ONC is excited to announce “Using Machine Learning Techniques to Enable Health Information Exchange to Support COVID-19-Focused PCOR,” a Patient-Centered Outcomes Research (PCOR) Trust Fund project implementing new technologies and standards to unlock the potential for health information exchanges (HIEs) to support research.
This project will pilot the use of a novel, privacy-preserving machine learning technique called split learning in several HIEs to understand its applicability and suitability for widespread adoption by HIEs. The use of the privacy-preserving split learning technique will test the ability to use HIE data for research at the individual HIE level and across multiple HIEs. It will also demonstrate a new method for PCOR researchers and a capability that can be adopted by HIEs across the nation.
Preliminary work for this project was completed in 2021 and included defining technical criteria for evaluating HIE readiness, specifying implementation requirements, and detailing actions to develop the split learning model. Next, HIEs interested in working with ONC will be selected. We anticipate providing regular updates to the community on the progress of the work, including any challenges we encounter along the way.
Health Information Exchanges are Key Partners in Research
As we’ve written before, research drives advances in health care, from one individual’s diagnosis to broader public health assessments. The amount of data now available for these types of analyses is greater than ever before, whether from an electronic health record (EHR), a personal device, or environmental sensors. While research is just the first step in a process that leads to improved health outcomes, researchers can now use many different types of data sources to inform their work.
State and local HIEs, which in aggregate receive EHR data from more than 60 percent of U.S. hospitals, could be better used as a source of patient-level electronic health data for large-scale research. HIEs routinely collect patient data from a variety of sources and then facilitate the exchange of patient health information with clinicians, public health agencies, and laboratories. Increased use of this data for patient-centered research could help facilitate research activities, including in public health emergencies such as COVID-19. However, varied technical and privacy requirements often put in place by states can make it difficult for HIEs to make data easily usable for researchers.
An Approach to Sharing HIE Data with Researchers in Privacy Preserving Manner
Participating HIEs will be able to take advantage of the anticipated implementation of ONC’s Cures Act Final Rule, including being able to access electronic health information from participating providers using a certified Health Level Seven International® (HL7®) Fast Healthcare Interoperability Resources® (FHIR®) application programming interface (API) and the United States Core Data for Interoperability (USCDI). The innovative use of the FHIR API standards including HL7® Bulk FHIR® API to deliver value in health care has never been greater and we hope that this project lays the ground for further innovation by the research community.
We are excited about the new phase of this project and look forward to sharing more information as it progresses!
This post was originally published on the Health IT Buzz and is syndicated here with permission.