Synthea Synthetic Patient Records in OMOP CDM, 1k to 2.8M Persons

SyntheaTM synthetic patient generator data models the complete medical history of synthetic patients. The dataset is provided in the OMOP Common Data Model format at three scales: 1,000, 100,000, and 2,800,000 synthetic persons. Amazon Web Services hosts this data, which is free from cost, privacy, and security restrictions for secondary use.

Use Cases

• Testing and validating OMOP CDM-based analytics pipelines based on synthetic patient records.
• Training machine learning models for clinical prediction tasks based on modeled medical histories.
• Benchmarking healthcare data standardization tools using the provided OMOP CDM format.
• Simulating population health studies based on the scalable synthetic cohorts (1k to 2.8m persons).

Strengths

• Data is explicitly free from cost, privacy, and security restrictions, enabling broad secondary use.
• Provides three distinct population scales (1k, 100k, and 2.8m persons) for flexibility in testing.
• Models the medical history of synthetic patients, covering every aspect of healthcare as stated in the description.
• Formatted in the standardized OMOP Common Data Model, which suggests interoperability for clinical research.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count for each specific file is unknown, which may limit suitability assessment.
• Last update date is unknown; freshness unverified.

Provenance

Source

SyntheaTM synthetic patient generator.

Collection Method

Algorithmically generated synthetic patient data modeling medical histories.

Time Range

null

Freshness

Last updated date is unknown.

Geography

null