Big Data Analytics and Intelligence

A Perspective for Health Care

Poonam Tanwar, Vishal Jain, Chuan-Ming Liu, Vishal Goyal, Poonam Tanwar, Vishal Jain, Chuan-Ming Liu, Vishal Goyal

• Publisher: Emerald Publishing Limited
• Year: 2020
• ISBN:
  9781839091018
• Topic: Business
• Subtopic: Information Management
• Index: Business

Big data is a field of research that is growing rapidly, and as the Covid-19 crisis has shown, health care is an area that could benefit greatly from its increased use and application. Big data, as derived partly from the internet of things and analysed according to specific algorithms, has a large and beneficial role to play in preventative medicine, in monitoring the health of specific groups, and in improving diagnostics.
Big Data Analytics and Intelligence: A Perspective for Health Care focuses on various areas of health care, ranging from nutrition to cancer, and providing diverse perspectives on all of them. This book explores the entire life-cycle of big data, from information retrieval to analysis, and it shows how big data's applications can enhance, streamline and improve services for patients and health-care professionals. Each chapter focuses on a specific area of health care and how big data is applicable to it, with background and current examples provided.

Chapter 1

Big Data Analytics and Intelligence: A Perspective For Health Care

K. Kalaiselvi and A. Thirumurthi Raja

Abstract

Big Data is one of the most promising area where it can be applied to make a change is health care. Healthcare analytics have the potential to reduce the treatment costs, forecast outbreaks of epidemics, avoid preventable diseases, and improve the quality of life. In general, the lifetime of human is increasing along world population, which poses new experiments to today’s treatment delivery methods. Health professionals are skillful of gathering enormous volumes of data and look for best approaches to use these numbers. Big data analytics has helped the healthcare area by providing personalized medicine and prescriptive analytics, medical risk interference and predictive analytics, computerized external and internal reporting of patient data, homogeneous medical terms and patient registries, and fragmented point solutions. The data generated level within healthcare systems is significant. This includes electronic health record data, imaging data, patient-generated data, etc. While widespread information in health care is now mostly electronic and fits under the big data as most is unstructured and difficult to use. The use of big data in health care has raised substantial ethical challenges ranging from risks for specific rights, privacy and autonomy, to transparency and trust.

Keywords: Patient predictions; electronic healthcare records; telemedicine; medical imaging; patient engagement; predictive analysis; enhance security

1. Introduction

The concept of enormous data generated from various sources has been accepted and implemented by a lot of information technology-based organizations nowadays. It helps various organizations to understand that capturing and storing all the data that is being generated within the organization can be beneficial in the future and can get useful insights. Few of the most important advantages that can be gained with the help of using these generated data after analyzing are that it helps in increasing the speed and quality of work in the working environment. Since big data enables the working environment faster and agile it gives the particular organizations a competitive edge and uniqueness from other business organizations.

The implementation of big data analytics in any organizations lets them take a step forward in securing their important data. Hence the data can be used in later stages to identify new opportunities. This helps in building a better organization and takes an appropriate business decisions which will help in attaining more profits and making the customers much happier. The various importance of big data include as follows. Another important feature of big data is that it not only helps in understanding enormous data but also helps in reducing the cost incurred in various ways. By implementing big data technologies and various data manipulation tools it helps in achieving cost advantages. It also ensures that a large amount of collected data can be stored securely in order to ensure privacy protection. A large amount of data can be securely stored and it can be used to identify more efficient ways of doing business. Secondly, it helps in taking faster and better quality decision. With the help of rapid speed analytical tools, various resources and data can be combined to analyze new sources of data. Most of the modern businesses are able to analyze the contents and format of information as and when it is generated and make decisions by analyzing it (Panagiota, Korina, & Sameer, 2019). It also helps in identifying new products and services that can be manufactured to gain more profit and attract more customers. By understanding customer needs and satisfaction through analytics it makes a huge percentage of customers more satisfied.

Since big data and its analytical tools were introduced it has positively helped in healthcare sector in order to save lives more and more. A vast quantity of information collected from various sources over the internet are collected and stored so later on it can be analyzed various analytical tools. The analyzed information can be later on applied to healthcare sector. By using data sets collected from various sources to analyze healthcare situations it has helped to prevent and cure diseases (Ahmed, Fathima-Zahra, & Ayoub, 2018). This also helps the doctors to understand the medical history of the patients. These generated reports can be used to understand if there is any possibility for serious illness. Treatment at an early stage consists of less procedure and can help in reducing the cost incurred by the patients. This also helps the insurance-based business companies or organizations to understand a better picture of patient’s medical history in order to give tailored custom insurance packages.

This has also helped the healthcare area by providing personalized medicines and medical risk interface to generate external and internal reports of the particular patient data. The data generated at various levels within healthcare systems are significant. The sources of these data are mainly from electronic health records (EHR), imaging data, patient-generated data, etc. While widespread information in health care is mostly electronical and fits under the big data since most of the information are in unstructured format hence making it time consuming to understand and make useful information out of it (Uthayasankar, Muhammad, & Zahir, 2017). The uses of big data in various sections of the society have increased at an unexpected rate. This has also increased the various challenges and risk involved. These challenges are faced mainly with regards to rights, privacy, and trust.

Fig. 1 Various Applications of Big Data in Health Care.

The application mainly dependent on the healthcare section takes to help technologies that solve the issues based on computer diagnosis systems. The important task in this section is to upgrade the performance of the system to execute the user required computing. Fig. 1 represents the various applications of big data in healthcare industry. Most widely used areas in which these enormous data can be implemented are mostly EHRs, to improvise security and privacy of the patients, patient predication, medical imaging, patient engagement, and telemedicine. These are the few areas where big data and analytics are used.

