Survey on map reduce based apriori algorithms in medical field for the prediction of diabetes mellitus

摘要

Now-a-days, Health care has become very expensive and greatest concern for everyone. With the changes in lifestyle, food habits andreduction in physical activities, most of the people are suffering with the attack of chronic diseases. Among several chronic diseases,Diabetes Mellitus was identified as one of the most common chronic disease being suffered by the people of all ages. Particularly, in India,the prevalence of diabetes mellitus is very high in number and the numbers are increasing at an alarming rate. In general, most of thepeople notice the diabetes at the advanced stages which creates complications thereafter. Always early detection of diseases during prediabeticstage is highly recommended. Further, with the usage of Electronic Health Records and Electronic Medical Records by healthcarepractitioners, it is possible to detect the disease during the initial stages. But, the only problem is the storage and maintenance of digitalhealth records which is growing at an exponential rate resulting the Big Data. The processing and analysis of big data requires distributedenvironment known as Hadoop. Our study is to predict the diabetes mellitus and its risk factors and also help the practitioners in makingstrategic decisions using data mining techniques in the Hadoop environment. As part of survey, in this paper, we report and describevarious MapReduce based Apriori algorithms and their performance measures.