Machine Learning for Healthcare: Handling and Managing Data

Cover
Half Title
Title Page
Copyright Page
Table of Contents
Preface
Acknowledgments
Editors
List of Contributors
Chapter 1 Fundamentals of Machine Learning
	1.1 Introduction
	1.2 Data in Machine Learning
	1.3 The Relationship between Data Mining, Machine Learning, and Artificial Intelligence
	1.4 Applications of Machine Learning
		1.4.1 Machine Learning: The Expected
		1.4.2 Machine Learning: The Unexpected
	1.5 Types of Machine Learning
		1.5.1 Supervised Learning
			1.5.1.1 Supervised Learning Use Cases
		1.5.2 Unsupervised Learning
			1.5.2.1 Types of Unsupervised Learning
			1.5.2.2 Clustering
			1.5.2.3 Association Rule
			1.5.2.4 Unsupervised Learning Use Case
		1.5.3 Reinforcement Learning (RL)
	1.6 Conclusion
	References
Chapter 2 Medical Information Systems
	2.1 Introduction
	2.2 Types of Medical Information Systems
		2.2.1 General Medical Information Systems
		2.2.2 Specific Medical Information Systems
	2.3 Types of General Medical Data
		2.3.1 Numerical Data
		2.3.2 Textual Data
		2.3.3 Categorical Data
		2.3.4 Imaging Data
	2.4 History of Medical Information Systems
	2.5 Collection of MIS Data through Various Platforms
		2.5.1 Traditional
		2.5.2 Electronic
	2.6 Diagnosis and Treatment of Disease through MIS Data
	2.7 Conclusion
	References
Chapter 3 The Role of Metaheuristic Algorithms in Healthcare
	3.1 Introduction
	3.2 Machine Learning in Healthcare
	3.3 Health Information System Framework
	3.4 Privacy and Security of Data
	3.5 Big Data Analytics in Disease Diagnosis
	3.6 The Metaheuristic Algorithm for Healthcare
	3.7 Conclusion
	References
Chapter 4 Decision Support System to Improve Patient Care
	4.1 Introduction
	4.2 Related Work
	4.3 Feature Selection
		4.3.1 Entropy Formula
	4.4 Experimental Setup
	4.5 Conclusion
	References
Chapter 5 Effects of Cell Phone Usage on Human Health and Specifically on the Brain
	5.1 Introduction
	5.2 Background
	5.3 Radiation Produced by a Mobile Phone
	5.4 MATLAB Tools
		5.4.1 Problem Statement
		5.4.2 Research Objective
	5.5 State-of-the-Art Research and Technology
	5.6 Discussion of Tools
	5.7 Methodology
		5.7.1 Quantitative Approach
		5.7.2 Design Research
	5.8 Method of Data Collection
		5.8.1 Sampling Technique
		5.8.2 Sample Size
		5.8.3 Instrument for Data Collection
		5.8.4 Research Model
	5.9 K-Means Clustering
	5.10 Result and Discussion
	5.11 Conclusion
	References
Chapter 6 Feature Extraction and Bio Signals
	6.1 Introduction
	6.2 Feature Extraction
		6.2.1 Common Spatial Patterns
		6.2.2 Adaptive Common Spatial Patterns
		6.2.3 Adaptive CSP Patches
		6.2.4 Canonical Correlation Analysis
		6.2.5 Band Power Features
		6.2.6 Adaptive Band Power Features
		6.2.7 Time Point Features
		6.2.8 Time Points with Adaptive XDAWN
	6.3 Feature Selection and its Approaches
		6.3.1 Filter Approach
		6.3.2 Wrapper Approach
	6.4 Conclusion
	References
Chapter 7 Comparison Analysis of Multidimensional Segmentation Using Medical Health-Care Information
	7.1 Introduction
	7.2 Literature Review
		7.2.1 Static Structure of Literature Review with Another Research Comparison
	7.3 Methodology
		7.3.1 Original Result of Image Testing in Binary Transformation
		7.3.2 High Dimension Structured Graphs
			7.3.2.1 Grab-Cut
	7.4 Algorithm
	7.5 Result Comparison and Discussion
	7.6 Conclusion
	Acknowledgments
	References
Chapter 8 Deep Convolutional Network Based Approach for Detection of Liver Cancer and Predictive Analytics on Cloud
	8.1 Introduction
		8.1.1 Types of Liver Diseases
	8.2 Medical Images and Deep Learning
		8.2.1 Micro-Service Architecture
		8.2.2 Integration of NVDIA GPU for Deep Learning on Cloud
		8.2.3 Presenting the Sockets and Slots for Processors
		8.2.4 Clock Details of Deep Learning Server
		8.2.5 Threads for Deep Learning–Based Computations
		8.2.6 Available Hard Disk for Use
		8.2.7 Memory
		8.2.8 Overall Details of Used Computing Environment with Deep Convolutional Networks
