To register for both an adjunct event and the Health Datapalooza, use the green online registration button. If you would like to register for an adjunct event, and not the full Health Datapalooza program, or you've already registered for the conference, please use this registration form and fax, email (registrations@academyhealth.org), or mail the form to AcademyHealth.

Introduction to NPI and NPPES


  • Date & Time: Sunday, February 9, 2020 | 9:00 a.m. – 12:30 p.m.
  • Where: Marriott Marquis, Washington, D.C.
  • Registration Fee: $150 Member/Non-member

Health Data Workshop in Collaboration with CareSet Systems

NPPES is the public data that lists every provider (both doctor and hospital) in the United States. It details where they provide treatment, what type of healthcare provider they are, and basic contact information. Typically, claims data analysis and healthcare system modeling begin with this dataset. Data Source: http://download.cms.gov/nppes/NPI_Files.html

This year, there are three new files coming out of NPPES include health information exchange endpoints, additional locations and other business names. This class will explain all of the fields, and the basic instructions for getting the data into an online database like AWS or Google database products, and how to filter the data on basic fields. Key topics will include:

  • Short history of HIPAA and its relationship to NPPES.
  • How to break the NPPES data into state-level data that can be loaded easily into Excel.
  • How to use csvkit to filter the NPPES csv file.
  • Understanding the National Uniform Claim Committee Healthcare Provider Taxonomy.
  • How to properly determine the “primary” provider type (taxonomy) for a healthcare provider.
  • Working with credentials in NPPES (be careful).
  • Review the address information in NPPES.
  • Review phone information in NPPES.
  • Review new endpoints file.
  • Review new other-name file.
  • Review new practice location file.

CMS Physician Utilization Data


  • Date & Time: Sunday, February 9, 2020 | 1:30 p.m. – 5:00 p.m.
  • Where: Marriott Marquis, Washington, D.C.
  • Registration Fee: $150 Member/Non-member

Health Data Workshop in Collaboration with CareSet Systems

For years, CMS was prevented from releasing data that summarized the procedures CMS physicians did for the Medicare program by a court order. In 2013, this court order was overturned allowing CMS to publish summaries of how physicians performed services under Medicare. This dataset is now among the most popular that CMS produces.

Since that time CMS has begun to publish a dataset, whose long name is the Medicare Provider Utilization and Payment Data: Physician and Other Supplier Public Use File (PUF). The industry typically short hands this as the “CMS Physician Utilization Data”. Using this, it is possible to build very sophisticated models of how physicians behave and how they change this behavior over time.

  • Understand the privacy constraints of CMS data, and how they have been applied to the files in this dataset.
  • Review the interactive versions that CMS offers to work with this data online.
  • Learn how to download and work with this data yourself, either by loading into a spreadsheet (requires filtering first) or by loading it into a database.
  • Learn the procedure codesets that make up the data, including what a HCPCS code is and what a CPT code is and where you can learn more about these datasets.
  • Learn where CPT codes end and where HCPCS codes and how to differentiate between them. Learn to examine the codesets by the motivations of their maintaining bodies, the AMA and CMS respectively.
  • Bundling procedure codes together for analysis using the AHRQ Healthcare Cost and Utilization Project (HCUP)
  • This dataset does not include data billed outside the Carrier setting. Learn what the “Carrier Setting” is and how it related to the history of the Medicare program.
  • Understand the different “place of service” codes are and how they are split into “office” and “facility” in this PUF.
  • Learn the basics of NPI and how to filter this data by type of physician
  • Learn to compare the contents of the national, state, provider, and provider+HCPCS level summary files.

Best Practices of Data Visualization for Healthcare Professionals: You Have the Data, but Can You See the Story?


  • Date & Time: Sunday, February 9, 2020 | 2:00 p.m. – 5:00 p.m.
  • Where: Marriott Marquis, Washington, D.C.
  • Registration Fee: $150 Member/Non-member

Health Data Workshop in Collaboration with HealthDataViz, LLC

Effectively communicating your health and healthcare data visually is a skill to be learned and developed. During this interactive session we’ll discuss the research of how people see and understand data, the best practices of data visualization, and examples of how leading organizations are creating clear and compelling displays of data.