By Mary Agnes Carey, CQ HealthBeat Associate Editor
January 29, 2007 -- President Bush's fiscal 2008 budget request will include new funding to build an electronic "rapid learning" health care network, said Carolyn Clancy, director of the Agency for Healthcare Research and Quality (AHRQ).
The network would use the resources of individual data repositories at health plans and other large health systems, allowing "researchers to benefit from an extensive web of databases, without needing access to individual patient information or [creating] a mega central repository," Clancy said Friday at a Health Affairs forum.
"Health plans and other large health systems are already using their data systems to generate evidence as a natural byproduct of health care delivery," Clancy said. "Through this new partnership for effective health care, findings would be generated from these multiple sources and combined to produce more complete and powerful information."
Health information technology, or health IT, can make health information available when and where it's needed, reduce medical errors, and improve the physician–patient relationship, and it can also help medical professionals learn more about particular illnesses and how to treat them, Clancy and other speakers at the forum said.
"In the clinic, it can give providers real-time feedback to help them continually improve the effectiveness of their care," Clancy said. "In the community, it can help bring together stakeholders to look at patient outcomes and work toward improvement. And on the broadest level, it has the potential to be a kind of information 'nervous system,' enabling us to learn directly from the health delivery system itself."
Lynn Etheredge, a consultant with the Health Insurance Reform Project at George Washington University and author of the lead paper in the journal Health Affairs' special edition focusing on "a rapid-learning health system," said it was critical to use health IT to learn "as much as possible, as soon as possible" to speed medical discoveries and cures.
"In the current world of medical research, it takes several years to see if your first hunch or hypothesis was right," Etheredge said.
A "rapid-learning" health system could also use data to help determine why health costs are increasing, analyze the comparative benefits and risks of prescription drugs and medical treatments, and help determine why there are wide variations in how one treatment impacts one patient versus another, Etheredge said.
David Eddy, the founder and medical director of Archimedes Inc., said electronic medical records can be used not only to determine what has happened in the past as is currently happening, but also to build models that help predict what is likely in the future.
"With better data we can build better models," Eddy said, adding that such models also can be used to create virtual clinical trials that will speed up the research and development process of new drugs.
In a paper distributed at the event, Eddy noted that "data from EMRs can be invaluable for this purpose and can indeed put rapid learning on turbo."