A Fuzzy Logic Based Decision Support Framework for Medical Diagnosis and Sustainability Analysis of Neurological Disorders Using Analytical and Algorithmic Modeling

Susceptibility analysis is a useful technique that aids medical professionals in diagnosing and treating brain tumours as well as determining the severity of a patient’s suspected brain tumor. This approach has proven particularly beneficial in developing countries with limited resources and medical facilities. By utilizing set-based operations of an arithmetical model, specifically the fuzzy parameterized complex intuitionistic fuzzy hypersoft expert set (FPCIFHSES), this study seeks to develop a reliable multi-attribute decision support system for evaluating patients’ susceptibility to brain tumors. The FPCIFHSES is thought to be more dependable and comprehensive when managing information-based challenges due to its intricate components and fuzzy parameterization, which are intended to address the data’s periodic form and unclear characteristics (sub-characteristics), correspondingly. Based on the professional judgements of experts, the suggested FPCIFHSES-susceptibility framework approximates certain appropriate forms of brain tumours in terms of the most pertinent signs (characteristics) in units of complex intuitionistic fuzzy numbers (CIFNs). The scores for these kinds of cancers are calculated using a core matrix that connects them to fuzzy parameterized multi-argument-based pairs once the fuzzy parameterized values of the multiargument- based tuples have been determined and the CIFNs have been converted into fuzzy values. The membership of score values in [0, 1] is used to assess a patient’s susceptibility.