A MapReduce Based Distributed Framework for Similarity Search in Healthcare Big Data Environment

Overview & Synopsis

Similarity search in the big data environment is a challenging task. Patient Similarity search (PaSi) is an important issue in healthcare network and data. The results of PaSi search may be highly useful for drawing different conclusions and decisions to improve healthcare systems. Such findings can also be useful for choosing the treatment paths for new patients. In this paper, we propose a MapReduce based framework as a solution to the PaSi problem in the context of a healthcare network imagined to be implemented considering the healthcare centers of India. It is assumed that such a healthcare network will be implemented in future over the Government of India cloud known as GI cloud or ‘MeghRaj’. The paper also discusses the associated implementation challenges of the proposed framework and the query handling approach for the proposed framework to solve the PaSi problem is stated. Finally, the paper outlines the future scope of the work.