: Improving Data to Advance Health Equity Solutions

Need help?

The CMS Office of Minority Health offers a Health Equity Technical Assistance program to assist organizations, researchers, and those looking for help around health equity data collection and analysis, resources to embed health equity, and other resources to improve health equity efforts. Contact [email protected] for more information.

In addition, the CCW offers information and contacts for those with questions regarding the data warehouse. If you have a question more information about the MBISG data, you can also contact the MBISG team directly at [email protected].

Sign up for our listserv to get the latest on health equity from the CMS Office of Minority Health.

The post Medicare Bayesian Improved Surname Geocoding (MBISG) Algorithm to Predict Race, Ethnicity of People with Medicare Now Available appeared first on Pennsylvania Office of Rural Health.