Incoporating Data Mining Applications into Clinical Guildelines

Computer based clinical guidelines have been developed to help caregivers in practicing medicine. GLIF3 (Guideline Interchange Format 3) is one of several standards that specify the structure for defining guideline models. The decision making steps within the GLIF3 guidelines are limited to evaluation of basic logic expressions. On the other hand, data mining analyses aim at building descriptive or predictive mining models that contain valuable knowledge. However, this knowledge can not be represented using the current guideline specification standards. In this paper, we focus on encoding and sharing the results obtained from a data mining study in the context of clinical care and hence to make it available at the point of care. For this purpose, we investigate available standards to encode the mining results in an interoperable manner and then elaborate on how to incorporate them in the context of guideline-based clinical decision support systems, and in particular GLIF3 models. Finally, we demonstrate the proposed approach using a developed prototype tool for modeling and execution of knowledge-assisted guideline