Health Data Analytics And Informatics

By Mbuso Mabuza

With the advent of big data analytics and informatics, and its associated technologies, a rapid growth in career opportunities, coupled with continual technological innovation, has led to an increasing need for qualified professionals who are able to analyse big data and manage technology and information in the healthcare industry.

This book is designed to help you meet that need by providing you with a detailed overview of topics and to explore areas of interest pertaining to data analytics and informatics in the healthcare and biomedical ecosystem. The main topics covered in this book include: data analytics and healthcare informatics; artificial intelligence and machine learning technologies; biomedical sensors and trackers; digital clinical trials; high-definition medicine; precision medicine; connected health; how data analytics and informatics can transform healthcare; reflections and perspectives for the future. The book will appeal to people who are interested in the ways in which health data and technology can be used to enhance the quality of health care.

Healthcare informatics is a multi-disciplinary field suited for innovators, healthcare workers, and non-healthcare professionals, united in the goal of improving the quality of health care. Healthcare informatics involves the acquisition, storage and retrieval of healthcare information and aims to ensure the availability of critical data enable the making of sound policies and programmatic decisions to improve patient care across interactions with the health system.

Big Data analytics covers collection, manipulation, and analyses of massive, diverse data sets that contain a variety of data types such as electronic health records (EHRs) to reveal hidden patterns, cryptic correlations, and other intuitions on a Big Data infrastructure Due to its effectiveness, Big Data analytics is widely used in various fields.

Biomedical big data analytics is in the initial adoption phase, and many healthcare organisations want to implement big data analytics to obtain its benefits. To succeed, big data analytics in the healthcare and biomedical ecosystem needs to be packaged so it is menu-driven, user-friendly, real-time and transparent.

Artificial intelligence (AI) and Big Data analytics are seen as novel tools in the planning of health services as well as identifying and monitoring health problems in individuals and populations.

Automation's major benefit is that it helps medical personnel in processing large amounts of patient's data, especially when taking into consideration that medical personnel are often overwhelmed by a series of healthcare tasks. There is potential in delivering more targeted, wide-reaching, and cost-efficient healthcare by exploiting current big data trends and technologies.

The slow pace of innovation in the healthcare industry reflects challenges that are unique to healthcare in implementing and applying sophisticated big data analytics tools, and this points to the need for federal or government policy to emphasise interoperability of health data and prioritise payment reforms that will encourage providers to develop data analytics capabilities.

Salient guidelines and important implications for practitioners and implementers of big data analytics systems that can assist with successful adoption of big data analytics systems in the healthcare system need to be developed. Describing the crucial factors that are required for understanding is important prior to creating a strategy for the acceptance of big data analytics in the healthcare industry, particularly in low- and middle-income countries, where the industry requires filling the gap of big data analytics adoption.

• Language: English
• Publisher: Lekwandza Media
• Release date: Apr 7, 2023
• ISBN: 9798215004739

Mbuso Mabuza

Dr Mbuso Mabuza is a highly motivated and multi-skilled international public health professional who has served in the public and private sectors of different countries. He has served as a prevention specialist at the Johns Hopkins Bloomberg School of Public Health, and as a consultant at the World Bank, among others. His mission is to improve health outcomes and to expand quality healthcare experiences amongst all groups of people and influence change and innovation.

Book preview

Preface

With the advent of big data analytics and informatics, and its associated technologies, a rapid growth in career opportunities, coupled with continual technological innovation, has led to an increasing need for qualified professionals who are able to analyse big data and manage technology and information in the healthcare industry.

This book is designed to help you meet that need by providing you with a detailed overview of topics and to explore areas of interest pertaining to data analytics and informatics in the healthcare and biomedical ecosystem. The main topics covered in this book include: data analytics and healthcare informatics; artificial intelligence and machine learning technologies; biomedical sensors and trackers; digital clinical trials; high-definition medicine; precision medicine; connected health; how data analytics and informatics can transform healthcare; reflections and perspectives for the future. The book will appeal to people who are interested in the ways in which health data and technology can be used to enhance the quality of health care.

Healthcare informatics is a multi-disciplinary field suited for innovators, healthcare workers, and non-healthcare professionals, united in the goal of improving the quality of health care. Healthcare informatics involves the acquisition, storage and retrieval of healthcare information and aims to ensure the availability of critical data enable the making of sound policies and programmatic decisions to improve patient care across interactions with the health system.

Big Data analytics covers collection, manipulation, and analyses of massive, diverse data sets that contain a variety of data types such as electronic health records (EHRs) to reveal hidden patterns, cryptic correlations, and other intuitions on a Big Data infrastructure Due to its effectiveness, Big Data analytics is widely used in various fields.

Biomedical big data analytics is in the initial adoption phase, and many healthcare organisations want to implement big data analytics to obtain its benefits. To succeed, big data analytics in the healthcare and biomedical ecosystem needs to be packaged so it is menu-driven, user-friendly, real-time and transparent.

Artificial intelligence (AI) and Big Data analytics are seen as novel tools in the planning of health services as well as identifying and monitoring health problems in individuals and populations. AI-driven tools can harness readily available, real-time data – such as that generated through social media and electronic health records – to effectively plan and allocate resources for health services, identify and prevent misinformation related to public health concerns, develop targeted communication to promote behaviour change and predict and intervene early in ill health.

Automation’s major benefit is that it helps medical personnel in processing large amounts of patient’s data, especially when taking into consideration that medical personnel are often overwhelmed by a series of healthcare tasks. There is potential in delivering more targeted, wide-reaching, and cost-efficient healthcare by exploiting current big data trends and technologies.