2. Big Data Overview

The term big data describes a huge amount of information which can be in any raw format are extracted from various sources in its raw format without making any changes. The users require a computing system that can be powerful enough to organize it and manipulate these data according to the needs of the user. Few examples of these sources are mobile, internet, social media, etc. Later stages of these raw data are used for further processing and can be used to make strategic decisions. With the help of big data and its analytical tools it enables by providing useful decisions that can be taken for future references. It also helps in understand data that were collected decades ago find solutions accordingly. Usually any problems related to data are solved by understanding its scope and impact.

The data collected from big data can be mainly of three types or format. The three types are Volume, Velocity, and Variety. Volume mainly extracts the information from various channels, which includes websites that helps in establishing mass communication and interaction and information generated based on machine-to-machine processing. In the early stages of big data, the main issue was related to storage. Since the advancement in time and technology this burden has been able to be reduced. Velocity refers to the process of collecting data, whereas the third model refers to variety. In this process data can be in various formats of structured, numerical information, and financial transactions. The main difference between big data and data analytics is that big data analytics is the mechanism of collecting large information for a particular task whereas big data is objective for the progression of collecting data that is in raw format and needs further changes to be made to understand and make meaningful information’s out of it. The tools that are used for analyzing are referred to as analytical tools.

Few fields where big data mainly works are as follows: The information’s stored in various flights are stored in black box. The data generated from this source are huge and mainly stored in its original format as it is. The information in the black box is regarding the communications made within and with the technical staff. Various sites such as Face book and Twitter contain the information and the views posted by people from all around the world. These can be either text, photos, audios, or documents. Another source of big data is from Stock Exchange. The data produced from stock exchanges are stored in servers so that in later stages it can be used for various organizations to understand the market situations. It holds information mainly regarding the price of public shares, financial transactions that take in various business organizations that help the investors to understand how profitable a business is. Power Grid Data is also a source from where data can be extracted. Base station is like a data base storage unit since it consists of information regarding the power grid. Search Engine Data is one of the main sources of big data that are widely used by enormous number of researchers. The data generated from various search engines can be incorporated with existing problems to solve it.

3. Big Data Applications in Health Care

3.1. Various Sources of Data, Methods, and the Challenges Faced

The data retrieved from hospitals and other healthcare industry are difficult to be controlled. It requires a lot of effort and modern techniques to conduct experiments on these data. To conduct experiments, it is important to understand the data, its contents, its source, and format. It is also important to organize it according to various needs. The various difficulties faced can be solved if observational designs are optimized as much as possible to understand the data. The main aim of conducting experiments is to understand the collected data (Etta & Leah, 2019). These data are compared to understand if they are linked and co-related with each other in nature. The process of staffing at different levels of the organization is analyzed to understand the outcome expected from the patients to see if there exists some relation between the data.

Correlational designs are mostly limited from conducting experiments and from determining the relation between outcomes of two levels. Nurse staffing at different levels is the most important factor that help in predicting outcomes for correlational designs. These factors consist of information regarding the environments like nursing care or other services. The data collected from statistical methods can be controlled by various factors that are associated with staffing levels. These factors include the size of the hospital, academic affiliation, or location of the hospital. By carefully selecting the variables and data for processing will help in getting maximum correlation outcome (Etta & Leah, 2019; Uthayasankar et al., 2017).

Reviewing the variables will help in understanding the factors that influences various stages of staffing. The host factors influence elements like important decisions that are to be taken by the organization, quality of nursing care and clinical outcomes.

3.1.1. Levels of Staffing. Staffing levels are set by administrators of the particular organization and these factors are influenced by various forces such as budgetary considerations and features of local nurse labor markets. The administrative department helps in forming the departmental, work hours, shifts, and other incentives not only to the one level but also to the sub-levels (Antonio, Luis, Maribel, Guilherme, 2019). The practice of the nurse is influenced by the workforce design used in assigning work for a particular project. Few of the other factors that influence the working environment are environment, methods of communication, and the support services available.

There are various variables that contribute toward improving the care and needs of the patient. These factors are inclusive of how serious the patient’s health condition is, if any previous medical conditions and family medical history. The health situation of the patient can get worse or better during the stay in the hospital.

• The quality of care provided can results in appropriate execution of assessments and also to improve patient’s health situation to get expected outcome and prevent unexpected events. For example, the care provided by the nurses, the examinations done by the doctors to understand the patient’s health condition, the medicines or drugs prescribed by the doctors are factors that help in measuring the quality of the care.
• One main factor that is used to measure the quality standards is by giving more importance to safety issues. For example, it is very important to measure the accuracy of medical administration. If the doctors identify the patients’ health problems at an early stage it will be much more beneficial and result in rapid improvement of patient’s health condition.

3.1.2. Outcomes Capturing and analyzing the patient information helps in generating a summarized report so that it can be used in later stages for better understanding. Even though it has resulted in great success still this method is very challenging because it requires a lot of practical understanding and financial considerations. Medical records of patients are used widely in this area as secondary source of data. To understand the outcomes most of the researchers usually use summarized versions of patient records maintained by hospital. These data contain useful healthcare records that explain mainly about how diseases are treated and also regarding the procedures undergone by the patients before date of discharge. The quality and reliability of these documentations can be different depending on various organizations and the way they maintain it. The form of maintaining electronic medical record helps in keeping information regarding assessment conducted. Analyzing these documents or records will help in improving the performance of the healthcare organization. Wider application of information technology in these types of organizations will be helpful in various ways. This also leads to making users search for data sources that can be trusted to improve performance.

If the healthcare settings are compared accurately it will help in understanding the various risks the patients may face in the future. Eventually these reports are taken for better under...