Characteristics and classification of big data in health care sector

Abstract

Information technology has advanced during the last five decades to the stage where its impact is being felt by the society in every service that it gets from media, business, health care, consumer electronics, energy and power, and transportation domains. During this course of human-technology interaction enormous amount of data and knowledge transfer takes place directly between service providers and their clients, as well as indirectly between clients. Because human tendency is to “analyze” its past in order to predict the “future”, keeping track of this dynamically streaming voluminous heterogeneous data, called Big Data (BD), and analyzing it for meaningful discovery of knowledge that leads to value-added business becomes an important research activity. It is in this context that research in Big Data (BD) computing has emerged. Meaningful decisions can be based only on significant knowledge discovery, which in turn requires a good understanding of the characteristics of the accumulated data, an appropriate classification of this huge collection, and an efficient analysis of it. Health care sector is a critical infrastructure because its services affect the lives of humans and the lack of service continuity may be disastrous to the economy and human lives. The large amount of data collected by this sector from its clients is structured into Electronic Health Records (EHR) which is BD, and is used along with pharmaceutical and regulatory data in providing health services. More BD is generated while administering services and measuring their impacts on clients after administering the services. It is in this larger context that we investigate the types and sources of Health Care BD (HBD), its characteristics, and give a classification of it.