Careset Labs – Datasets

We believe the release of reliable and current data is vital to the improvement of the healthcare system.

careset_labs_logo_250x79

CareSet Labs creates open healthcare datasets. We believe the release of reliable and current data is vital to the improvement of the healthcare system. Our mission is to encourage an ecosystem of innovators to collaborate and share tools and research methodologies around open healthcare datasets. Purchase of the datasets available at CareSet Labs supports the community of data scientists focused on leveraging initiatives of transparency in healthcare.

Purchase of the datasets available at CareSet Labs supports the community of data scientists focused on improving transparency in healthcare.

Cart is empty (0)

DocGraph Hop Teaming

DocGraph Hop Teaming is latest version of the classic dataset that shows how health care providers in the United States work together.

Please take a look at the extensive documentation for the reasons for the improved HOP dataset.

Data DocumentationDocGraph Hop Teaming Dataset Documentation

License: Open Source Eventually / Commercial License

Version :

MrPUP 2014

The Medicare Referring Provider Utilization for Procedures (MrPUP) dataset details the healthcare procedures that Medicare providers referred in the outpatient setting in 2014, and is particularly useful in understanding how specific doctors use blood tests, CT scans, and MRIs to diagnose patients.

Data DocumentationCareSet MrPup Dataset Documentation

License: Open Source Eventually / Commercial License

License :

PaPR Data Set

The PaPR data set is an important new open data set that describes the adoption of e-prescribing as measured in Part D Medicare data.The dataset, called PaPR (Providers and Prescribing Records) details how different individual prescribers deliver prescriptions to pharmacies, either using e-prescribing, faxes or paper.  The PaPR (pronounced “paper”) data set aggregates this information on a per-prescriber basis.

Data Documentation: Data Documentation

License: Non-Commercial , Commercial

Year :
License :

Root NPI Graph (2016)

Root NPI Graph was an improved version of the FOIA “shared Medicare patients in time” provider teaming dataset. This was the second version of the “DocGraph” dataset and is often called the Doctor Referral dataset as referred to by Medicare. It includes both implicit and explicit referral relationships between doctors, hospitals and other types of entities.

Note that this dataset has been deprecated in favor of the new DocGraph HOP teaming dataset. For all new projects, please use that dataset. We maintain these datasets here mainly for comparison and archival purposes.

Data DocumentationCareSet Root NPI Graph Dataset Documentation

License: Non-Commercial , Commercial

License :

Root NPI Graph (2015) – Free

Root NPI Graph (2014) – Free

Cancer Moonshot Data

Details how cancer patients enter and exit hospitals. This data is aggregated Medicare data starting in 2010 and ending in 2015, totaling six years.

Data Documentation: CareSet Cancer Moonshot Dataset Documentation

License: Creative Common 3.0

Physician Shared Patient Patterns

The physician referral data linked below was provided as a response to a Freedom of Information Act (FOIA) request that CareSet made more than 5 years ago.

These datasets can be difficult to find on the CMS website and sometimes the CMS resource is down, for this reason, we mirror this dataset here.

These files represent the number of encounters a single beneficiary has had across physicians at intervals of 30, 60, 90 and 180 days. For more details about the file contents for years 2009 – 2015, please see the Technical Requirements document.

Note that this dataset has been deprecated in favor of the new DocGraph HOP teaming dataset. For all new projects, please use that dataset. We also maintain these datasets because they go back farther than HOP, which could be useful for long-term analysis projects.

Data Source: Physician Shared Patient Patterns

License: Open Database License (ODbL)

Version :