Biomedical Data Mining for Information Retrieval: Methodologies, Techniques, and Applications

Cover
Half-Title Page
Series Page
Title Page
Copyright Page
Contents
Preface
1 Mortality Prediction of ICU Patients Using Machine Learning Techniques
	1.1 Introduction
	1.2 Review of Literature
	1.3 Materials and Methods
		1.3.1 Dataset
		1.3.2 Data Pre-Processing
		1.3.3 Normalization
		1.3.4 Mortality Prediction
		1.3.5 Model Description and Development
	1.4 Result and Discussion
	1.5 Conclusion
	1.6 Future Work
	References
2 Artificial Intelligence in Bioinformatics
	2.1 Introduction
	2.2 Recent Trends in the Field of AI in Bioinformatics
		2.2.1 DNA Sequencing and Gene Prediction Using Deep Learning
	2.3 Data Management and Information Extraction
	2.4 Gene Expression Analysis
		2.4.1 Approaches for Analysis of Gene Expression
		2.4.2 Applications of Gene Expression Analysis
	2.5 Role of Computation in Protein Structure Prediction
	2.6 Application in Protein Folding Prediction
	2.7 Role of Artificial Intelligence in Computer-Aided Drug Design
	2.8 Conclusions
	References
3 Predictive Analysis in Healthcare Using Feature Selection
	3.1 Introduction
		3.1.1 Overview and Statistics About the Disease
		3.1.2 Overview of the Experiment Carried Out
	3.2 Literature Review
		3.2.1 Summary
		3.2.2 Comparison of Papers for Diabetes and Hepatitis Dataset
	3.3 Dataset Description
		3.3.1 Diabetes Dataset
		3.3.2 Hepatitis Dataset
	3.4 Feature Selection
		3.4.1 Importance of Feature Selection
		3.4.2 Difference Between Feature Selection, Feature Extraction and Dimensionality Reduction
		3.4.3 Why Traditional Feature Selection Techniques Still Holds True?
		3.4.4 Advantages and Disadvantages of Feature Selection Technique
	3.5 Feature Selection Methods
		3.5.1 Filter Method
		3.5.2 Wrapper Method
	3.6 Methodology
		3.6.1 Steps Performed
		3.6.2 Flowchart
	3.7 Experimental Results and Analysis
		3.7.1 Task 1—Application of Four Machine Learning Models
		3.7.2 Task 2—Applying Ensemble Learning Algorithms
		3.7.3 Task 3—Applying Feature Selection Techniques
		3.7.4 Task 4—Appling Data Balancing Technique
	3.8 Conclusion
	References
4 Healthcare 4.0: An Insight of Architecture, Security Requirements, Pillars and Applications
	4.1 Introduction
	4.2 Basic Architecture and Components of e-Health Architecture
		4.2.1 Front End Layer
		4.2.2 Communication Layer
		4.2.3 Back End Layer
	4.3 Security Requirements in Healthcare 4.0
		4.3.1 Mutual-Authentications
		4.3.2 Anonymity
		4.3.3 Un-Traceability
		4.3.4 Perfect—Forward—Secrecy
		4.3.5 Attack Resistance
	4.4 ICT Pillar’s Associated With HC4.0
		4.4.1 IoT in Healthcare 4.0
		4.4.2 Cloud Computing (CC) in Healthcare 4.0
		4.4.3 Fog Computing (FC) in Healthcare 4.0
		4.4.4 BigData (BD) in Healthcare 4.0
		4.4.5 Machine Learning (ML) in Healthcare 4.0
		4.4.6 Blockchain (BC) in Healthcare 4.0
	4.5 Healthcare 4.0’s Applications-Scenarios
		4.5.1 Monitor-Physical and Pathological Related Signals
		4.5.2 Self-Management, and Wellbeing Monitor, and its Precaution
		4.5.3 Medication Consumption Monitoring and Smart-Pharmaceutics
		4.5.4 Personalized (or Customized) Healthcare
		4.5.5 Cloud-Related Medical Information’s Systems
		4.5.6 Rehabilitation
	4.6 Conclusion
	References
5 Improved Social Media Data Mining for Analyzing Medical Trends
	5.1 Introduction
		5.1.1 Data Mining
		5.1.2 Major Components of Data Mining
		5.1.3 Social Media Mining
		5.1.4 Clustering in Data Mining
	5.2 Literature Survey
	5.3 Basic Data Mining Clustering Technique
		5.3.1 Classifier and Their Algorithms in Data Mining
	5.4 Research Methodology
	5.5 Results and Discussion
		5.5.1 Tool Description
		5.5.2 Implementation Results
		5.5.3 Comparison Graphs Performance Comparison
	5.6 Conclusion & Future Scope
	References
6 Bioinformatics: An Important Tool in Oncology
	6.1 Introduction
	6.2 Cancer—A Brief Introduction
		6.2.1 Types of Cancer
		6.2.2 Development of Cancer
		6.2.3 Properties of Cancer Cells
		6.2.4 Causes of Cancer
	6.3 Bioinformatics—A Brief Introduction
	6.4 Bioinformatics—A Boon for Cancer Research
	6.5 Applications of Bioinformatics Approaches in Cancer
		6.5.1 Biomarkers: A Paramount Tool for Cancer Research
		6.5.2 Comparative Genomic Hybridization for Cancer Research
		6.5.3 Next-Generation Sequencing
		6.5.4 miRNA
		6.5.5 Microarray Technology
		6.5.6 Proteomics-Based Bioinformatics Techniques