Although prediction models in clinical care present advantages such as increase in efficiency and cost-effectiveness, probabilities estimated by a prediction model are not considered to replace but rather help the doctor’s decision-making. A particular feature selection algorithm plays a vital role for accurate classification of diseases. In a high workload environment, it may be challenging to embed the prediction models into the workflow of physicians.

The slow pace of innovation in the healthcare industry reflects challenges that are unique to healthcare in implementing and applying sophisticated big data analytics tools, and this points to the need for federal or government policy to emphasise interoperability of health data and prioritise payment reforms that will encourage providers to develop data analytics capabilities.

Salient guidelines and important implications for practitioners and implementers of big data analytics systems that can assist with successful adoption of big data analytics systems in the healthcare system need to be developed. Describing the crucial factors that are required for understanding is important prior to creating a strategy for the acceptance of big data analytics in the healthcare industry, particularly in low- and middle-income countries, where the industry requires filling the gap of big data analytics adoption.

Chapter 1

Data Analytics and Healthcare Informatics

––––––––

1.1 Overview of Data Analytics and Healthcare Informatics

The healthcare industry generates as much as 30 percent of the world data; and it is projected that the data generated by the healthcare industry will leap to 36 percent in 2025. Leveraging the power of this data to enhance medicine, medical research and patient outcomes has become a job for specialists with expertise in data analytics and/or health informatics.

Healthcare informatics specialists work with clinical data generated by electronic health records platforms, diagnostic imagery, vital sign monitoring, drugs side effect tracking systems, clinical trials and practice management software. The soft skills that healthcare informatics specialists need to have include analytical thinking skills, communication skills, curiosity and drive, ethics, organisation, and problem solving. The hard skills that healthcare informatics specialists need to have include computer programming, data analytics, healthcare information technology, and management.

Healthcare informatics is a multi-disciplinary field suited for innovators, healthcare workers, and non-healthcare professionals, united in the goal of improving the quality of health care. Healthcare informatics is broadly focused on the applications of the vast quantities of data generated by the healthcare industry.

Healthcare informatics emerged as its own discipline in the early 1960s not long after medical professionals began using electronic systems to manage patient data. It was concerned primarily with facilitating data exchange between departments by standardising electronic communication protocols.

Modern healthcare informatics is a healthcare discipline that exists at the intersection of medicine and Big Data. It is so new that its definition is still evolving. It involves the acquisition, storage and retrieval of healthcare information and aims to ensure the availability of critical data enable the making of sound policies and programmatic decisions to improve patient care across interactions with the health system.

The growing range of applications of data technology in healthcare have led to the emergence of informatics specialties such as:

Biomedical informatics or clinical informatics: It handles the collection and analysis of biological data derived from patient populations or individuals.

Clinical research informatics: Concerned with the discovery and management of data generated by clinical trials.

Consumer health informatics: Promotes patient empowerment, health literacy and consumer education through digital information systems.

Electronic medical record (EMR) management: Focused on the development and management of technologies that make medical records keeping more efficient.

Healthcare information technology: Encompasses everything related to the information technology systems used in medical and medicine-adjacent settings.

Health data science: Uses data to drive decision-making in medicine and medical research.

Hospital management informatics: Is concerned exclusively with data generated by clinical and administrative activities in hospitals.

Imaging informatics: Focuses on the efficiency, accuracy, usability and reliability of medical imaging services using digital technology.

Information security: Ensures that patient records, provider records and facility records remain secure.

Nursing informatics: Studies the efficiency of patient care delivery and operations management in nursing.

Pharmacy informatics: Deals exclusively with data related to medications and pharmaceutical treatment.

Population health informatics: Uses computer science, information science and population health data to inform public health initiatives and to improve public health outcomes.

Telemedicine and mobile medicine: Uses real-time data and health IT systems to make medical treatments more accessible and effective.

––––––––

Data analytics is the use of advanced analytic techniques against very large, diverse big data sets that include structured, semi-structured and unstructured data, from different sources, and in different sizes from terabytes to zettabytes.

The most popular definition of Big Data is the 5Vs, which are Volume, Velocity, Variety, Verification/Veracity, and Value (Huang et al, 2015). Big Data infrastructure is a framework, which covers important components including Hadoop, NoSQL databases, massively parallel processing (MPP), and others, that is used for storing, processing, and analysing Big Data (Raghupathi and Raghupathi, 2014)). Big Data analytics covers collection, manipulation, and analyses of massive, diverse data sets that contain a variety of data types including electronic health records (EHRs) to reveal hidden patterns, cryptic correlations, and other intuitions on a Big Data infrastructure (Chute et al, 2013).

Clinical data of millions of patients at a clinic /hospital or in a large study exhibit many of the features of Big Data. The volume comes from large amounts of records that can be derived from the EHRs for patients; for example, medical images including magnetic resonance imaging (MRI) or neuroimaging data for each patient can be large, while social media data gathered from a population can be large-scale as well. The velocity occurs when data is accumulated at high speeds, which can be seen when monitoring a patient’s real-time conditions through medical sensors for sleep apnoea, for instance. The variety refers to data sets with a large amount of varying types of independent attributes, such as data sets that are gathered from many different resources. Veracity is a concern when working with possibly noisy, incomplete, or erroneous data where such data need to be properly evaluated using other relevant true evidence. Value portrays the usefulness for improving healthcare outcome. The advance in the fields of health informatics is a vital driving force in the expansion of Big Data, due to either the volume of clinical information produced or the complexity and variety of biomedical data that encompasses discoveries from