A data processing system with 200+ composable operators for cleaning, filtering, deduplicating and synthesizing text, image, audio and video data for foundation model training.
synthetichealth/synthea
Open-source simulator that generates realistic but synthetic patient populations with health records in formats such as FHIR, C-CDA and CSV.
- Stars
- 3,406
- Forks
- 955
- Open issues
- 279
- Last commit
- 7 hours ago
What is it?
Synthea is a synthetic patient population simulator. It models patients from birth to death and produces synthetic health records that look realistic but do not describe real people, which makes it useful where real clinical data is restricted or unavailable.
Each simulated patient goes through conditions, allergies, medications, vaccinations, vitals, labs, procedures and care plans, driven by a modular rule system. Default statistics and demographics are based on Massachusetts census data, and users can adjust them through configuration or add custom Generic Modules or Java rule modules.
Output formats include HL7 FHIR (R4, STU3 and DSTU2), bulk FHIR in ndjson, C-CDA, CSV and CPCDS, each switched on via properties in synthea.properties. The project is written in Java and built with Gradle, requiring JDK 17 or newer.
Key features
- 01Simulates patients from birth to death with encounters, conditions, medications and vitals
- 02Configurable demographics and statistics, with defaults based on Massachusetts census data
- 03Modular rule system with Generic Modules and custom Java rule modules
- 04Exports HL7 FHIR (R4, STU3, DSTU2), bulk FHIR ndjson, C-CDA, CSV and CPCDS
- 05Command-line options for state, city, population size, seed and filters
Use cases
- Testing healthcare software or FHIR integrations without using real patient records
- Generating sample datasets for analytics, dashboards or machine learning prototypes in health data
- Creating realistic test populations for interoperability and data pipeline validation
Topics
FAQ
- What is synthea?
- Open-source simulator that generates realistic but synthetic patient populations with health records in formats such as FHIR, C-CDA and CSV. Synthea is a synthetic patient population simulator. It models patients from birth to death and produces synthetic health records that look realistic but do not describe real people, which makes it useful where real clinical data is restricted or unavailable.
- Is synthea free to use? What license does it have?
- synthea is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
- Is synthea still maintained?
- Actively maintained. The last commit to synthea was on Oct 21, 2026.
- What can I use synthea for?
- Testing healthcare software or FHIR integrations without using real patient records Generating sample datasets for analytics, dashboards or machine learning prototypes in health data Creating realistic test populations for interoperability and data pipeline validation
- Where can I get synthea?
- The source code and installation instructions are on GitHub: https://github.com/synthetichealth/synthea
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Free, cross-platform Java app for designing model rockets and simulating their flight, aerodynamics and trajectory before building.
Offline companion app that pairs with WHOOP 4.0 and 5.0 straps over Bluetooth and keeps all biometric data on your own device.
A self-hosted AI health data engine that standardizes lab reports, wearable data and genetic files into one traceable record, with an MCP server.
A Python multi-agent framework for building, simulating and studying LLM-based agents, with tools, memory, and data generation support.
A PyTorch-based open-source framework for deep learning on healthcare imaging data, covering preprocessing, networks, losses and evaluation metrics.