An epistemological framework for medical knowledge-based systems

An abstraction paradigm for unifying different perspectives concerning the analysis and design of knowledge-based systems (KBSs) is presented. The model accounts for all of the conceptual features of knowledge-based systems, thus making clear which features are intrinsic to the problem and which are artifacts of the implementation. The proposal is based on a two-level analysis of knowledge-based systems: an epistemological and a computational level. At the first level, ontology and inference models of a knowledge-based system are defined. At the computational level, methods and formalisms are adopted after the epistemological analysis has been carried out. The study is confined to medicine with three generic tasks identified: diagnosis, therapy planning, and monitoring. The results of this analysis indicate that the generic tasks manage different ontologies, but can be executed exploiting a unique inference model. Computational issues are discussed to argue that the model provides a conceptual view on existing systems and some design insights for future ones