Implementation of a "real-world" learning health care system: Washington State's Comparative Effectiveness Research Translation Network (CERTAIN).

Abstract

Learning health care systems apply the experiences of prior patients to inform care and help to guide decision making for current patients. These systems should help to deliver more effective, efficient, and appropriate care. Most examples of learning systems derive from integrated care delivery systems and examples of such systems in the community at large have been lacking. The comparative effectiveness research translation network (CERTAIN) is a learning system bringing together hospitals and outpatient clinics across Washington State. CERTAIN leverages existing medical record-based data collection taking place at nearly all statewide hospitals and links this data collection with patient-reported information about function and quality of life. We have described the components of the CERTAIN infrastructure, the elements of a pilot project evaluating treatments of claudication, and the opportunities and challenges of developing and implementing a "real world" learning system. Examples in the areas of vascular disease, spine care, gastrointestinal disease, and urology. Learning health care systems face many operational challenges but hold great promise for discovery and implementation of more effective clinical practices.