CMS Data Feeds Dataset
About the Dataset
The CMS Data Feeds Dataset is a comprehensive collection of all current and future CMS data feeds available on cms.data.gov. This dataset transforms each feed into a view, aligning all feed file attributes and casting them to appropriate datatypes. The views are automatically updated when new feed files arrive, and the catalog itself is reviewed weekly for new CMS feeds — straightforward ones are added automatically, others get a closer look first.
Need a feed that isn't in the catalog yet? We can add it on demand — reach out and we'll evaluate it for the next release.
As of September 2026, the dataset encompasses 287 feeds and 5,532 feed files.
See the full list of feeds in the CMS Data Feeds Catalog.
Dataset Features
45 billion records and growing
285 feeds, reviewed weekly for new additions — automatic for straightforward feeds, reviewed first for others — plus on request
9,583 feed attributes
19 years of historical data
1.2 TB of data, continuously expanding
Daily updates to ensure data freshness
Automatic quality checks and active monitoring
Designed for seamless ingestion
Data Quality and Maintenance
Dataplex Consulting & Data Products prioritizes data quality through:
Automated data quality checks in all pipelines
Daily monitoring of ingestion and ETL jobs
Timely updates whenever CMS publishes new data
Rigorous processes to ensure data integrity and reliability
Business Applications
Users can leverage this dataset for various purposes, including:
Enriching or augmenting existing datasets
Analyzing published feed metrics over time
Performing segmentation analysis
Training machine learning models
Conducting geospatial analysis
Tracking healthcare trends and performance metrics
Example Use Cases
Analyze telehealth adoption trends across different states
Evaluate the financial performance of home health agencies
Track Medicare spending patterns by drug or geography
Assess hospital performance metrics and patient satisfaction scores
Monitor healthcare-associated infections across facilities
Which CMS Datasets Are Included
Every public CMS dataset published on catalog.data.gov and data.cms.gov is included, delivered as a ready-to-query view under its own name: 285+ feeds spanning provider directories, hospital quality and performance, outpatient and inpatient utilization, Medicare spending, home health, hospice, nursing home, and dialysis data. When CMS publishes a new dataset, it's picked up in our weekly review — straightforward feeds are added automatically, others get a closer look first.
Looking for a specific dataset (for example Medicare Outpatient Hospitals - by Provider and Service)? It is already a queryable view. Browse the full list in the CMS Data Feeds Catalog.
A Queryable CMS Database, Not Downloads
Instead of downloading hundreds of CSVs one release at a time, you get one CMS database on Snowflake or Databricks: every feed as a typed SQL view, joinable across datasets, with prior releases preserved for trend analysis. No parsing, no schema drift, no re-stitching files after each CMS refresh.
CMS Data by Subscription: Always Current
This is a subscription healthcare data feed, not a one-time extract: views refresh as CMS publishes, new feeds are added on an ongoing weekly basis, and ongoing utilization, spending, and quality data keeps flowing without re-downloading anything. Your queries stay the same while the data underneath stays current.
catalog.data.gov vs. This Product
The free CMS portals are authoritative, and for a single one-off download they are the right choice. This product exists for everything the portals can't do:
Access
Per-file downloads, one release at a time
SQL on Snowflake or Databricks
Schema
Raw CSVs; column types and layouts shift between releases
Typed, consistent views per feed
Joins
Manual stitching across files
Join any feeds in one warehouse
History
Current release only; old files disappear
Prior releases preserved for trending
Updates
Re-download after every CMS refresh
Views update automatically
Ready to access CMS Data Feeds data?
Questions? Contact our team for a walkthrough.
Snowflake
Databricks
Data Structure
The dataset consists of three main components:
FEEDS: Contains metadata about each CMS data feed
FEEDS_FILES: Stores information about individual files within each feed
Feed-specific views: Separate views for each feed (e.g., PatientReported_Outcomes, Medicare_Spending)
Entity Relationship Diagram
Sample Queries
📊 Recent Feed File Updates
Recent CMS feed file updates (last 30 days)
8/26/2026
8/1/2026
8/26/2026
8/1/2026
8/26/2026
8/1/2026
8/26/2026
8/1/2026
8/26/2026
8/1/2026
8/26/2026
8/1/2026
8/26/2026
8/1/2026
8/26/2026
8/1/2026
8/15/2026
7/22/2026
8/15/2026
7/22/2026
8/15/2026
7/22/2026
8/15/2026
7/22/2026
8/15/2026
7/22/2026
8/15/2026
7/22/2026
8/15/2026
7/22/2026
8/11/2026
1/1/2024 to 12/31/2024
8/11/2026
1/1/2024 to 12/31/2024
8/11/2026
1/1/2024 to 12/31/2024
8/11/2026
1/1/2024 to 12/31/2024
8/11/2026
1/1/2024 to 12/31/2024
8/11/2026
1/1/2024 to 12/31/2024
8/11/2026
1/1/2024 to 12/31/2024
8/11/2026
1/1/2024 to 12/31/2024
8/10/2026
4/1/2026 to 6/30/2026
🆕 Recently Added Feeds
ESRD QIP - Facility Commitment to Health Equity - Payment Year 2026 (Added: September 2026)
What's in this data: This dataset contains facility-level measure scores related to health equity for dialysis facilities, alongside state and national benchmark scores for the Payment Year 2026 ESRD Quality Incentive Program (QIP). It is significant for understanding facility performance and compliance with health equity measures in dialysis care.
