Big data modelling for predicting side-effects of anticancer drugs: A comprehensive approach

Abstract

Data Analytics is at the cutting edge of technology in areas where data is evolving widely and rapidly. This involves handling large volume of data, called Big Data with a wide variety of properties. Handling big data involves organizing and analyzing data. Many tools with different environments have evolved in recent times in handling big data. Few of them can accommodate structured or semi structured data. At a glance, using various Hadoop components Big Data can be scaled and handled. In this concern Big Data must be modelled before performing analytics which is imperative. Models were proposed for organizing big data, but most of them are conceptual. These models never declared a unified model for implementing big data. Moreover very few could quantify that object oriented relational data model can be used for organizing big data. As such it is not feasible to organize semi-structured and unstructured data, as big data is not limited to structured data alone. Big data analytics plays an important role in Healthcare sector where huge amount of data needs to be analyzed and the conclusion drawn. As Health data is increased by leaps and bounds the role of big data has also received greater importance. Hence this paper proposes an approach for modeling big oncology drug related data in Healthcare sector which implements analytics in optimal way. This model can be useful to young oncologist which brings years of experience in hand.