Diabetes Mellitus Prediction in Big Data-Using Hadoop / Map Reduce Frame work (Survey)

Abstract

Diabetes Mellitus disease prediction is a growing research in healthcare. More over number of data mining methods have been applied to evaluate the main causes of diabetes, but only small sets of clinical risk factors are considered. So the results generated by such methods may not represent exact diabetes. We have to analyse number of factors such as Hereditary and genetics factors, Stress, Body Mass Index, Increased cholesterol level, High carbohydrate diet, Nutritional deficiency, Nature of Exercises, Tension and worries, High blood pressure, Insulin deficiency, Insulin resistance. Then we evaluate and compare this system using suitable rules and Map Reduce algorithm. The performance of the system is assessed in terms of different parameter like rules used, classification accuracy, and classification error. By considering all these parameters, the system can predict diabetics in a great accuracy. Also this paper surveys about different techniques and tools available in Big Data to predict Diabetes mellitus. Big Data can significantly diabetes research and ultimately improves the quality of health care for diabetics patients.