Exploratory Data Analytics for Healthcare (Innovations in Big Data and Machine Learning)

Cover
Half Title
Series Page
Title Page
Copyright Page
Table of Contents
Preface
Editors
Contributors
Chapter 1 Visual Analytics: Scopes and Challenges
	1.1 Introduction: Concept of Visual Analytics
		1.1.1 Process of Visual Analytics
		1.1.2 Need and Benefits of VA in Healthcare
	1.2 VA Technologies and Tools
		1.2.1 General Features of Visual Analytics Tools
			1.2.1.1 Data Visualization
			1.2.1.2 Dashboards
			1.2.1.3 Integration with Multiple Data Sources
			1.2.1.4 Collaboration
		1.2.2 Visual Analytics Tools
	1.3 Scope of VA in Different Sectors of Medical Science
	1.4 Challenges to Face
	1.5 Conclusion
	References
Chapter 2 Statistical Methods and Applications: A Comprehensive Reference for the Healthcare Industry
	2.1 Introduction
	2.2 Conceptual Framework of the Methodology
		2.2.1 Outlier Definition
		2.2.2 Overview of Techniques and Motivation for Outlier Detection and Handling
			2.2.2.1 Z-Score or Extreme Value Analysis (Parametric)
			2.2.2.2 Probabilistic and Statistical Modeling (Parametric)
			2.2.2.3 Linear Regression Models (PCA, LMS)
			2.2.2.4 Proximity-Based Models (Non-Parametric)
	2.3 Definition of Clustering
		2.3.1 Density-Based Methods
		2.3.2 Distributed Based Algorithms
		2.3.3 Centroid-Based Algorithms
		2.3.4 Connectivity-Based Algorithms
		2.3.5 Density-Based Algorithms
		2.3.6 Subspace Algorithms
	2.4 How Clustering Concepts Aid Outlier Detection and Eradication
	2.5 Definition of Concept Hierarchy
		2.5.1 Binning
		2.5.2 Histogram Analysis
		2.5.3 Clustering Analysis
		2.5.4 Entropy-Based Discretization
		2.5.5 Segmentation via “Natural Partitioning”
	2.6 Purpose of the Study
	2.7 Research Questions
	2.8 What Are the Causes and Challenges of Imbalanced Classification?
	2.9 What Are the Issues That Occur While Analyzing Active Datasets of Epidemics?
	2.10 What Is Active Learning?
	2.11 What Are the Challenges Faced in Data Mining?
	2.12 Definition of Terms, Keywords, Algorithms, and Methodologies
	2.13 Applications and Future Scope of the Study
		2.13.1 Credit Card Fraud Detection
		2.13.2 Mobile Fraud Detection
		2.13.3 Insurance Claim Fraud Detection
		2.13.4 Insider Trading Detection
		2.13.5 Medical Public Health Outlier
		2.13.6 Industrial Damage Detection
		2.13.7 Image Processing
		2.13.8 Outlier Detection in Text Data
		2.13.9 Sensor Networks
		2.13.10 Miscellaneous Domains
	2.14 Conclusions
	References
Chapter 3 Machine Learning Algorithms for Healthcare Data Analytics
	3.1 Introduction
	3.2 Types of Machine Learning Algorithms
		3.2.1 Supervised Learning
			3.2.1.1 Algorithms for Supervised Machine Learning
		3.2.2 Unsupervised Learning
		3.2.3 Semi-Supervised Learning
		3.2.4 Reinforcement Learning
		3.2.5 Association Rules
	3.3 Models of Machine Learning
		3.3.1 Support Vector Machine
		3.3.2 Bayesian Networks
		3.3.3 Artificial Neural Networks
			3.3.3.1 Components of ANN Are
		3.3.4 Regression Analysis
			3.3.4.1 Method
	3.4 Application of Machine Learning in Various Fields
		3.4.1 Medical Diagnosis
		3.4.2 Image Recognition Process
		3.4.3 Speech Recognition
		3.4.4 Predicting Traffic
		3.4.5 Spam and Malware Filtering in Email
	3.5 Healthcare Data Analytics with Machine Learning
		3.5.1 Natural Language Processing