How you can use it:
Evaluate performance of individual dialysis facilities against state and national benchmarks.
Identify facilities that may need improvement in health equity measures to enhance patient care.
Support policymakers in assessing the impact of health equity initiatives in dialysis treatment.
Example Queries:
Retrieve the average FCHE measure score for each state to evaluate state-level performance.
List facilities with no score, along with their reasons for not receiving a score, to identify areas needing attention.
Medicare Short-Stay Hospital Discharge Rankings (Added: August 2026)
What's in this data: The Medicare Short-Stay Hospital Discharge Rankings dataset provides ranked information on Medicare-covered inpatient discharges from acute care hospitals by Diagnosis-Related Group (DRG). It highlights trends in hospital usage, common admission reasons, and changes in DRG rankings over time, offering valuable insights for healthcare providers and policymakers.
How you can use it:
Analyze trends in hospital discharges by DRG to identify increasing or decreasing health issues in the population.
Compare current fiscal year rankings with prior year rankings to evaluate changes in hospital performance and healthcare delivery.
Identify the most common conditions leading to Medicare-covered inpatient discharges for targeted healthcare interventions.
Example Queries:
This query compares the current and prior fiscal year rankings for each DRG to identify significant changes in performance.
Long-Term Care Hospital - Provider Data (Added: July 2026)
What's in this data: This dataset provides provider-level quality measures for long-term care hospitals as reported by CMS. It includes various metrics such as scores for specific measures, hospital details, and time frames, which are essential for evaluating hospital performance and quality of care.
How you can use it:
Analyze quality scores over time for individual long-term care hospitals to identify trends in performance.
Compare the quality measures of long-term care hospitals across different states or counties to assess geographic disparities.
Generate reports for stakeholders to evaluate compliance with CMS standards and inform quality improvement initiatives.
Example Queries:
This query analyzes the trends in scores for a specific hospital over multiple reporting periods.
📋 View the complete CMS Data Feeds Catalog
Frequently Asked Questions
Is there a subscription service for ongoing healthcare utilization data feeds? Yes. This dataset delivers CMS utilization, spending, and quality feeds as a subscription on Snowflake or Databricks, refreshed as CMS publishes, with new feeds reviewed and added weekly.
Is there a database of all CMS datasets? This product is exactly that: every public CMS dataset from catalog.data.gov and data.cms.gov as a typed, queryable view in one database, with 19 years of history.
How current is the data? Feeds update as CMS publishes: checked daily, loaded when new files appear. The Recent Feed File Updates section below shows the latest loads.
Can my AI agent or data pipeline consume this? Yes: access is plain SQL on Snowflake or Databricks. See the AI Agent Quickstart for the exact commands.
Get Started
Includes
All 232 feeds, daily updates, full documentation
Support
Email support included
Cancellation
Cancel anytime, no long-term commitment
Support and Contact
For questions or assistance with the CMS Data Feeds Dataset, please contact:
Email: support@dataplex-consulting.com
The Dataplex Consulting & Data Products team monitors ingestion and ETL jobs daily to ensure quality and timely delivery.
About Dataplex
Dataplex Consulting & Data Products delivers turnkey, analytics-ready data products that make complex public and commercial data easy to use across modern data platforms. Our data pipelines include automated quality checks and active monitoring to ensure timely, reliable, and well-structured data that is ready for downstream analytics, machine learning, and operational use.
In addition to data products, Dataplex provides data engineering and analytics consulting services to organizations of all sizes. We bring deep, hands-on experience supporting both early-stage companies and large enterprises, helping teams build scalable data platforms, improve data reliability, and become more data-driven.
Last updated