synthea

Synthetic Patient Population Simulator

Open Synthea patient data for machine learning and team training.

More realistic synthetic medication data.

This healthcare analytics project uses SQL queries to extract insights from patient data, encounters data, and etc.

Generate realistic and complete synthetic test data for US Core v3.1.0

A configurable synthetic patient generator which delivers and centralizes information on a repetitional continuous basis via the message broker technology and through a healthcare integration engine

A practical guide for a quick start in building learning health systems (LHS) units.

Examples of exploring synthetic healthcare data from the Agency for Healthcare Research and Quality in the United States Department of Health and Human Services, and MITRE Corporation.

The purpose of this application is to test LLM-generated interpretations of medical observations. The explanations are generated fully automatically by a large language model. This application should be used for experimental purposes only. It does not provide support for real world cases and does not replace advice from medical professionals.

Synthetic health dataset generator

The Patient Pathway Extractor is an application to transform patient medical data into a compact machine processable representation that can be used for machine learning and deep learning tasks.

A deep learning library for Electronic Health Record (EHR) data

Semantic web representation for the Synthea.

Voice AI for life after hospital discharge. It knows your care plan, answers recovery questions, books follow-ups, and escalates red-flag symptoms to your care team in real time.

Utilities and helper scripts for working with the Synthea synthetic patient data generator.

Create a simulation patient population using Synthea and ETL it into the OMOP Common Data Model

Synthea-inspired hybrid synthetic patient record generator — Gaussian copula + clinical modules, trained on Turkish pristine-healthy EHR cohorts. Outputs CSV + FHIR R4 (LOINC/SNOMED/ICD-10/RxNorm). Includes a Tauri desktop app for non-coders.

Reference implementation: modernizing a legacy payer data warehouse into a governed lakehouse with FHIR-ready data

Citation-grounded clinical Q&A over synthetic FHIR records: RAG with per-sentence source citations, abstention on insufficient evidence, Presidio PHI redaction, and a CI-gated evaluation harness.

End-to-end oncology RWE pipeline: synthetic EHR data (Synthea) harmonized to the OMOP CDM, an NSCLC cohort built with dbt and PostgreSQL, and survival analysis in R, benchmarked against SEER registry data. Includes data-quality checks and a documented case where the synthetic data failed validation. Methods demo, not real patient data.