Recognition-Based Diagnostic Reasoning

Abstract

Expertise in fault diagnosis often depends on recognizing particular patterns in observed data corresponding to situations that have prev10usly been seen and correctly interpreted . This approach can result. m significant efficiencies by avoiding a costly and detatled analysis based on the causal rel':'t10nships between faults and observable data. Recogrullon-based reasoning requires highly focused search strategies in order to extract relevant information from a knowledge base that contains a large number of prototyp es for various possible faults. This paper describes a model of recognition-based reasoning and descnbes ~ Implementation of the model. designed to solve diagnostic problems in pediatric cardiology. The model . first analyzes portions of the patient data to hypothe .slze a small set of potential diseases. Knowledge specific to each selected hypothesis is then used to refine these initial choices . The model has been validated against actual hospital cases and performs in a manner comparable to expert physicians.