ONC's Synthetic Health Data Challenge seeks new approaches to analytics

The use of realistic health record information that mimics lifelong medical histories can enable more innovative algorithms for disease modeling.
By Mike Miliard
02:59 PM
Synthetic Health Data

The Office of the National Coordinator for Health IT this week launched its new Synthetic Health Data Challenge – offering researchers a chance to explore new avenues of medical research.

WHY IT MATTERS
The new challenge is part of ONC's Synthetic Health Data Generation to Accelerate Patient-Centered Outcomes Research project.

Participants are invited to develop and test innovative new tools and approaches to build on the capabilities of Synthea, an open-source synthetic patient generator that models the medical histories of synthetic patients.

The goal is to advance research and development and to validate the realism of synthetic health records generated by Synthea, according to ONC – creating or improving disease-progression and treatment modules used to create synthetic records, and driving innovative new uses of synthetic health data.

Phase I proposals can be submitted in either of two categories: Enhancements to Synthea or Novel Uses of Synthea Generated Synthetic Data. The best of them will move on to Phase II: Prototype or Solutions Development.

Phase II features awards totaling up to $100,000: Up to two first-place winning solutions will receive $25,000 each, up to two second-place solutions will receive $15,000 each, and up to two third-place solutions will receive $10,000 each.

For more information, visit the ONC website. To register for the Synthetic Health Data Challenge or the Phase I Informational Webinar, visit Challenge.gov. 

THE LARGER TREND
As ONC defines it, synthetic health data is "realistic (but not real) health record data that contains a complete medical history from birth to death. This data can be used without cost or restriction and is intended to support the specific interests of researchers and developers for testing the effectiveness of tools, algorithms, and disease modeling approaches."

As Robert Lieberthal, an economist at the MITRE Corporation, told Healthcare IT News a year ago, wider and smarter use of synthetic data could go a long way toward development of more effective analytics for clinical decision support, value-based care insights and more.

"Synthetic data is a solution to many of the problems that plague our health IT system," Lieberthal explained. "Synthetic generally consists of fully synthetic – fabricated – patient records and claims data. It is different from partially de-identified data, or data sets where variables have been censored or removed in order to restrict on protected health information variables.

"Once the synthetic data has been created, it can be improved through shrinking the size of data or its complexity," he added. "Synthetic data also can be used to simulate the health IT system of the future, such as fully interoperable data or integrated clinical/EHR and claims/insurer data."

ON THE RECORD
"Synthetic data like those created by Synthea can augment the infrastructure for patient-centered outcomes research by providing a source of low risk, readily available, synthetic data that can complement the use of real clinical data," said ONC Chief Scientist Teresa Zayas-Cabán in a statement about the new Synthetic Health Data Challenge.

"By enhancing Synthea with new clinical data modules or demonstrating novel uses of Synthea-generated synthetic data, challenge participants will support PCOR research and development efforts by enhancing PCOR researchers' ability to conduct rigorous analyses and generate relevant findings."

Twitter: @MikeMiliardHITN
Email the writer: mike.miliard@himssmedia.com

Healthcare IT News is a HIMSS publication.

Want to get more stories like this one? Get daily news updates from Healthcare IT News.
Your subscription has been saved.
Something went wrong. Please try again.