Hadoop-Based Distributed Computing Algorithms for Healthcare and Clinic Data Processing

摘要

There exit a huge demand on utilizing big data technology to process healthcare related patients data for healthcare information extraction and medical knowledge discovery. In this paper, we briefly review the demands and application potentials using big data technology with an emphasis on common challenges. After briefly addressing the Hadoop/MapReduce code components and modules, we use a simple clinic data to demonstrate how to map and reduce on small dataset with illustrated workflow. We give simple scenario of using other MapReduce calculation modules for counting and classification. This serves as a basic step into future utilization of big data to healthcare domain.