generating-synthea-data

Generate reproducible synthetic patient records in FHIR R4, C-CDA, and CSV formats.

5.0k|615|Updated Oct 4, 2025
One-click install
npx skills add https://github.com/maziyarpanahi/openmed --skill generating-synthea-data
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: generating-synthea-data
Source: https://github.com/maziyarpanahi/openmed/tree/main/skills/generating-synthea-data
Command: npx skills add https://github.com/maziyarpanahi/openmed --skill generating-synthea-data

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps clinical AI teams create realistic, shareable patient records without using real protected health information, enabling safer development, testing, demonstrations, and de-identification evaluation.

Core Features & Use Cases

  • Synthetic Record Generation: Create longitudinal patient populations with MITRE Synthea in FHIR R4, C-CDA, and CSV formats.
  • Reproducible Test Fixtures: Pin seeds, versions, locations, and modules to produce stable datasets for continuous integration and development.
  • Leakage-Gate Evaluation: Use Synthea's known synthetic identifiers as ground truth for measuring de-identification recall without exposing real patient data.
  • Use Case: Generate a seeded population of synthetic patients, process their FHIR narratives through OpenMed de-identification and analysis workflows, and commit the resulting fixtures to a test suite.

Quick Start

Use the generating-synthea-data skill to create a small, reproducible Synthea population in FHIR, C-CDA, and CSV formats for OpenMed testing.

Frequently Asked Questions about generating-synthea-data

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate synthetic patient data in FHIR R4 format for testing?

Generate synthetic patient data in FHIR R4 format by running MITRE Synthea with pinned seeds to produce reproducible, longitudinal patient records for safe clinical AI testing without exposing real protected health information.

What is the best way to create reproducible test fixtures using synthetic patient records?

Create reproducible test fixtures by pinning seeds, versions, locations, and modules in MITRE Synthea to generate stable synthetic patient datasets for continuous integration pipelines and development testing.

Can I use synthetic patient data to evaluate de-identification recall?

Use synthetic patient data to evaluate de-identification recall by leveraging Synthea's known synthetic identifiers as ground truth, measuring leakage-gate performance without exposing real patient records.

Does Synthea require Java to generate synthetic FHIR or C-CDA records?

Synthea requires Java 11 or newer to generate synthetic patient records in FHIR R4, C-CDA, or CSV formats, ensuring appropriate versioning of generated fixtures for clinical AI development.

What output formats are available when generating synthetic patient data?

Synthetic patient data generation supports FHIR R4, C-CDA, and CSV output formats, enabling versatile ingestion into clinical AI workflows and testing pipelines.

Why use synthetic data instead of real patient records for clinical AI development?

Use synthetic data to avoid exposing real protected health information during clinical AI development, enabling safer testing, demonstrations, and de-identification evaluation with shareable, realistic patient records.