Employing Hybrid Reasoning to Support Clinical Decision-Making

Abstract

Clinical reasoning, involving abstraction, abduction, deduction, and induction, is the primary tool that physicians use when making clinical decisions. To support them, we focus on the creation of an AI system that is able to emulate clinical reasoning. We leverage Semantic Web technologies to perform a set of AI tasks involving the various forms of inference associated with clinical reasoning strategies. In particular, for the scope of this work, we focus on clinical problems that require differential diagnosis techniques. For a given clinical scenario, overlapping reasoning types and strategies may be employed by a physician in conjunction, signifying the need for our AI system to perform hybrid reasoning. Therefore, we consider the construction of a hybrid reasoner that is compatible with description logics. For medical scenarios where description logics may not have some needed expressivity, we consider possible extensions that will allow for the representation of such a scenario. The reasoning system, clinical rule representation, and the resulting recommendations will be evaluated based on domain expert consultation in order to determine whether the recommendation aligns with what the expert would recommend.