The Department of Health and Human Services (HHS) on February 14, 2026, opened access to a huge trove of Medicaid provider-level data, now publicly available for analysis on the HHS Open Data platform. These data were pulled from the Centers for Medicare and Medicaid Services’ (CMS) TMSIS system and include six years of data spanning the COVID-19 pandemic with provider level detail by procedure code.
There are many concerns with the data, including data comparability, along with data integrity. For example, when considering data comparability, state Medicaid programs use differing service definitions or units of service under the same procedure code. Some states may allow for billing in 15-minute increments, while others may cover 24 hours of service in an increment under the same procedure code, making it difficult to compare data across providers.
CMS specifically acknowledged data integrity issues, though there was no information on resolution of the concerns. The agency provides no additional context to indicate if those data were excluded from the data set, adjusted for, corrected, or included without reverence to the identified data integrity issues.
Despite the data integrity concerns and the lack of context for the data (like the COVID-19 pandemic, which significantly impacted Medicaid spending and payment rates), public researchers have indicated that they are ‘crunching the data’ in order to identify fraudulent activity among Medicaid providers.
Any claims of fraud stemming solely from analysis of this data without significant context and background on aligned data sets should be met with skepticism.
LeadingAge is monitoring the situation, and independent research organization KFF has published an analysis of the data and an overview of concerns.