Advanced Prognostic Predictive Modelling in Healthcare Data Analytics (Lecture Notes on Data Engineering and Communications Technologies, 64)

Preface
Contents
Editors and Contributors
Data Visualization in the Transformation of Healthcare Industries
	1 Introduction
		1.1 Reasons Behind the Use of Data Visualization Tools in Health Care
		1.2 Key Benefits of Medical Dashboards for Healthcare Providers
	2 Data Visualization Tools and Applications
		2.1 Visualization Tool Types and Advantages
		2.2 Examples of Data Visualization Tools
	3 How Data Visualization Has Transferred the Healthcare Industry
		3.1 Infographics
		3.2 Control Panel Analytics
		3.3 Customized Data Visualization in Healthcare Industries
		3.4 Interactive Widgets
	4 Recent Advancements in Data Visualizations of the Medical Care
		4.1 Healthcare Dashboards
		4.2 Global Health Parameters
		4.3 Visualization Tools for Health Score Computation
	5 Safety and Security Issues with These Tools
	6 Conclusions
	References
Emerging Healthcare Problems in High-Dimensional Data and Dimension Reduction
	1 Introduction
	2 Related Work
	3 Methodology
		3.1 Principle Component Analysis (PCA)
		3.2 Linear Discriminant Analysis (LDA)
		3.3 tDistributed Stochastic Neighborhood Embedding (t-SNE)
		3.4 Singular Value Decomposition (SVD)
	4 Result and Discussion
	5 Conclusion
	References
Applications of Fuzzy Logic in Bioinformatics: A Survey
	1 Introduction
	2 A Prolegomena to FRB Models and FRBD Models
	3 Basic Structure of FRB Models
		3.1 Linguistic Variables
		3.2 If-Then Fuzzy Rules
		3.3 Inference Procedure in FRB-Models
		3.4 Defuzzification Methods
	4 Basic Structure of the FRBD Model
	5 Example of Some Models Based on FRB Models and FRBD Models
	6 Discussion and Conclusion
	References
Disease Prediction Using Data Mining and Machine Learning Techniques
	1 Introduction
	2 Related Work
	3 Methodology
		3.1 Naive Bayes
		3.2 Decision Tree
		3.3 Logistic Regression
		3.4 Random Forest
		3.5 Convolutional Neural Networks
		3.6 Recurrent Neural Networks
	4 Results
		4.1 Cancer Data Set
		4.2 Brain Tumor Data Set
	5 Conclusion
	References
Spatial Contextual Thresholding Technique: A Case Study to Detect Nodule of Thyroid in Ultrasound Images
	1 Introduction
	2 Material and Techniques
		2.1 Image Dataset
		2.2 Evaluation Metrics
		2.3 Techniques
	3 Results and Discussion
	4 Conclusion and Future Scope
	References
Cognitive Intelligent Healthcare (CIH) Framework by Integration of IoT with Machine Learning for Classification of Electroencephalography (EEG)
	1 Introduction
	2 Related Works
	3 Aim
	4 Objective
	5 Existing System
		5.1 Disadvantages of Existing System
	6 Internet of Things: Problems and Challenges
	7 Proposed Methodology
		7.1 System Model
		7.2 Cognitive Intelligent Healthcare (CIH) Framework
		7.3 Pulse Sensor
		7.4 Oxygen Monitoring Sensor
		7.5 Arduino Uno Control Unit
		7.6 Pre-processing of EEG Signal
		7.7 Feature Extraction and Feature Selection
		7.8 Logistic Regression (LR) Model for EEG Classification
	8 Results and Discussion
	9 Conclusion
	References
Prognostic Modeling with the Internet of Healthcare Things Applications
	1 Introduction
	2 IoT in Healthcare
	3 Prognostic Modeling (PM) and Prognostic Health Modeling (PHM) with IoT
		3.1 Role of ML and DL Techniques
		3.2 Role of Artificial Intelligence (AI)
		3.3 Role of Big Data and Cloud Computing (CC)
	4 Application of Prognostic Modeling
	5 Advantages
	6 Limitations
	7 Conclusion
	8 Future Prospect
	References
Cancer Tissue Segmentation in Various Conditions with Semiautomatic and Automatic Approach
	1 Introduction
		1.1 Medical Image Analysis
		1.2 Segmentation
	2 Basic Segmentation Methods
		2.1 Point Detection
		2.2 Line Detection
		2.3 Edge Detection
		2.4 Edge Processing and Boundary Recognition
		2.5 Thresholding
