Synthetic data has tremendous value in health research and healthcare applications with one of the benefits including the ability to make decisions without compromising patient privacy. Synthetic data can also speed up software development, increase access to important patient data, and improve research that benefits veterans.
The data available to researchers and the public has multiplied in recent years. It has been used to uncover meaningful insights that address many challenges, including veteran health. However, there are often issues of lack of access to actual datasets due to privacy concerns and legal restrictions.
Addressing these challenges is key to engaging the broader research community to tackle the important issues and challenges to which VA is committed. Although there are some risks, synthetic data is being considered to fill this gap while balancing the privacy guarantee to protect veterans.
VA has a platform where synthetic data can be generated. Yet, there is currently no policy in place regarding the use of this data. VA worked with the American Council for Technology-Industry Advisory Council (ACT-IAC) to develop policies. The collaboration resulted in a white paper that describes how to create and use synthetic data.
What is summary data and why is it important?
Synthetic data is generated from computer simulations or algorithms modeled from published studies that reflect typical patient care pathways based on statistical data. This provides an alternative to real-world data that would otherwise have to be extracted from patients’ electronic health records.
An example of synthetic data already used in VA is the VA Suicide Prevention Grand Challenge. The challenge aims to reduce veteran suicide by 10%. The Grand Challenge relies on internal and external collaborators to quickly find innovations in prevention, including the use of synthetic data.
Kshemendra Paul is VA’s Chief Data Officer. She spoke about the value and importance of synthetic data at the ACT-IAC Community of Interest in February. This is where the white paper was presented.
“We have so much data available to us on health care and benefits and veterans service,” Paul said. “If we can rip the cultural and structural kryptonite out of our chests and integrate that data and manage it, we can better serve veterans and frankly position VA leadership broadly to help lead health care and wellness in the states. -United.”
Learn more about synthetic data
If you want to learn more about synthetic data and the considerations for using it in healthcare, ACT-IAC is hosting a Synthetic Data Workshop on May 4 from 9 a.m. to 1 p.m. ET. Dr. Carolyn Clancy, VHA Assistant Undersecretary for Health for Discovery, Education, and Affiliate Networks (DEAN) is on the list of keynote speakers.
Dr. Amanda Purnell is Director of Data and Analytics Innovation for the VHA Innovation Ecosystem and will lead a session on the role of academia and industry in advancing the governed use of data synthetics. You can learn more and register for the event here.
To learn more about the VHA innovation ecosystem, visit our website.