Geisinger researchers share framework for putting a learning health system into practice

While the learning health system, so far, is largely theoretical, researchers with Geisinger Health System lay out a framework for making it a reality within the Danville, Pennsylvania-based organization in an article at eGEMs (Generating Evidence & Methods to improve patient outcomes).

They sought to broaden the scope of previous learning health system models from individual learning activities to apply learning organization-wide, enlisting a group focused on learning made up representatives from clinical operations, administration, research, bioethics, quality and safety, academic affairs and others.

Their framework focuses on nine areas: Data and analytics; people and partnerships; patient and family engagement; ethics and oversight; evaluation and methodology; funding; organization; prioritization; and deliverables.

A realistic assessment of the culture, resources and capabilities related to learning are vital to such an effort, according to the authors.

Among its examples:

  • Data and analytics: A health informatics infrastructure that supports data requirements of multiple stakeholders is vital, the authors say, as is one that captures routine encounter data without disrupting workflow. Geisinger has yet to develop the optimal IT infrastructure for learning, the author say, due to differences in data source, structure, volume and flow across the system. The health system aims to build a culture that continuously informs and shapes the organization's technological landscape to support learning.
  • Patient and family engagement: Patient engagement has been pivotal to changes in biobank consent provisions, and to the development of research projects that address meaningful patient questions, the researchers say. A Patient and Family Advisory Council advises physicians and other practitioners on the delivery of care in a number of areas, including obesity. Geisinger also is one of the OpenNotes initiative study sites, in which patients can see their doctors' clinical notes through a secure patient portal.

"Integration of clinical operations, patients, their families and research activities may be influenced by many factors--including communication, and the misalignment of goals and resources," the authors say. "These factors point to the importance of addressing organizational culture and attitudes toward learning early in the planning process and throughout the system."

Data standards and interoperability are key to developing a learning health system, Holt Anderson, who is heading efforts to develop the governance and policy framework for a stakeholder group known as the Learning Health Community, recently told FierceHealthIT.

The lack of a standard data model poses a potential roadblock for the Patient-Centered Outcomes Research Institute's (PCORI) efforts develop a "network of networks" to further comparative effectiveness research (CER), a Government Accountability Office report recently concluded.

To learn more:
- find the article
- check out the Learning Health Community