	8.3 Deep Learning for Liver Diagnosis with the Projected Model
	8.4 Proposed Model and Outcomes
	8.5 Conclusion
	References
Chapter 9 Performance Analysis of Machine Learning Algorithm for Healthcare Tools with High Dimension Segmentation
	9.1 Introduction
	9.2 Literature Review
	9.3 Methodology
		9.3.1 Proposed Framework
		9.3.2 Light Field Toolbox for MATLAB
		9.3.3 High Dimensional Light Field Segmentation Method
		9.3.4 High Dimensional Structured Graphs
	9.4 High Dimension Structured Graphs
		9.4.1 Grab-Cut
		9.4.2 Image Testing Value
		9.4.3 Image Testing Result
		9.4.4 Graph Cut Value for B/W Image
		9.4.5 Image Testing Value
		9.4.6 Image Testing Result
	9.5 Algorithm
	9.6 Result and Discussion
	9.7 Conclusion
	9.8 Future Work
	Acknowledgment
	References
Chapter 10 Patient Report Analysis for Identification and Diagnosis of Disease
	10.1 Introduction
	10.2 Data Variability
		10.2.1 Structured Data
			10.2.1.1 Human Generated Data
			10.2.1.2 Machine Generated Data
		10.2.2 Semi-Structured Data
		10.2.3 Unstructured Data
		10.2.4 Comparison of Structured, Unstructured Data, and Semi-Structured
	10.3 Data Collection of Diseases
		10.3.1 EMR Data Collection through eHealth Devices
		10.3.2 Semantic Data Extraction from Healthcare Websites
		10.3.3 Patient Chatbots
		10.3.4 Structured Data
		10.3.5 Consistency and Quality of Structured Data
	10.4 Predictive Models for Analysis
		10.4.1 Regression Techniques
		10.4.2 Machine Learning Techniques
		10.4.3 Algorithms
			10.4.3.1 Naïve Bayes
			10.4.3.2 Support Vector Machine
			10.4.3.3 Logistic Regression
			10.4.3.4 Decision Trees
		10.4.4 Use Cases
			10.4.4.1 Cleveland Clinic
			10.4.4.2 Providence Health
			10.4.4.3 Dartmouth Hitchcock
			10.4.4.4 Google
	10.5 Semi-Structured Data
		10.5.1 Semantic Extraction
		10.5.2 Web Mantic Extraction
		10.5.3 Use Cases
	10.6 Unstructured Data
		10.6.1 Finding Meaning in Unstructured Data
		10.6.2 Extraction of Data
			10.6.2.1 Text Extraction
			10.6.2.2 Image Extraction
			10.6.2.3 Challenges of Data Extraction from PDFs
			10.6.2.4 Video Extraction
			10.6.2.5 Sound Extraction
		10.6.3 Algorithms
			10.6.3.1 Natural Language Processing
			10.6.3.2 Naïve Bayes
			10.6.3.3 Deep Learning
			10.6.3.4 Convolutional Neural Network
			10.6.3.5 Phenotyping Algorithms
		10.6.4 Use Cases
	10.7 Conclusion
	References
Chapter 11 Statistical Analysis of the Pre- and Post-Surgery in the Healthcare Sector Using High Dimension Segmentation
	11.1 Introduction
	11.2 Methodology
		11.2.1 Sampling Techniques
		11.2.2 Sample Data and Size
		11.2.3 Light Field Toolbox for MATLAB
		11.2.4 High Dimensional Light Field Segmentation Method
	11.3 Support Vector Machine (SVM)
		11.3.1 4-Dimentional SVM Graphs
	11.4 Statistical Technique
	11.5 Result and Discussion
	11.6 Conclusion
	11.7 Future Work
	References
Chapter 12 Machine Learning in Diagnosis of Children with Disorders
	12.1 Introduction
		12.1.1 Down Syndrome (DS)
		12.1.2 Sensory Processing Disorder (SPD)
		12.1.3 Autism Spectrum Disorder (ASD)
		12.1.4 Aims and Organisation
	12.2 Existing Tools for Diagnosis of DS, SPD, and ASD
		12.2.1 Existing Tools of DS Diagnosis
		12.2.2 Existing Tools of SPD Diagnosis
		12.2.3 Existing Tools for ASD Diagnosis
	12.3 Machine Learning Applied for Diagnosis of DS, SPD, and ASD
	12.4 Machine Learning Case Studies of DS, SPD, and ASD
		12.4.1 Machine Learning (ML) Case Study for DS
		12.4.2 Machine Learning Case Study of SPD
		12.4.3 Machine Learning Case Study for ASD
	12.5 Conclusion
	References
Chapter 13 Forecasting Dengue Incidence Rate in Tamil Nadu Using ARIMA Time Series Model
	13.1 Introduction
	13.2 Literature Review
		13.2.1 Findings
	13.3 Methods and Materials
		13.3.1 Study Area
		13.3.2 Snapshot for Dataset
		13.3.3 Proposed Model
		13.3.4 Estimate and Develop the Model
	13.4 Results and Discussions
	13.5 Conclusion
	13.6 Acknowledgment
	References
Index