A longstanding informatics challenge has been to develop efficient mechanisms whereby valid medical knowledge - such as that contained in practice guidelines - can be operationalized in systems that support decision making by clinicians. However, a frustrating impediment to the satisfaction of this goal has been the difficulty of translation of guideline knowledge into computable formats. In this competing renewal application we propose a research program that will extend successful accomplishments. 1. Recognizing that vague and ambiguous recommendations impede both guideline implementation and adherence, we will model and characterize the forms of ambiguity and vagueness that are prevalent in guideline statements, ascertain the degree to which such statements lead to clinical uncertainty, and identify methods to diminish this uncertainty. 2. In collaboration with the American Academy of Pediatrics and the American Academy of Family Physicians, we will develop, install, and evaluate software tools that support efficient authoring of scientifically valid and implementable guidelines. Working with the national professional societies offers an opportunity to move the tools and techniques developed in the last grant period into the real world where they will be evaluated and iteratively improved. 3. We will facilitate implementation of guideline knowledge by developing tools to help translate natural language recommendations into formal rules and apply a framework based on action-types to design reusable implementation strategies that can be used at national and local levels. 4. We will modify and further extend the Guideline Elements Model to accommodate concepts that are critical for guideline document modeling, authoring, and implementation activities. We will create an XML Schema and provide capabilities to current users to assure their GEM files remain compatible. Furthermore, we will submit the new model as a proposed standard to HL7 and/or ASTM. A systematic process for translating guideline knowledge into operational decision support systems can have substantial benefits for delivery of high-quality, evidence based health care. In addition, the proposed activities focus on systems that will preferentially impact children - a particularly vulnerable population.
Showing the most recent 10 out of 19 publications
