Syntegra | Secure Healthcare Data Sharing

Product

Syntegra unlocks and accelerates the use of sensitive healthcare data using cutting edge artificial intelligence. We have developed a unique generative model, purpose built for healthcare, to synthesize replicas of entire complex datasets, precisely replicating all statistical properties, while removing any potential to identify the source of the synthetic records. This Syntegra technology takes advantage of modern statistical language modeling and transfer learning, allowing for continuous improvement of our already first-class technology.

Flexible Deployment

Syntegra’s synthetic data engine is fully containerized, allowing for easy deployment where your data is already stored (on-premises or private cloud).

Private

Syntegra automatically produces detailed privacy metrics for every synthetic dataset, allowing you to be confident in the privacy of the underlying data.

Secure

De-identification is broken. It no longer prevents re-identification.

Complete

Syntegra replicates full datasets, not just cohorts, maintaining robust statistical fidelity. All variable types are accepted. And data can be in tables or time-series of events (patient journeys).

Company

Syntegra provides validated replicas of medical data that match the statistical properties of the underlying source, yet cannot be linked to the original. Using our synthetic data engine, multiple stakeholders, including large health systems, life science companies, insurance providers, data scientists, and clinical research organizations can now seamlessly share privacy-guaranteed healthcare information, while bypassing the need for expensive and time consuming compliance and data governance structures, secure “sandboxes,” and complicated access protocols.

We apply state-of-the-art deep generative models, trained on data at rest, to learn billions of embedded statistical patterns. Once trained, only model parameters are required to generate “realistic but not real” patient records. Privacy is guaranteed in a way that goes beyond HIPAA or GDPR compliance. Since the resulting synthetic data contains no identifiable information on real individuals, it does not fall under HIPAA, GDPR, or any other privacy regulation. The synthetic data maintains individual-level statistical fidelity, and can be immediately utilized for statistical analysis, reporting, and building predictive models with full accuracy and no re-identification risk. The company is led by a team of extraordinary serial entrepreneurs, data scientists and university faculty with deep knowledge in medicine and data science.