A new medical diagnosis method based on Z-numbers

摘要

Handling uncertainty in medical diagnoses is an open issue. In this paper, we present a new decision-making methodology based on Z-numbers. First, experts’ opinions are represented by Z-numbers. A Z-number is an ordered pair of fuzzy numbers denoted by Z = (A, B). We then propose a new method for ranking fuzzy numbers. Based on this ranking method, we present a novel method for transforming Z-numbers into basic probability assignments. This allows information from different sources to be combined by Dempster’s combination rule, and results in more reasonable decision making because of the advantages of information fusion. Finally, two experiments on risk analysis and medical diagnosis illustrate the efficiency of the proposed methodology.