Bipolar fuzzy TOPSIS and bipolar fuzzy ELECTRE-I methods to diagnosis

Abstract

Medical diagnosis is the process of determining which disease or condition explains a person’s symptoms or signs. The complexity and uncertainty of diagnostic information make the diagnostic process difficult to accomplish. Many theories concerned with medical diagnosis such as fuzzy set theory, rough set theory and soft set theory are presented in the past. We are concerned with bipolar fuzzy multi-criteria decision-making (MCDM) methods. The main purpose is to provide guidance for determining a patient’s health status and evaluating the factors influencing that status in bipolar fuzzy environment. Bipolar fuzzy set theory offers a useful tool for developing knowledge-based systems in MCDM methods. Since the diagnosis of an appropriate disease involves bipolar judgement, we utilize bipolar fuzzy Technique for the Order of Preference by Similarity to Ideal Solution (TOPSIS) and YinYang bipolar fuzzy Elimination and Choice Translating Reality (ELECTRE) in medical diagnosis, where the various diseases for various symptoms and weights of various symptoms are assessed using bipolar fuzzy information and fuzzy information, respectively. Comparison of BF-TOPSIS and BF-ELECTRE-I is presented. The illustrated methods demonstrate the practicability, feasibility and sustainability of diagnostic process. BF-TOPSIS gives one diseases as diagnosis, whereas BF-ELECTRE-I gives the set of diseases as diagnosis. Moreover, the comparison analysis demonstrates which diagnostic process is more credible and accurate. This article presents two powerful MCDM techniques for the diagnosis of a disease in which the pairwise comparison of diseases and symptoms is considered in bipolar behavior.