Diabetes Prediction Methodology on the Synthesis of Big Data – Hadoop Cluster

Abstract

            Big Data is a one of the new technology that widely applied in research settings for number of fields. By considering all applications of Big Data we cannot neglect the Health care are. It has the great power to analyse the cause of many disease. In this paper we are focusing on the prediction of diabetes. Healthcare data are being generated at very increasing manner. In this situation big data and its analysis tools have major role in prediction the cause of diabetes. In this paper we are showing, what are the methods to connect diabetes prediction and big data tools? While predicting diabetes we need to consider the clinical parameters as well as nonclinical parameters. For an example, diet of a patient has an important role in the cause of diabetes of a person [1]. For the better treatment of diabetes we must collect and analyse all the causes of diabetes. The periodically or regularly high amounts of data are the sole of Big Data. Increased use of smart devices such as smart phone or any other smart devices cheaply exploits digital health technology. We can use this data for the research purpose [2].  We can combine number of big data tools for the purpose.