Fuzzy Logic-Based Disease Classification Using Similarity-Based Approach with Application to Alzheimer’s

With the advent of the post genomics era, there has been a surge in the amount of medical data for healthcare applications as well as the number of novel solution methodologies. The management and analysis of this data are a tricky task, as the data is scattered over a plethora of public and private repositories. The task becomes challenging if the data exhibits diverse characteristics such as gene information. Finding the gene of interest, causing a certain disease, or understanding the case–control data set is a much daunting task for the researchers. Locating the targeted gene, responsible for causing a certain disease, will depend upon the ability of computational methods. The current software based on these methods uses various statistical tests for performing the intended function. The statistical test used performs univariate classification independently for each gene of interest. To circumvent the uncertainty of the role of each gene independently, fuzzy logic plays a crucial role. It uses similarity-based approach to analyse the data especially real-time data. Therefore, the aim of this work is to demonstrate the use of fuzzy logic for gene identification and disease classification in an efficient manner.