Decision support system for the differential diagnosis of breast disease

Abstract

The histopathological diagnosis of breast disease is representative of many problems of differential diagnosis encountered in the medical domain. It requires highly trained and experienced experts and is characterized by a large number of features whose presence or absence involves much uncertainty. Computer-based decision support systems intended to function in a consultative capacity during differential diagnosis have had limited success for two fundamental reasons. Firstly, they take an autonomous role and assume that the user has no contribution to make to the problem-solving process. Secondly, the established techniques for representing and reasoning with medical knowledge are of limited suitability in this domain. Such systems are unable to reach a correct diagnosis quickly and often subject the user to a cumbersome dialogue. These are not tolerated by pathologists working under severe time constraints. We first look at the problem-solving methods employed by pathologists in this domain and examine the functionality of traditional expert system methodologies. We then present a cooperative design which allows the pathologists to express his or her ideas within a decision support system whilst gaining assistance in required areas. A novel inference technique based upon the set partitioning technique in hypergraphs is also described. This mathematical method has the ability to cope with the incomplete or inadequate knowledge which is a characteristic of breast disease, whilst directing data gathering in a meaningful manner. In particular this approach can significantly reduce the amount of irrelevant data which the pathologist must enter before a conclusion is reached. Thus it can potentially improve the efficiency and user acceptability of medical expert systems.