Automatic construction of Fuzzy Inference Systems for computerized clinical guidelines and protocols

Abstract

Clinical guidelines and protocols (CGPs) are standard documents with the aim of helping practitioners in their daily work. Their computerization has received much attention in recent years, but it still presents some problems, mainly due to the low sustainability and low adaptability to changes (both in knowledge and technology) of the computerized CGPs. This paper presents an approach to an easy and automatic creation of Fuzzy Inference Systems (FISs), which are suitable for the computerized interpretation of differential diagnoses. The proposed FIS development process is based on applying Model-Driven Software Engineering techniques: automatic generation of computer artefacts and separation of concerns. The process focuses on the separation of roles during the design stage: domain experts use a basic editor that allows them to define the categories and factors that will be involved in the FIS in natural language, while knowledge engineers at a later stage refine these elements using a more advanced editor. The whole system has been tested by automatically generating two FISs that have been included in a computerized CGP for the diagnosis of a rare disease called hyperammonemia. This CGP has been validated and it is currently in use.