Just need a research report

Big Data Analytics in Healthcare
Running head: Big Data Analytics
Big Data Analytics
Big Data Analytics in Healthcare    September 16    2018    
    
Contents
Big Data Analytics in Healthcare    3
Abstract    3
Introduction    3
Problem Statement    4
Research Objectives    4
Literature review    5
Financial Analytics Contributing Significantly to Big Data in Healthcare    7
Research methodology    8
Discussion and Future work    9
Conclusions    9
Big Data Analytics in Healthcare
Abstract
The rapidly evolving field of big data analytics has begun to perform a key role in the development of healthcare research and practices. It offers tools to collect, manage, analyze and absorb the vast array of different, structured and unstructured data generated by current healthcare systems. Recently, big data analytics have been applied to help provide the process of care and disease discovery. However, adoption rates and research development in this area are still hampered by some of the fundamental problems inherent in the big data paradigm. This article analyses the process, definition, and use of the big data in medical management. The unstructured data is rising much quicker than the structured and semi-structured data. Almost 90% of the big data is in a form of the unstructured data. The main steps in the management of big data in the medical business are data collection, data management, data storage, data visualization, and data analysis.
Introduction
The debate over big data analytics has taken great interest from industry and academics due to the big data, knowledge, and skills of intellectual extraction. Big data and cloud computing are the two most important trends in defining emerging analytical tools. Big data have applications in various areas such as traffic control, weather forecasting, fraud detection, security, education reform and health care (Agneeswaran et al., 2013). Extraction of information from large amounts of data has become a daunting task. Likewise, big data analysis can be used to make effective decisions in health care through some modifications in the existing Data Learning Algorithm. According to Sutherland and Shan, big data is based on three main characteristics, i.e. volume, velocity, and variation. Various sources (such as astronomy, environmental data, transport data, stock market transactions, censuses, airline traffic, internet images, etc are generating large amounts of data. The rate of data from different sources is called velocity. Variety of different types of data, including text, audio, images, videos etc.
Problem Statement
From a statistical point of view, big data is only small in quantity, but it is likewise very large in the terms of dimensions. Size is also called a feature. Prevailing traditional data mining approaches are difficult to provide useful information. Existing machine learning methods need to be modified to better decision making and data extraction. Recently, due to the rapid growth of data, a trend of healthcare is shifting from the cure to a prevention. Scientists are committed to improving the efficiency and reliability of healthcare systems to minimalize the cost of curing in the healthcare and to provide better medicines for patients. Healthcare systems and Hospitals are good warehouses for patient history, test reports, medical images, and other big data. Handling large amounts of missing values and unstructured data​​is a challenging task. Enhancements in present machine learning and data mining methods have helped to advance personalized medicines that can prevent and cure disease (Chang, 2015). Present traditional machine learning algorithms are suitable for the centralized databases, that requires lots of time to analyze and store large amounts of data. Likewise, storing and processing big data on a single machine is not feasible. So, there is a requirement to parallelize existing methods and use hybrid methods with sufficient capabilities to modify these methods to overcome challenges of processing and storing large data sets in a dispersed environment.
Research Objectives
The study aims to provide health care decision makers with advances in big data analytics that effectively address large and heterogeneous health data sets. In cases where patients are in urgent need of analysis on a mobile device but are not connected to the Internet, it is necessary to perform an analysis locally. If the patient is connected, the data can be transferred to the cloud or server for in-depth analysis. Similarly, various combinations can be identified and some scenarios that will be considered within the scope of the study are listed.
Literature review
According to the study conducted by Hurwitz, Kaufman & Bowles, (2015), health care plays an important role in our society. In order to improve medical efficiency, people's accuracy and quality are the main goals of the government and researchers. Surgery, medicine, healthcare, as well as most other healthcare-related actions have increased considerably and upgraded over the...