Intelligent Medical Diagnosis Reasoning Using Composite Fuzzy Relation, Aggregation Operators and Similarity Measure of q-Rung Orthopair Fuzzy Sets

Abstract

Medical diagnosis is the process of finding out what is the disease a person may be suffering from. From the symptoms and their gradation, the doctor can decide which the dominant disease is. Nevertheless, in the process of medical diagnosis, there is ambiguity, uncertainty, and a lack of medical knowledge that can adversely affect the doctor’s judgment. Thus, a tool of artificial intelligence, fuzzy logic, has come to enhance the decision-making of diagnosis in a medical environment. Fuzzy set theory uses the membership degree to characterize the uncertainty and, therefore, fuzzy sets are integrated into imperfect data in order to make a reliable diagnosis. The patient’s medical status is represented as q-rung orthopair fuzzy values. In this paper, many versions and methodologies were applied such as the composite fuzzy relation, fuzzy sets extensions (q-ROFS) with aggregation operators, and similarity measures, which were proposed as decision-making intelligent methods. The aim of this procedure was to find out which of the diseases (viral fever, malaria fever, typhoid fever, stomach problems, and chest problems), was the most influential for each patient. The work emphasizes the contribution of aggregation operators in medical data in order to contain more than one expert’s aspect. The performance of the methodology was quite good and interesting as most of the results were in agreement with previous works.