Synthea: An approach, method, and software mechanism for generating synthetic patients and the synthetic electronic health care record

By Jason A. Walonoski, Mark Kramer, Joseph Nichols, A. Quina, Chris Moesel, D. Hall, C. Duffett, Kudakwashe Dube, Thomas Gallagher, S. McLachlan. 2017

450 citations recorded by the source corpus.

Abstract Objective Our objective is to create a source of synthetic electronic health records that is readily available; suited to industrial, innovation, research, and educational uses; and free of legal, privacy, security, and intellectual property restrictions. Materials and Methods We developed Synthea, an open-source software package that simulates the lifespans of synthetic patients, modeling the 10 most frequent reasons for primary care encounters and the 10 chronic conditions with the highest morbidity in the United States. Results Synthea adheres to a previously developed conceptual framework, scales via open-source deployment on the Internet, and may be extended with additional disease and treatment modules developed by its user community. One million synthetic patient records are now freely available online, encoded in standard formats (eg, Health Level-7 [HL7] Fast Healthcare Interoperability Resources [FHIR] and Consolidated-Clinical Document Architecture), and accessible through an HL7 FHIR application program interface. Discussion Health care lags other industries in information technology, data exchange, and interoperability. The lack of freely distributable health records has long hindered innovation in health care. Approaches and tools are available to inexpensively generate synthetic health records at scale without accidental disclosure risk, lowering current barriers to entry for promising early-stage developments. By engaging a growing community of users, the synthetic data generated will become increasingly comprehensive, detailed, and realistic over time. Conclusion Synthetic patients can be simulated with models of disease progression and corresponding standards of care to produce risk-free realistic synthetic health care records at scale.

Subfields: Artificial Intelligence, Epidemiology, Health Information Management

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Synthesizing Tabular Data using Generative Adversarial Networks (2018, background): “RGAN and RCGAN [13] can generate real-valued time-series data. medGAN [9], corrGAN [33] and several improved models [2, 6, 47, 3, 44] can generate discrete medical records but do not tackle the complexity in generating multimodal continuous variables. ehrGAN [8] generates augmented medical records…”
Synthetic Data for Deep Learning (2019, methodology): “[617] present the Synthea software suite designed to simulate the lifespans of synthetic patients and produce realistic synthetic EMRs.”
Clinical Text Data in Machine Learning: Systematic Review (2020, background): “For instance, Synthea, the original open source synthetic health data software, can be used to simulate disease progression and the corresponding medical care to produce risk-free health care records at scale [138].”
Synthetic data generation for tabular health records: A systematic review (2022, background): “It was proposed by Walonoski et al. in 2018 [38] as an open-source synthetic health simulator that simulates synthetic patients from birth to death in JSON format via di ff erent pre-defined modules (diabetes, cancer, infections, treatments, etc).”
The National COVID Cohort Collaborative (N3C): Rationale, design, infrastructure, and deployment (2020, methodology): “104 • Computational derivation: Computational models of real-world data are produced on demand, which can be used to produce novel data in a multidimensional space (eg, features) that adhere to the quantitative distributions and covariance Table 4.”
Harnessing the power of synthetic data in healthcare: innovation, application, and privacy (2023, background): “The growing interest in the medical use of synthetic data has led companies to develop open source (e.g., Synthea) 12 or commercial (e.g., MDClone ’ s Synthetic Data Engine) 13 tools that can automate the generation of high-quality and clinically realistic synthetic datasets.”