Skip to content Skip to navigation

Roadblocks to the Learning Health System

May 20, 2013
| Reprints
Researchers with ImproveCareNow, an EHR-linked multicenter registry, hand out a report card on meeting technical requirements

A few weeks ago I saw a great presentation by Keith Marsolo, Ph.D., who is leading the development of a research data warehouse based on i2b2 at Cincinnati Children's Hospital. His organization is the hub for ImproveCareNow, a 50-care center quality improvement and research network focused on pediatric inflammatory bowel disease.

In this network, clinicians define model care guidelines, develop tools and processes to reduce variation and ensure all patients receive optimal care. (EHR vendors Epic, Cerner, and GE cooperated in creating the data collection forms that allow ImproveCareNow registry data to be captured directly in the HER. They also helped develop the procedures that allow the form responses to be pulled from the EHR so they can be transferred to the registry.)

In his talk at the at the Mid-Atlantic Healthcare Informatics Symposium in Philadelphia, Marsolo addressed the progress the registry has made toward its goal of becoming a “learning health system,” as well as the challenges it still has to overcome in terms of getting already stressed hospital IT staff to work on EHR data extraction and tensions between centralized and distributed data sharing models.

I had been thinking about Marsolo’s presentation recently when by chance I came across a paper he wrote in the online journal eGEMs called “In Search of a Data-in-Once, Electronic Health Record-Linked, Multicenter Registry— How Far We Have Come and How Far We Still Have to Go.” 

I think this paper provides a great service because it involves one of the most advanced examples of a learning health network we have basically giving a report card on how easy or difficult it finds data collection, transmission, processing and analysis in our current healthcare environment. I encourage you to read the entire paper, but its basic point is that while the technology exists to build a robust national learning health system, a multitude of business, political and social roadblocks stand in the way.

In this paper Marsolo notes that participants in ImproveCareNow are fairly representative of subspecialty care at a national scale. And that for each of the necessary elements of the system, “roadblocks range from determining how to fund and use clinical or operational IT infrastructure for research purposes, to untangling the intellectual property issues that arise from interfacing external applications with proprietary EHRs, to developing the governance policies that allow for third-party integration without threatening the stability of the clinical infrastructure or leading to a loss of control.”

“Federal regulations such as Meaningful Use may force a resolution of some of the issues, particularly around the sharing of patient data, but real change will need to come from the health care community itself,” the paper concludes. “We predict that a few enterprising health care centers will conclude that there is a business opportunity in developing and supporting learning health systems and that they will make it a priority to overcome the above barriers. Once they succeed, the rest of the health care community will be forced to play catch-up.”