Machine Learning and Deep Learning in Efficacy Improvement of Healthcare Systems

Om Prakash Jena, Bharat Bhushan, Nitin Rakesh, Parma Nand Astya, Yousef Farhaoui, Om Prakash Jena, Bharat Bhushan, Nitin Rakesh, Parma Nand Astya, Yousef Farhaoui

• Editorial: CRC Press
• Año: 2022
• ISBN:
  9781000486827
• Edición: 1
• Categoría: Computer Science
• Categoría: Data Mining

The goal of medical informatics is to improve life expectancy, disease diagnosis and quality of life. Medical devices have revolutionized healthcare and have led to the modern age of machine learning, deep learning and Internet of Medical Things (IoMT) with their proliferation, mobility and agility. This book exposes different dimensions of applications for computational intelligence and explains its use in solving various biomedical and healthcare problems in the real world. This book describes the fundamental concepts of machine learning and deep learning techniques in a healthcare system. The aim of this book is to describe how deep learning methods are used to ensure high-quality data processing, medical image and signal analysis and improved healthcare applications. This book also explores different dimensions of computational intelligence applications and illustrates its use in the solution of assorted real-world biomedical and healthcare problems. Furthermore, it provides the healthcare sector with innovative advances in theory, analytical approaches, numerical simulation, statistical analysis, modelling, advanced deployment, case studies, analytical results, computational structuring and significant progress in the field of machine learning and deep learning in healthcare applications.

FEATURES

• 
  
  

• Explores different dimensions of computational intelligence applications and illustrates its use in the solution of assorted real-world biomedical and healthcare problems

• 
  
  

• Provides guidance in developing intelligence-based diagnostic systems, efficient models and cost-effective machines

• 
  
  

• Provides the latest research findings, solutions to the concerning issues and relevant theoretical frameworks in the area of machine learning and deep learning for healthcare systems

• 
  
  

• Describes experiences and findings relating to protocol design, prototyping, experimental evaluation, real testbeds and empirical characterization of security and privacy interoperability issues in healthcare applications

• 
  
  

• Explores and illustrates the current and future impacts of pandemics and mitigates risk in healthcare with advanced analytics

This book is intended for students, researchers, professionals and policy makers working in the fields of public health and in the healthcare sector. Scientists and IT specialists will also find this book beneficial for research exposure and new ideas in the field of machine learning and deep learning.

1 Machine Learning in Healthcare An Introduction

Shruti Dambhare and Sanjay Kumar

Galgotias University, Noida, Uttar Pradesh, India

DOI: 10.1201/9781003189053-1

CONTENTS

1. 1.1 Introduction
2. 1.2 Machine Learning and Its Basic Workings
3. 1.3 Why Machine Learning?
4. 1.4 Machine Learning Techniques
5. 1.4.1 Supervised Learning
6. 1.4.1.1 Workings of Support Vector Machine Algorithm
7. 1.4.2 Unsupervised Learning
8. 1.4.2.1 Clustering Types
9. 1.5 Understanding the Healthcare Industry
10. 1.6 Applications of ML in Healthcare
11. 1.6.1 Machine Learning in Prognosis
12. 1.6.2 Machine Learning in Diagnosis
13. 1.6.3 Electronic Health Records
14. 1.6.3.1 Electronic Health Records and Machine Learning
15. 1.6.4 Applications of ML in Medical Image Analysis
16. 1.6.5 Machine Learning in Natural Language Processing of Medical Documents and Literature
17. 1.6.6 Machine Learning and Pandemic Combatting
18. 1.6.7 Applications of ML in Pandemic Predictions
19. 1.6.8 Applications of ML in Pandemic Controls
20. 1.7 Conclusion
21. References

1.1 Introduction

Technology and its continuous advancements have paved the way to exhilarating and effective innovations in various walks of human lives. Healthcare is one such key segment that is continuously witnessing the ripple effects of technological innovations via the new cutting-edge technologies like big data, Internet of things, cloud computing and machine learning, etc. Over the past decade, the healthcare industry and its various segments have seen a radical shift in its way of functioning and if it is to be defined in a most simple way the answer would be that, it has become more “digital”, “smart” and provides interoperability feature. Healthcare is a huge industry, and the amalgamation of machine learning in healthcare has resulted in the creation and development of life-altering applications. These applications, which were once only a part of science fiction and human imagination, are today's reality and ubiquitous to human lives.

With exponentially growing digitalization in all major sectors, the way “data” is seen and handled for example: data management, data sharing and data processing, is a task of high importance. When such data comes from the health and medical segment, it's even more important to utilize such data. At this point, such machine learning techniques and applications aids in providing valuable solutions to the ever-increasing medical needs. The healthcare industry, which has seen over 10 to 12 trillion dollars of global investments, is still crippled by the high operational cost, insufficient health workforce and poor infrastructure and many other shortcomings like transparency, no placement service delivery, changing health policies and laws.

To overcome such staggering challenges, machine learning can be effectively used. Ranging from simple chatbots that offer preliminary medical support to creation of predictive models to diagnose an onset of disease, prognosis to prevent the wider complications due to an underlying aliment to personalized medicine; machine learning has some promising solutions to offer. Machine learning also has added another dimension to myriad of possibilities to tackle even the mammoth issue like the pandemic and can provide solutions with other new and emerging technologies like IoT, big data, biometrics, cloud computing, deep learning, etc.

