An Optimized Integrated Framework of Big Data Analytics Managing Security and Privacy in Healthcare Data

Abstract

Big data analytics has anonymously changed the overall global scenario to discover knowledge trends for future decision making. In general, potential area of big data application tends to be healthcare, where the global burden is to improve patient diagnostic system and providing patterns to assure the privacy of the end users. However, data constraints exists on real data which needs to be accessed while preserving the security of patients for further diagnostic analysis. This advancement in big data needs to addressed where the patient right needs to maintained while the disclosure of knowledge discovery for future needs are also addressed. To, embark and acknowledge the big data environment its adherently important to determine the cutting-edge research which can benefit end users and healthcare practioners to discover overall prognosis and diagnosis of disease while maintaining the concerns for privacy and security of patient data. In current state of art, we tried to address the big data analytics approach while maintain privacy of healthcare databases for future knowledge discovery. The current objective was to design and develop a novel framework which can integrate the big data with privacy and security concerns and determine knowledgably patterns for future decision making. In the current study we have utilized big data analytical technique for patients suffering from Human Immunodeficiency Virus (HIV) and Tuberculosis (TB) coinfection to develop trends and detect patterns with socio economic factors. Further, a novel framework was implemented using unsupervised learning technique in STATA and MATLAB 7.1 to develop patterns for knowledge discovery process while maintain the privacy and security of data. The study overall can benefit end users to predict future prognosis of disease and combinatorial effects to determining varied policies which can assist patients with needs.