-
Notifications
You must be signed in to change notification settings - Fork 2
Getting Started
Roberto Cruz edited this page May 15, 2026
·
2 revisions
This guide walks you through installing Synthea and generating your first synthetic patients.
- Python 3.8 or higher
- UV — fast Python package manager
# macOS and Linux
curl -LsSf https://astral.sh/uv/install.sh | sh
# Windows
powershell -c "irm https://astral.sh/uv/install.ps1 | iex"
# Or via pip
pip install uv# Clone the repository
git clone https://github.com/TIET-AI/tietai-synthea.git
cd tietai-synthea
# Create virtual environment and install
uv venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
uv pip install -e .
# Optional: install dev dependencies
uv pip install -e ".[dev]"
# Optional: physics and visualization extras
uv pip install -e ".[physiology,visualization]"# Generate 10 patients (no activation needed with uv run)
uv run synthea -p 10
# Generate 100 patients in Massachusetts
uv run synthea -p 100 --state Massachusetts
# Generate with a fixed seed (reproducible output)
uv run synthea -p 50 -s 12345
# Generate only female patients aged 25–40
uv run synthea -p 20 -g F -a 25-40
# Output to a specific directory
uv run synthea -p 100 -o ./output --state California --city "San Francisco"Output files are written to ./output/ by default. With FHIR export enabled (the default), you will find one JSON bundle per patient under output/fhir/.
# List all available disease modules
uv run synthea --list-modules
# Show version
uv run synthea --version
# Run the test suite
uv run pytest -vEach run produces a structured output directory:
output/
├── fhir/
│ ├── hospitalInformation*.json # Facility bundle
│ ├── practitionerInformation*.json
│ └── <PatientName>_*.json # One bundle per patient
├── csv/ # CSV tables (if enabled)
└── metadata/
└── simulation.json # Run statistics