Dataset

Medicare & Medicaid claims-derived datasets

Freely available Medicare and Medicaid claim files, including provider utilization, inpatient and outpatient summary claims, durable equipment, prescription drug events and hospital price transparency, the fullest public picture of US healthcare demand.

Visit provider

Dataset card

Medicare & Medicaid claims-derived datasets are public-domain releases from CMS Data that distill U.S. federal healthcare program claims into analyzable records of providers, services, and spending. The source page does not disclose the underlying schema or column definitions.

What this dataset contains

The records are derived from Medicare and Medicaid claims and are tagged with medicare, medicaid, claims, healthcare-spending, and providers, indicating coverage of program utilization and reimbursement activity. Because the publisher has not provided a description or sample rows, the specific population (e.g., all fee-for-service claims, summary tables, or provider-level aggregates) cannot be confirmed. License terms are listed as public domain / open terms, allowing broad reuse.

Structure and fields

No column names, field types, or row counts are listed in the source facts. The masked sample is reported as '(none)' and the schema is marked '(unknown)', meaning analysts must download or consult CMS documentation to discover fields such as claim identifiers, provider IDs, service codes, or payment amounts. Any structural detail beyond the tagged topics would be speculation.

How analysts use it

Given the healthcare-spending and providers tags, plausible use cases include mapping provider billing patterns, tracking procedure volumes, and benchmarking reimbursement across regions. Because the schema is unconfirmed, concrete joins (e.g., linking claims to provider taxonomies) cannot be verified from the source facts. Researchers should retrieve the official CMS documentation before integrating the data into investment or policy workflows.

Documentation & references 2