Optimizing the Query Performance for Discovering the Diagnosis of Diabetics

Developing healthcare trade's move towards processing huge health records, and to admission entire for exploration and put into action will importantly increases the difficulties. Due to the growing unstructured nature of Big Data form health industry, it is essential to structure and emphasis its size into nominal value with possible solution. Health care management faces many challenges that make us to know the significance to develop the data analytics. Diabetic Mellitus (DM) one of the Non Communicable Diseases (NCD), is a major health hazard in developing countries such as India. The extreme censure is to deal with large dataset with great amount of dimensionality, together in terms of the number of structures the data has, as well the number of rows of data that user is big business with. It can be observed as an automated solicitation of algorithms to discover hidden patterns and to extract information from data. Decision support system to deliver Analytical Processing techniques are used to provide analysis of data. The proposed work aims at the comparison of four algorithms called AK-mode algorithm, K-mode Algorithm, ROCK Algorithm, And MULIC Algorithm. Finally AK-mode Algorithm provides better results compared with the other algorithms. In this paper presents an integrative approach to conclude the diabetic disease from clinical big data. The clinical database is generally redundant, incomplete, dubious and unpredictable. The main objective of integrating is to experiment with different strategies of training data in order to increase the augury accuracy.