			3.5.1.1 Introduction
			3.5.1.2 Important Use Cases of NLP Are
			3.5.1.3 Implementing Predictive Analytics in Healthcare
			3.5.1.4 Workflow of NLP
	3.6 Case Studies Based on EHR
		3.6.1 Introduction to EHR
		3.6.2 Schemes
	3.7 Issues and Challenges
	3.8 Conclusions
	References
Chapter 4 A Review of Challenges and Opportunities in Machine Learning for Healthcare
	4.1 Introduction
	4.2 Identifying Disease and Diagnosis
		4.2.1 Medical Imaging Diagnosis
		4.2.2 Robotic Surgery
		4.2.3 Personalized Medicine
		4.2.4 Drug Development
		4.2.5 Destructive Testing
		4.2.6 Non-Destructive Testing
	4.3 Supervised Learning Techniques
		4.3.1 Decision Tree Methods
		4.3.2 Support Vector Machine
	4.4 Electrocardiography (ECG) Tool for Evaluation
	4.5 Feature Extraction
		4.5.1 MSE Loss
	4.6 Spatial (SA) and Channel-Wise Attention (CA)
	4.7 Addressing a Hierarchy of Healthcare Opportunities
	4.8 Clinical Task Automation: Automating Clinical Tasks during Diagnosis and Treatment
	4.9 Clinical Support and Augmentation: Optimizing clinical Decision and Practice Support
	4.10 Opportunities for New Research in Machine Learning
	4.11 Accommodating Data and Practice Non-stationary in Learning and Deployment
	4.12 Personalized Medicine
	4.13 Automatic Treatment or Recommendation
	4.14 Automatic Care or Guidance
	4.15 Error Potential as Applicable to AI and ML to Healthcare
	4.16 Health Data Requires a High Level of Customization
	4.17 Generation of Design ECGs
	4.18 Conclusion
	References
Chapter 5 Digitalizing the Health Records Using Machine Learning Algorithms
	5.1 Introduction
	5.2 Literature Study
	5.3 Background
	5.4 Working Principle of Digitalization
	5.5 Case Study on Digitalization Method
	5.6 Case Study with Image Database
	5.7 Experimental Example
	5.8 Data Flow in Machine Learning
	5.9 Future Trends and Conclusion
	References
Chapter 6 Interactive Visualization for Understanding and Analyzing Medical Data
	6.1 Introduction
	6.2 Sources of Medical Data
	6.3 Types of Medical Data
	6.4 Interactive Visualization Process of Medical Data
		6.4.1 Image Analysis
			6.4.1.1 Data Acquisition
			6.4.1.2 Data Transfer and Storage
			6.4.1.3 Image Enhancement
			6.4.1.4 Image Segmentation
			6.4.1.5 Image Registration
			6.4.1.6 Visualization
		6.4.2 Unstructured Text Analysis
		6.4.3 Signal Data Analysis
	6.5 Visualization Methods
	6.6 Conclusion
	References
Chapter 7 Heart Disease Prediction Using Tableau
	7.1 Introduction
	7.2 Types of Heart Disease
		7.2.1 Congenital Heart Disease
			7.2.1.1 Causes and Symptoms
		7.2.2 Coronary Heart Disease
			7.2.2.1 Causes and Symptoms
		7.2.3 Arrhythmia
			7.2.3.1 Causes and Symptoms
		7.2.4 Dilated Cardiomyopathy
			7.2.4.1 Causes and Symptoms
		7.2.5 Myocardial Infarction
			7.2.5.1 Causes and Symptoms
		7.2.6 Heart Failure
			7.2.6.1 Causes and Symptoms
		7.2.7 Hypertrophic Cardiomyopathy
			7.2.7.1 Causes and Symptoms
		7.2.8 Mitral Valve Regurgitation
			7.2.8.1 Causes and Symptoms
		7.2.9 Mitral Valve Prolapse
			7.2.9.1 Causes and Symptoms
		7.2.10 Pulmonary Stenosis
			7.2.10.1 Causes and Symptoms
	7.3 Machine Learning Algorithms Used for Predicting Heart Disease
		7.3.1 Naïve Bayes
		7.3.2 Support Vector Machine Algorithm
		7.3.3 Random Forest
		7.3.4 Decision Tree
			7.3.4.1 Information Gain (ID3)
