smart-on-fhir/cumulus-etl

Extract FHIR data, Transform with NLP and DEID tools, and then Load FHIR data into a SQL Database for analysis

60
/ 100
Established

This tool helps healthcare researchers and analysts prepare large volumes of patient data for clinical investigations. It takes raw Fast Healthcare Interoperability Resources (FHIR) exports from electronic health record systems, then cleans and anonymizes them. The output is structured, de-identified patient data loaded into a SQL database, ready for secure querying and analysis.

Available on PyPI.

Use this if you need to process population-scale clinical data from FHIR exports, protect patient privacy through de-identification, and extract valuable insights from unstructured clinical notes using natural language processing, all within a SQL-queryable format.

Not ideal if you are working with small datasets, do not require de-identification or advanced NLP on clinical notes, or prefer to keep your data exclusively within the FHIR standard without transformation to a SQL database.

clinical-research healthcare-analytics patient-privacy medical-data-processing population-health
Maintenance 13 / 25
Adoption 6 / 25
Maturity 25 / 25
Community 16 / 25

How are scores calculated?

Stars

22

Forks

6

Language

Python

License

Apache-2.0

Last pushed

Mar 18, 2026

Commits (30d)

0

Dependencies

17

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/smart-on-fhir/cumulus-etl"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.