Data Mining of Association between Hyperuricemia and Common Chronic Diseases Based on Evolutionary Apriori Algorithm (EAA)

With the rapid development of medical information, a large amount of medical data has been generated, which contains huge potential information. Data mining is widely used to discover hidden information in these large amounts of data. This application can promote the transformation of diagnosis and treatment mode of chronic diseases from medical research, clinical decision-making, disease early warning. In this paper, we take the hyperuricemia as the research object. An optimized Apriori Algorithm has been proposed to mine the correlation model of chronic diseases related to hyperuricemia in order to provide a basis for the precise treatment of hyperuricemia. An associated relation is proposed according to the experiments, which could apply an auxiliary support to doctor's clinical diagnosis and disease research in the local. The evaluation experiments of performances demonstrate an efficient performance for the proposed algorithm compared with the original Apriori Algorithm.