			7.3.4.2 Gain Ratio (C4.5)
			7.3.4.3 Gini Index (CART)
	7.4 K-Nearest Neighbor
	7.5 Logistic Regression
	7.6 CASE Study: Exploring Heart Disease from the Given Dataset
		7.6.1 Dataset
		7.6.2 Percentage of People Having Various Chest Pain Type
		7.6.3 Resting Blood Pressure Histogram
		7.6.4 Diagnosis of Heart Disease in the Given Record
		7.6.5 Chest Pain-Based Heart Disease Count
		7.6.6 CORR ([Resting Blood Pressure], [Serum Cholesterol])
	7.7 Conclusions
	References
Chapter 8 A Deep Learning Framework Using AlexNet for Early Detection of Pancreatic Cancer
	8.1 The Pancreas and Its Function
	8.2 Cancerous Cell and Its Effect on the Human Body
	8.3 Pancreatic Cancer
	8.4 Statistics (Mortality Rate)
	8.5 Symptoms
	8.6 Causes and Risk Factors Associated with Pancreatic Cancer
	8.7 Detection and Treatment
		8.7.1 Previous Work
		8.7.2 Significance of Early Detection
		8.7.3 Challenges of Early Detection
		8.7.4 Existing Approaches in Detecting Cancer
		8.7.5 Imaging Tests
		8.7.6 Other Tests Available
	8.8 Treatment
	8.9 Prerequisite Knowledge Required
		8.9.1 Pancreas Image Classification
	8.10 Convolution Neural Network
	8.11 Proposed Architecture
		8.11.1 Max Pooling
	8.12 Dataset
	8.13 Preprocessing of Data
	8.14 Data Augmentation
		8.14.1 Need of Augmentation
	8.15 Model Used
	8.16 Results
	8.17 Conclusion
	References
Chapter 9 Applications of the Map-Reduce Programming Framework to Clinical Big Data Analysis: Current Landscape and Future Trends
	9.1 Introduction
		9.1.1 Big Data
			9.1.1.1 History of Big Data
			9.1.1.2 Importance of Big Data
			9.1.1.3 Working of Big Data
			9.1.1.4 Big Data Use-Cases
		9.1.2 Hadoop
			9.1.2.1 Hadoop History
			9.1.2.2 Importance of Hadoop
		9.1.3 Map-Reduce
			9.1.3.1 Importance of Map-Reduce
			9.1.3.2 Hadoop Map-Reduce Working
	9.2 Big Data Frameworks for Healthcare
	9.3 Role of Hadoop Map-Reduce Framework in Clinical Analysis
		9.3.1 Mapping of Clinical Data with Hadoop Map-Reduce in Context with Big Data
	9.4 Challenges of Hadoop Map-Reduce Framework in Clinical Analysis
		9.4.1 Clinical Big Data and Forthcoming Claims
	9.5 Future Trends of Hadoop Map-Reduce Framework in Clinical Analysis
	9.6 Conclusions
	References
	Web References
Chapter 10 An Investigation of Different Machine Learning Approaches for Healthcare Analytics
	10.1 Machine Learning for Ailment Identification and Diagnosis Using ML Models
		10.1.1 Data Loading
			10.1.1.1 Data Preprocessing
	10.2 Explore Your Data
	10.3 Splitting Data
		10.3.1 Efficient Split
	10.4 Generate the Model
		10.4.1 Supervised Learning
		10.4.2 Unsupervised Learning
		10.4.3 Semi-Supervised Learning
		10.4.4 Reinforcement Learning
	10.5 Evaluate Model
		10.5.1 Drug Discovery
		10.5.2 Drug Development Phases
		10.5.3 Machine Learning Technique for Image Classification
			10.5.3.1 Support Vector Machine (SVM)
		10.5.4 The Neural Network to Deep Learning
	10.6 Machine Learning in Treatment Studies
	10.7 Machine Learning for Personalized Medicine
		10.7.1 Radiation-Oncology
		10.7.2 Rheumatic Disease
		10.7.3 COVID-19
	10.8 Smart Health Records
		10.8.1 Smart Health Data Process
		10.8.2 Deep Learning Algorithms in Healthcare
		10.8.3 Artificial Neural Network
		10.8.4 Deep Neural Network
		10.8.5 Convolutional Neural Network
	10.9 Implementation Challenges of Machine Learning in Healthcare
