Why Big Data and What Is It? Basic to Advanced Big Data Journey for the Medical Industry

Abstract The idea of big data is mainly reflected in its dimensions, which are popularly known as the Big Vs, which stands for Volume, Variety, Velocity, and Veracity. However, the concept goes beyond the Big Vs and testing of hypotheses, to focus on data analysis, hypothesis generation, and ascertaining the progressive strength of association. Preliminary study reveals that big data analytics adopts many data mining methods, such as descriptive, diagnostic, predictive, and prescriptive analytics. This evolving technology has tremendous application in healthcare, such as surveillance of safety or disease, predictive modeling, public health, pharma data analytics, clinical data analytics, healthcare analytics, and research. Moreover, the journey of big data in the medical domain is proving to be one of the important research thrusts of recent times. Study reveals that medical data is very specific and heterogeneous due to varied data sources such as scanned images, CT scan reports, doctor prescriptions, electronic health records (EHRs), etc. Medical data analytics faces some bottlenecks due to missing data, high dimensions, bias, and limitations of the study of patients through observation. Therefore, special big data techniques are required to handle them. Besides, many ethical, legal, social, clinical, and utility challenges are also a part of the data-handling process, which makes the role of big data in the medical field very challenging. Nevertheless, big data analytics is a fuel to the healthcare system that will provide a healthier life to patients; the issues and bottlenecks when removed from the system will be a boon for the entire human race. The chapter focuses on understanding the big data characteristics in medical big data, medical big data analytics, and its various applications in the interest of society.