Big Data Analytics for Healthcare Services Using C4.5 Algorithm on Map Reduce

Abstract

Healthcare industry is an ever-increasing rise in the large amount of records such as doctors, patients, medicines and medical history. Although previous medical records are beneficial for not only individual but also human society, maintaining and analyzing large amount of such data is a big problem. Traditional data mining tools are inadequate for such amount of data. Big data analysis can be used in various applications with different domains like education, security and health care. This system uses MapReduce based C4.5 Decision Tree algorithm for health care big data to manage, analyze and extract the most suitable data for right conditions. The classification rules produced by this system can be used to classify the particular disease. Tuberculosis disease is used as a case study in the system.