An Ontological Model for Artificial Reasoning

Application to Medical Diagnosis

Abstract

Representing knowledge in a language that is both understandable by humans and easily exploitable by machines remains the subject of several research studies. Domain ontologies are recognized as an efficient way to describe knowledge through concepts and relations in several domains of expertise while remaining shareable and reusable. This paper aims to propose an approach for “artificial reasoning” that we consider as a foundational pillar for “Artificial Intelligence.” Our particular interest in this work is on how to design systems that can use human knowledge to process and solve the complex problem of diagnosis, given the required expertise in a specific domain of knowledge. The approach we present in this paper is based on using properties of ontologies, by representing expert knowledge through a graph reasoning model, to formalize the diagnosis process using an ontology-based model. We first describe our proposal on how to represent expert knowledge in a general way before focusing on the diagnosis problem. Finally, we apply the whole process to the specific domain of cardiology.