The remainder of the paper is organized as follows. Section 1.2 gives an in-depth idea about “machine learning” and its fundamental workings and usage for general applications. It covers the basic difference between artificial intelligence and machine learning. It describes the reason why machine learning is widely accepted and applied over general statistics and the various machine learning techniques are elaborated in section 1.4. Section 1.5 gives an insight to the various segments of the healthcare industry and provides a detailed overview of the wide spectrum of these different segment, which makes the entire healthcare industry. Section 1.6 highlights the various applications of machine learning in healthcare ranging from medical diagnosis, prognosis, electronic health records (EHR), medical image analysis, disease prediction and pandemic combatting solutions to pandemic outbreak prediction and control measures is covered. This section is followed by section 1.7, which states research trends and the conclusion.

1.2 Machine Learning and Its Basic Workings

Artificial intelligence has revolutionized many domains related to human existence. The past century has witnessed a key surge in the application of machine learning in such domains exhibiting state-of-the-art performances. Such an amalgamation of machine learning technology and application of machine learning algorithms in various walks of life has become a normal phenomenon. A U.S. visionary of computer games and artificial intelligence, Arthur Samuel (1901–1990) coined in 1959 the word 'machine learning.' He identified it as “a study field that allows computers to learn without having to be programmed explicitly” [1,2,3]. Machine learning since then went through a lot of systematic changes and with the ever-growing new research and applications of machine learning in various areas fuelled by the demands of humans, this led to a bloom of this field which found its separate path from its mother branch, artificial intelligence.

A basic question which set off the so-called machine learning revolution [4]: could a computer learn without being specifically instructed how? The field of artificial intelligence developed machine learning models by integrating mathematical information with the computer's ability to transfer vast quantities of data faster than anyone else could. These models may take raw data, identify a pattern influencing it, and adapt to new circumstances what they learned. Computers, in other words, may discover the hidden truths in the data by themselves. A machine learning model depicts the patterns hidden in data. Machine learning model can also be stated as mathematical representation which exhibits the pattern found within a set of data Figure 1.1 demonstrates this machine learning process. When the machine learning model is trained (or constructed or adapted) to the training data, some ruling function is observed within those. The ruling function is then transformed or stated into rules that can be used for predictions in novel environments [5,6,7,8].

Figure 1.1 Machine learning process.

As a point of conclusion, we may infer that unlike traditional programming where we input program and get results or rule; in machine learning (which is a sub-branch of artificial intelligence), the machine learns on its own rather than some prewritten algorithm which programs as shown in Figure 1.2. There are two key steps in this, one which is finding fresh interdependencies between two set of variables which are used as input and second is to predict new output with the known set of inter-dependability in the data variables.

Figure 1.2 Traditional programming vs. machine learning.

1.3 Why Machine Learning?

As per the definition given by Mitchell [9], machine learning is a branch of artificial intelligence that employs a variety of statistical, probabilistic and optimization tools to “learn” from past examples and to then use that prior training to classify new data, identify new patterns or predict novel trends.

Similar to statistics, machine learning used understand and examine data but the power of machine learning over statistics lies in the applicability of probabilistic methods, Boolean logic, conditional properties [10,11,12] as well as other systematic methods which help in training data sets and segregate patterns or relationships. The core strength of machine learning lies in the fact that it paves way to make inferences and decision making which were otherwise very difficult to make using conventional statistical method, most of which are based on multivariate regression or correlation analysis. If we consider general statistics, it usually loses its potential when relationships are nonlinear, which in fact is true for all biological systems in the natural settings [13]. Statistical methods assume that variables are independent.

Still, machine learning outcomes are not always correct and hence the practical applicability of machine learning being successful is not fixed. Undoubtedly with any method being used, clarity about the issue at hand and shortcomings of the data at disposal is mandatory. At the same time it is qui...

Índice

• Cover
• Half Title
• Series Page
• Title Page
• Copyright Page
• Contents
• Preface
• Editors
• Contributors
• Chapter 1 Machine Learning in Healthcare: An Introduction
• Chapter 2 A Machine Learning Approach to Identify Personality Traits from Social Media
• Chapter 3 Influence of Content Strategies on Community Engagement over the Healthcare-Related Social Media Pages in India
• Chapter 4 The Impact of Social Media in Fighting Emerging Diseases: A Model-Based Study
• Chapter 5 Prediction of Diabetes Mellitus Using Machine Learning
• Chapter 6 Spectrogram Image Textural Descriptors for Lung Sound Classification
• Chapter 7 Medical Image Analysis Using Machine Learning Techniques: A Systematic Review
• Chapter 8 Impact of Ensemble-Based Models on Cancer Classification, Its Development, and Challenges
• Chapter 9 Performance Comparison of Different Machine Learning Techniques towards Prevalence of Cardiovascular Diseases (CVDs)
• Chapter 10 Deep Neural Networks in Healthcare Systems
• Chapter 11 Deep Learning and Multimodal Artificial Neural Network Architectures for Disease Diagnosis and Clinical Applications
• Chapter 12 A Temporal JSON Model to Represent Big Data in IoT-Based e-Health Systems
• Chapter 13 Use of UAVs in the Prevention, Control and Management of Pandemics
• Chapter 14 Implicit Ontology Changes Driven by Evolution of e-Health IoT Sensor Data in the τOWL Semantic Framework
• Chapter 15 Classification of Text Data in Healthcare Systems – A Comparative Study
• Chapter 16 Predicting Air Quality Index with Machine Learning Models
• Index