		2.6 Region-Based Segmentation
		2.7 Template Matching
		2.8 Texture Segmentation
	3 Semiautomatic Segmentation
		3.1 Random Forest
		3.2 Graph-Cut Method
		3.3 Random Walk Algorithm
		3.4 Atlas-Based Methods
	4 Fully Automatic Segmentation
		4.1 Supervised Learning Algorithms
		4.2 Unsupervised Learning Algorithms
		4.3 Deep Learning Methods
	5 Conclusion
	References
Diabetes Prediction Using Machine Learning Approaches
	1 Introduction
		1.1 Different Types of Diabetes
		1.2 Machine Learning Approaches
		1.3 Objective of This Study
	2 Related Works
	3 Background
		3.1 Description of Classifier Models
		3.2 Performance Evaluating Metrics
	4 Dataset Used
	5 Experimental Results
	6 Conclusions
	References
Prediction of Pneumonia from Chest X-Ray Images Using Pre-trained Convolutional Neural Networks
	1 Introduction
	2 Related Work
	3 Pre-trained Convolutional Neural Network Model
	4 Experimental Results and Discussions
		4.1 About Datasets
		4.2 Performance Evaluation on Benchmark Datasets
	5 Conclusions
	References
Early Screening of COVID-19 from Chest CT Using Deep Learning Technique
	1 Introduction
		1.1 History
		1.2 Epidemiology and Pathogenesis
		1.3 Clinical Features
		1.4 Treatment
		1.5 Prevention
	2 Introduction to Deep Learning
		2.1 History
		2.2 Architecture
		2.3 Applications
	3 Proposed Method
		3.1 Methodology
	4 Process
		4.1 Segmentation of COVID-19 from CT Scans
		4.2 Details of the Architecture
		4.3 Segmentation
		4.4 Performance Measurement
	5 Result and Discussion
	6 Conclusion
	References
A Probe into Performance Analysis of Real-Time Forecasting of Endemic Infectious Diseases Using Machine Learning and Deep Learning Algorithms
	1 Introduction
		1.1 Big Data Computational Epidemiology
		1.2 Related Work
	2 Materials and Methods
		2.1 Data Set
		2.2 Proposed Methodologies
	3 Application of Machine Learning Techniques to Cholera Outbreak Prediction
	4 Application of LSTM to Cholera Outbreak Prediction
		4.1 Adam
		4.2 Stochastic Gradient Descent
		4.3 Stochastic Gradient Descent with Momentum
		4.4 Root Mean Square Propagation
		4.5 Gradient Clipping
		4.6 L2 Regularization
		4.7 Performance Evaluation Metrics
	5 Result and Discussion
		5.1 Performance Metrics Using Machine Learning Algorithms
		5.2 Performance Metrics Using Long Short-Term Memory Algorithm
	6 Conclusion
	References
Clinical Decision-Making and Predicting Patient Trajectories
	1 Introduction
		1.1 Steps in Predictive Analysis
		1.2 Descriptive Analytics: Insight into the Past
		1.3 Predictive Analytics: Understanding What Is to Come
		1.4 Prescriptive Analytics: Understanding What’s to Return
		1.5 Prescriptive Analytics: Advice on Possible Outcomes
	2 Technology and Development
		2.1 Systems (Precision) Medicine
		2.2 Personal Medicine
		2.3 Population Health and Risk Scoring
		2.4 Integrated Care
	3 Advantages
		3.1 Digital Health Tools
		3.2 Enhanced Clinical Predictive Modeling
		3.3 Computer-Aided Diagnosis (CAD)
		3.4 Localization and Segmentation
		3.5 Feature Extraction and Classification
	4 Disease Diagnosis and Prognosis
		4.1 Machine Learning (ML) in Medicine
	5 Classical ML Versus Deep Learning Methods
		5.1 State-of-the-Art ML for Cancer Diagnosis/Prognosis
	6 Predicting Cancer Survival
		6.1 Deep Learning and Cancer
		6.2 Model Development and Validation
		6.3 Model Development
		6.4 In Practice
	7 AI in Clinical Healthcare Delivery
		7.1 Clinical Decision Support
		7.2 Image Processing
		7.3 Health Systems
		7.4 Readiness and Governance
	8 Medical Prediction
		8.1 Improve Results
	9 Cohort Treatment
	10 Electronic Decision
	11 Disease-Based Prediction
		11.1 Inflectional Disease
		11.2 Heart
		11.3 Kidney (CKD)
		11.4 Breast Cancer
		11.5 Cervical Cancer
		11.6 Drug Treatment
		11.7 Technical Implementation—Simulation
	12 Discussions
	References