“By harnessing all of this vast data on disease and patient experiences in real time, rapid learning is giving us the tools and knowledge to develop optimal treatments for things like cancer and get them into the hands of doctors and patients in ways that will make a meaningful difference in outcomes.”—Lori Melichar, Senior Program Officer, RWJF
Dates of Project: August 2005 through December 2013
“To control costs, you want to promote prevention and use of the most cost-effective treatments and strategies. Why don’t we use cost-effective treatments and strategies? We don’t have any way of producing evidence-based quality care that can diffuse rapidly through the health care system.”—Nancy Barrand, Senior Program Adviser, RWJF
Description: Lynn Etheredge and Judith Moore at George Washington University, working with many collaborators, developed, promoted, and spread the concept of a rapid-learning health system, which involves analyzing information from large databases of electronic patient data (with personal identifying information removed) to continuously improve the quality, safety, and cost-effectiveness of medical technologies, medications, procedures, and health policies.
“The objective of a rapid-learning health care system is simply to learn as fast as possible about what is the best treatment for each patient—and deliver it.”—Lynn Etheredge
Through journal articles, white papers, reports, and blogs; planning meetings, conferences, and workshops and presenting at them; and collaborations with federal health policy staff and medical and health care experts, Etheredge and his network generated interest and large national investments both in a rapid-learning health system in general, with a new clinical research system of more than 100 million patients, and in rapid-learning projects in cancer, pediatrics, and Alzheimer’s disease.
Rapid learning is now part of the lexicon of researchers, health systems, government agencies, medical specialty societies, and other organizations, and rapid-learning ideas, investments, and initiatives are becoming part of—and starting to transform—mainstream health care.
Etheredge LM. “Rapid Learning: A Breakthrough Agenda.” Health Affairs, 33(7): 1155–1162, 2014. Available online.
Etheredge LM. “Creating A High-Performance System for Comparative Effectiveness Research.” Health Affairs, 29(10): 1761–1767, 2010. Available online.
Etheredge LM. Health Affairs special issue, “A Rapid-Learning Health System,” January 2007. Available online (scroll down to 26 January 2007).
- The Center for Medicare & Medicaid Innovation Center, with $10 billion of new funds, to rapidly research, test, and disseminate better models for health care payment and service delivery
- The Patient-Centered Outcomes Research Institute, with $650 million per year–and a national system of new learning networks designed to include 100 million patients–to fund and disseminate comparative effectiveness research (comparing different ways to diagnose, prevent, treat, or monitor disease)
- The National Institute of Health’s Big Data to Knowledge (BD2K) initiative to develop standardized policies, practices, software, and competencies to improve researchers’ access to biomedical data
The American Society of Clinical Oncology is now implementing CancerLinQ™ (Learning Intelligence Network for Quality), a rapid-learning network for cancer care proposed by Lynn Etheredge (see RWJF video “A Rapid Learning System Prototype.”
The National Pediatrics Learning Network, part of the Patient-Centered Outcomes Research Institute, is developing a clinical data research infrastructure for research collaboration to improve pediatric health and health care delivery.
- Rapid Learning Project January 30, 2013
- Expanding a Biorepository at Kaiser Permanente September 17, 2012
- Project ECHO: Bridging the Gap in Health Care for Rural and Underserved Communities April 24, 2014
- Using Mathematical Modeling to Make Informed Decisions on Health Care Alternatives January 16, 2013
- About this grant
Rapid-learning health systems speed up knowledge generation from big data and adoption of best practices.