A Synthetic FHIR Dataset
summary
Open-source Synthea generates realistic but synthetic patient histories and writes FHIR DSTU2/STU3/R4 bundles (transaction or bulk formats) using JSON module builder state machines that map to Conditions, Encounters, MedicationRequests, Observations, Claims, etc. It supports seeding for reproducible cohorts, filters by age/gender/location, assigns real CMS providers, and can produce 10,000+ patients (example run created ~11,440 records). Bundles POST to a HAPI-like sandbox and zip uploads use Microsoft AZCopy.
AI-written summary · about
chapters (8)
- 0:00Introduction and setup
- 4:36Understanding Synthea
- 7:38Configuring disease models
- 12:50Running synthetic data
- 17:48Exporting to FHIR servers
- 20:59Advanced generation filters
- 24:50Large-scale batch generation
- 33:34Sharing and closing








