A Pythagorean Fuzzy CRITIC MAUT Decision Framework for Disease Diagnosis under Uncertain Clinical Data

Abstract

Clinical information is often incomplete, vague, and uncertain, and the diagnosis of disease is a difficult task for accurate decision making. Multi-Criteria Decision-making (MCDM) is a range of decision-making methods that have been extensively used in healthcare, but most methods have the following problems: They use subjective criterion weights, they are not good at expressing hesitation and uncertainty, and they do not have integrated objective criterion weights and a utility-based ranking mechanism. To resolve these drawbacks, this research introduces a novel Pythagorean Fuzzy CRITIC MAUT decision framework for the diagnosis of a disease in the case of uncertainty in clinical conditions. The proposed framework incorporates Pythagorean fuzzy sets (PFS) to effectively model uncertainty and hesitation, uses the CRITIC method to determine the weights of the criteria objective based on the variability of the data and inter-criterion correlation, and finally applies the multi-attribute utility theory (MAUT) to assess and rank the disease alternatives based on their utility values. The proposed framework is applied to a numerical case study with four disease alternatives. The results indicate that the alternative ( ) has the highest value of the integrated utility  and is the most preferred disease alternative, followed by ( )  and ( )  and ( )  respectively. The results showed that the proposed framework can effectively distinguish between the various disease options, minimize subjective influences, and offer a clear, objective, and accurate decision-support system. Thus, the proposed model is very promising in helping clinical decisions in uncertain clinical settings.