Skip to content Skip to navigation

Envisioning a health data system that learns from itself

December 30, 2014
by Richard R. Rogoski
| Reprints

Systems integration and the adoption of electronic health records (EHRs) is not enough to identify and share best practices within the healthcare industry, according to a new report.

The report, issued by an independent group of scientists called JASON at the request of the U.S. Department of Health & Human Services, calls for a "closed loop" health data system that ensures "a continuous and transparent cycle of research, analysis, development and adoption of improvements relevant to health and wellness and to the delivery of healthcare."

Right now there is no feedback between healthcare outcomes and clinical research, the scientists said, which hinders learning within the system.

Furthermore, to build a true interoperable data infrastructure, the report calls for the integration of healthcare data from multiple sources. This would include data collected from EHRs, personal health devices, social media and patient collaborative networks, as well as demographic and environmental information.

In its conclusion the report states: "A robust data infrastructure that can enable a 'Learning Health System,' requires the ability to ingest all the data, keep the data safe, understand it, integrate the data, and communicate the knowledge gained. This concept requires scalability that goes well beyond the interoperability of EHR systems."