Description
This synthetic healthcare dataset contains 1,000 patients with 1 year of longitudinal healthcare history, designed for secure testing without disclosing PHI. Using a Monte Carlo simulation, each record emulates clinically relevant treatment scenarios through realistic healthcare encounters and events. Ideal for single-organization use, this dataset includes healthcare data messages across multiple HL7 standards.
Key Features:
- 1,000 synthetic patients with 1 year of longitudinal healthcare data
- Common conditions included: Appendicitis, Cancer, Covid, Diabetes, Hypertension, Pregnancy, Pulmonary Embolism, and more
- Emulates real-world healthcare records with realistic gaps in data
- Multi-standard dataset supporting HL7 ADT, VXU, ORU, CCD, and FHIR
HL7 Message Standards Included:
ADT (Admission, Discharge, Transfer):
- A01 (Admit/Visit Notification): 1,410 messages
- A03 (Discharge/End Visit): 1,410 messages
- A04 (Register a Patient): 6,198 messages
VXU (Vaccination Update):
- V04 (Unsolicited Vaccination Update): 2,273 messages
ORU (Observation Result):
- R01 (Laboratory Results): 948 messages
CCD (Continuity of Care Documents):
- Fields: Demographics, Medications, Allergies, Encounters, Diagnosis, Lab Results, Immunizations, Social History
- Total: 7,608 messages
FHIR (Fast Healthcare Interoperability Resources):
- JSON FHIR R4 bundles
- 3,769 bundles (~376,900 total FHIR resources)
For multi-partner use or custom datasets, contact us for more details.