		10.9.1 High Level of Data Customization
		10.9.2 Accessibility of Expertise and Talents
		10.9.3 Venture Budget
	10.10 Conclusion
	References
Chapter 11 The Potential of Machine Learning for Clinical Predictive Analytics
	11.1 Introduction
		11.1.1 Big Data
		11.1.2 Challenges Faced by Big Data
	11.2 Machine Learning Algorithms for Analytics
		11.2.1 Types of ML Algorithms
			11.2.1.1 Supervised Learning
			11.2.1.2 Unsupervised Learning
	11.3 Conclusion
	11.4 Common Terminologies
	References
Chapter 12 Predictive Analytics in Healthcare Using Machine Learning Tools and Techniques
	12.1 Introduction
	12.2 Predictive Analytics – An Overview
	12.3 Define Machine Learning
		12.3.1 Steps in Applying ML
		12.3.2 Collecting Data
		12.3.3 Data Preparation
		12.3.4 Training a Model
		12.3.5 Performance Evaluation
		12.3.6 Improving the Performance
	12.4 Machine Learning Algorithms
		12.4.1 Supervised Learning
		12.4.2 Unsupervised Learning
		12.4.3 Semi-Supervised Learning
		12.4.4 Reinforcement Learning
	12.5 Machine Learning Tools
		12.5.1 Platform vs. Libraries
		12.5.2 Graphical User Interface vs. Command Line Interface vs. Application Program Interface
		12.5.3 Local vs. Remote
		12.5.4 ML Using R
	12.6 Evaluation Metrics
		12.6.1 Confusion Matrix
		12.6.2 Accuracy
		12.6.3 Precision
		12.6.4 Recall
		12.6.5 F1 Score
		12.6.6 The Area under the Curve
		12.6.7 Mean Square Error
		12.6.8 Mean Absolute Error
	12.7 Machine Learning in Various Fields
		12.7.1 Transportation Industry
		12.7.2 Economics
		12.7.3 Healthcare Industry
		12.7.4 Agriculture Industry
		12.7.5 Sales and Marketing
	12.8 Machine Learning Predictions in Healthcare
		12.8.1 Predictions of Stroke
		12.8.2 Predictions on Thyroid Disorder
		12.8.3 Prediction of Diabetic Diseases
		12.8.4 Prediction of Bladder Volume
		12.8.5 Detection of Breast Cancer
	12.9 Conclusion
	References
Chapter 13 A Collective Study of Machine Learning (ML) Algorithms and Its Impact on Various Facets of Healthcare
	13.1 Introduction to Machine Learning
	13.2 Machine Learning vs. Data Mining
	13.3 Essential Keywords
	13.4 Step-by-Step Mechanism of ML
	13.5 History of Machine Learning
	13.6 Probability Theory
	13.7 Machine Learning Approaches
		13.7.1 Supervised Machine Learning
		13.7.2 Unsupervised Machine Learning
		13.7.3 Reinforced Machine Learning
	13.8 Machine Learning Applications
	13.9 Types of Machine Learning Algorithms
		13.9.1 Supervised Algorithm
			13.9.1.1 Simple Linear Regression Algorithm
			13.9.1.2 Random Forest Algorithm
			13.9.1.3 Logistic Regression Algorithm
			13.9.1.4 KNN (K-Nearest Neighbors)
			13.9.1.5 Decision Tree Algorithm
			13.9.1.6 Support Vector Machine (SVM)
			13.9.1.7 Naïve Bayes
		13.9.2 Unsupervised Learning Algorithm
			13.9.2.1 K-Means Algorithm
			13.9.2.2 Apriori Algorithm
			13.9.2.3 Clustering Algorithm
		13.9.3 Semi-Supervised Learning Algorithm
		13.9.4 Reinforcement Learning Algorithm
			13.9.4.1 Characteristics of Reinforcement Learning algorithm
			13.9.4.2 Reinforcement Learning Algorithm Applications
	13.10 Smart Healthcare
	13.11 Role of IoT in Smart Healthcare System
	13.12 Smart Healthcare System and Internet of Things (IoT)
	13.13 Evaluation of Algorithms Performance
	13.14 Discussion
	13.15 Conclusion and Future Scope
	References
Index