Verification of clinical guidelines encoded into knowledge-based DSSs

The empowerment of medical practices, in terms of consistency, effectiveness and efficiency, is being more and more pushed by the encoding of clinical practice guidelines in advanced decision support systems (DSSs). A prerequisite for their wide application is the guarantee of a high level of maintainability and reliability, with respect to different kinds of structural anomalies which can occur in the encoded guidelines and could compromise their practical value. This paper presents a verification approach, based on a formal taxonomy, devised to check the reliability of clinical guidelines encoded as rules. Its final goal is determining two categories of potential structural anomalies, i.e. inconsistency or redundancy, in a very general and understandable fashion. The approach has been developed within the EU IST CHRONIOUS Project, devoted to define a generic platform for remotely monitoring the health status of chronic patients. A sample set of clinical rules pertaining a specific chronic pathology, i.e. Chronic Kidney Disease, has been considered for its initial validation, showing its feasibility and efficacy in a real healthcare case.