		6.5.7 Expressed Sequence Tags (EST) and Serial Analysis of Gene Expression (SAGE)
	6.6 Bioinformatics: A New Hope for Cancer Therapeutics
	6.7 Conclusion
	References
7 Biomedical Big Data Analytics Using IoT in Health Informatics
	7.1 Introduction
	7.2 Biomedical Big Data
		7.2.1 Big EHR Data
		7.2.2 Medical Imaging Data
		7.2.3 Clinical Text Mining Data
		7.2.4 Big OMICs Data
	7.3 Healthcare Internet of Things (IoT)
		7.3.1 IoT Architecture
		7.3.2 IoT Data Source
	7.4 Studies Related to Big Data Analytics in Healthcare IoT
	7.5 Challenges for Medical IoT & Big Data in Healthcare
	7.6 Conclusion
	References
8 Statistical Image Analysis of Drying Bovine Serum Albumin Droplets in Phosphate Buffered Saline
	8.1 Introduction
	8.2 Experimental Methods
	8.3 Results
		8.3.1 Temporal Study of the Drying Droplets
		8.3.2 FOS Characterization of the Drying Evolution
		8.3.3 GLCM Characterization of the Drying Evolution
	8.4 Discussions
		8.4.1 Qualitative Analysis of the Drying Droplets and the Dried Films
		8.4.2 Quantitative Analysis of the Drying Droplets and the Dried Films
	8.5 Conclusions
	Acknowledgments
	References
9 Introduction to Deep Learning in Health Informatics
	9.1 Introduction
		9.1.1 Machine Learning v/s Deep Learning
		9.1.2 Neural Networks and Deep Learning
		9.1.3 Deep Learning Architecture
		9.1.4 Applications
	9.2 Deep Learning in Health Informatics
		9.2.1 Medical Imaging
	9.3 Medical Informatics
		9.3.1 Data Mining
		9.3.2 Prediction of Disease
		9.3.3 Human Behavior Monitoring
	9.4 Bioinformatics
		9.4.1 Cancer Diagnosis
		9.4.2 Gene Variants
		9.4.3 Gene Classification or Gene Selection
		9.4.4 Compound–Protein Interaction
		9.4.5 DNA–RNA Sequences
		9.4.6 Drug Designing
	9.5 Pervasive Sensing
		9.5.1 Human Activity Monitoring
		9.5.2 Anomaly Detection
		9.5.3 Biological Parameter Monitoring
		9.5.4 Hand Gesture Recognition
		9.5.5 Sign Language Recognition
		9.5.6 Food Intake
		9.5.7 Energy Expenditure
		9.5.8 Obstacle Detection
	9.6 Public Health
		9.6.1 Lifestyle Diseases
		9.6.2 Predicting Demographic Information
		9.6.3 Air Pollutant Prediction
		9.6.4 Infectious Disease Epidemics
	9.7 Deep Learning Limitations and Challenges in Health Informatics
	References
10 Data Mining Techniques and Algorithms in Psychiatric Health: A Systematic Review
	10.1 Introduction
	10.2 Techniques and Algorithms Applied
	10.3 Analysis of Major Health Disorders Through Different Techniques
		10.3.1 Alzheimer
		10.3.2 Dementia
		10.3.3 Depression
		10.3.4 Schizophrenia and Bipolar Disorders
	10.4 Conclusion
	References
11 Deep Learning Applications in Medical Image Analysis
	11.1 Introduction
		11.1.1 Medical Imaging
		11.1.2 Artificial Intelligence and Deep Learning
		11.1.3 Processing in Medical Images
	11.2 Deep Learning Models and its Classification
		11.2.1 Supervised Learning
		11.2.2 Unsupervised Learning
	11.3 Convolutional Neural Networks (CNN)— A Popular Supervised Deep Model
		11.3.1 Architecture of CNN
		11.3.2 Learning of CNNs
		11.3.3 Medical Image Denoising using CNNs
		11.3.4 Medical Image Classification Using CNN
	11.4 Deep Learning Advancements—A Biological Overview
		11.4.1 Sub-Cellular Level
		11.4.2 Cellular Level
		11.4.3 Tissue Level
		11.4.4 Organ Level
	11.5 Conclusion and Discussion
	References
12 Role of Medical Image Analysis in Oncology
	12.1 Introduction
	12.2 Cancer
		12.2.1 Types of Cancer
		12.2.2 Causes of Cancer
		12.2.3 Stages of Cancer
		12.2.4 Prognosis
	12.3 Medical Imaging
		12.3.1 Anatomical Imaging
		12.3.2 Functional Imaging
		12.3.3 Molecular Imaging
	12.4 Diagnostic Approaches for Cancer
		12.4.1 Conventional Approaches
		12.4.2 Modern Approaches
	12.5 Conclusion
	References
13 A Comparative Analysis of Classifiers Using Particle Swarm Optimization-Based Feature Selection
	13.1 Introduction
	13.2 Feature Selection for Classification
		13.2.1 An Overview: Data Mining
		13.2.2 Classification Prediction
		13.2.3 Dimensionality Reduction
		13.2.4 Techniques of Feature Selection
		13.2.5 Feature Selection: A Survey
		13.2.6 Summary
	13.3 Use of WEKA Tool
		13.3.1 WEKA Tool
		13.3.2 Classifier Selection
		13.3.3 Feature Selection Algorithms in WEKA
		13.3.4 Performance Measure
		13.3.5 Dataset Description
		13.3.6 Experiment Design
		13.3.7 Results Analysis
		13.3.8 Summary
	13.4 Conclusion and Future Work
		13.4.1 Summary of the Work
		13.4.2 Research Challenges
		13.4.3 Future Work
	References
Index