Abstract
Most of the research data and medical notes are unstructured or semi-structured and can't be processed using conventional data processing techniques, which creates a surge for big data analytics. In this chapter, the authors discuss big data analytics in healthcare, sources of healthcare big data, electronic health records, and much more. The authors talk about different analytic techniques involved, as well as different big data tools such as Hadoop. This chapter explains all the applications of big data analytics in healthcare, including EHR. This chapter elaborates and explains how big data analytics is used during pandemics and its future scope in the areas of healthcare, including real-time alerts and how big data is useful in the financial management of healthcare and the use of AI and big data in strategic planning, telemedicine, and medical imaging and diagnostics. Thus, this chapter is helpful for academics, health informatics professionals, healthcare stakeholders, clinical researchers, and pharmaceutical companies interested in big data analytics in healthcare.
TopIntroduction
Every day, huge volumes of heterogeneous data are created due to the digitalization of various industries. Today, the healthcare industry’s data volume is so enormous, it alone produces approximately 30% of the world's data. Sources and estimates indicate that currently 80 megabytes of data is generated by a single patient just from electronic health records and imaging. In the coming years, the data volume is said to reach at least 36% (Dash et al., 2019). A lot of this research data and medical notes are unstructured or semi-structured and can't be processed using conventional data processing techniques, which creates a surge for big data analytics. “Big data” is characterized as datasets that cannot be captured, stored, managed, or analyzed using traditional database software tools. In an effort to extract these values from the data sets, certain advanced data analytic techniques are applied to big data, this is further elucidated as big data analytics.
Big Data has been used in various areas, such as scientific research, public administration, and social networking. It is typically referred to as the volume and velocity of data that healthcare providers gather and analyze. It can contain various pieces of information related to a patient's care, such as demographic information, diagnoses, and medication details. The increasing number of medical devices and sensors has created a massive amount of data that is collected and analyzed in the healthcare industry. This data can be used for various applications, such as drug discovery and prediction of disease.
Big Data Analytics is used in healthcare for cancer treatment, drug discovery, and disease prediction. It helps in the prevention of virulent diseases by monitoring pestilential diseases and epidemic outbreaks. This helps in controlling the contamination and spread of infectious diseases. Big data analytics played a major role during the COVID-19 pandemic by early warning and detection of the SARS-CoV-2 virus and its variants (Maha Alafeef & Dipanjan Pan, 2022). After the outbreak of the coronavirus, various NGOs and governmental organizations around the world used different big data techniques and applications to stop, contain, and control the growth and spread of the coronavirus. Big data analytics helped to develop personalized medicine, which provided unprecedented treatment to the patient. This helps the doctors to provide better medicine to the patients with reduced medical costs.
The primary classifications of the data sources for the healthcare system are:
Structured Data
Structured data is defined as data that follows a specific data format, type, and organisational format. Several instances of this type in the medical industry include information on the symptoms and diagnosis of various diseases, test findings, patient details, including admission histories, prescription information, and information on how to pay for the available clinical services etc. These are all organised according to severity. Hence structured data simply represents a flat table.
Semi-Structured Data
Information that was arranged with limited and a self-descriptive character is called to as semi-structured data. Examples of such data include those produced by tools like sensors for efficient patient behavior monitoring. Semi-structured data supports a hierarchical data structure that contains nested information. The structure of the data is show in Figure 1.
Unstructured Data
Unstructured data refers information that doesn't naturally have a structure. Examples of this kind of data include human-language medical prescriptions, clinical correspondence, and so forth shown in Figure 2. Because of the massive diversity of data (organised, non - structured, semi-structured) from various sources, exploring medical data to gain pertinent knowledge for a wide range of stakeholders (clinicians, patients, hospitals, pharmacies, etc.) is a difficult, unnerving undertaking shown in Figure 2 (Adnan et al., 2020).
Figure 2. 4V’s of bigdata Health care Analytics
Key Terms in this Chapter
Hadoop: Hadoop is an open-source distributed processing framework that manages data processing and storage for big data applications running in clustered systems.
Artificial Neural Network: An artificial neural network is a computational model that mimics the way nerve cells work in the human brain.
Real-Time Analysis: Real-time monitoring is the process of collecting and storing performance metrics for data as it traverses your network. It involves polling and streaming data from infrastructure devices so that you know how your networks, applications, and services are performing.
Data Visualization: The graphic representation of information and data is known as data visualization. Data visualization tools offer an accessible way to see and understand trends, outliers, and patterns in data by utilizing visual elements like charts, graphs, and maps.
Tele-Health: Telehealth is the distribution of health-related services and information via electronic information and telecommunication technologies.
Mammography: Mammography is specialized medical imaging that uses a low-dose x-ray system. Doctors use x-ray examinations to identify and treat medical conditions. To create images of the inside of the body, a small amount of ionising radiation is exposed to you. The oldest and most popular type of medical imaging is x-ray.
Big Data: Big data is a combination of structured, semi-structured, and unstructured data collected by organizations that can be mined for information and used in machine learning projects, predictive modeling and other advanced analytics applications.
Strategic Analysis: Strategic analysis refers to the process of conducting research on a company and its operating environment to formulate a strategy.
Dstream: A Discretized Stream, the basic abstraction in Spark Streaming, is a continuous sequence of RDDs representing a continuous stream of data.
Electronic Health Record: An electronic health record (EHR) is a digital version of a patient’s paper chart. EHRs are real-time, patient-centered records that make information available instantly and securely to authorized users.