Machine Learning with Health Care Perspective (Learning and Analytics in Intelligent Systems, 13)

✍ Scribed by Jain

• Publisher: Springer
• Year: 2020
• Tongue: English
• Leaves: 418
• Category: Library

✦ Synopsis

This unique book introduces a variety of techniques designed to represent, enhance and empower multi-disciplinary and multi-institutional machine learning research in healthcare informatics. Providing a unique compendium of current and emerging machine learning paradigms for healthcare informatics, it reflects the diversity, complexity, and the depth and breadth of this multi-disciplinary area. Further, it describes techniques for applying machine learning within organizations and explains how to evaluate the efficacy, suitability, and efficiency of such applications. Featuring illustrative case studies, including how chronic disease is being redefined through patient-led data learning, the book offers a guided tour of machine learning algorithms, architecture design, and applications of learning in healthcare challenges.

✦ Table of Contents

Preface
What You Will Learn?
Who This Book Is For?
Contents
Machine Learning for Healthcare: Introduction
1 Introduction
2 Data Preparation (EDA)
2.1 Feature Cleaning
3 Feature Engineering
3.1 Feature Transformation
3.2 Feature Extraction
3.3 Feature Selection
4 Machine Learning Models to Classify Healthcare Data
4.1 Logistic Regression (LoR)
4.2 Neural Networks (NN)
4.3 K Nearest Neighbor (KNN)
4.4 Support Vector Machine (SVM)
4.5 Decision Tree (DT)
4.6 Ensemble
5 Diagnosing Model Performance
6 Experimental Setups
7 Results and Discussion
7.1 Data Preparation (EDA)
7.2 Feature Engineering
7.3 Building Model
7.4 Evaluating Model Performance
8 Conclusions
References
Artificial Intelligence in Medical Diagnosis: Methods, Algorithms and Applications
1 Introduction
2 Machine Learning Techniques (ML)
3 Natural Language Processing (NLP)
4 AI Resources
5 Application of AI in Medical Diagnosis
6 Conclusion
References
Intelligent Learning Analytics in Healthcare Sector Using Machine Learning
1 Introduction
2 Motivation
3 Machine Learning
3.1 Advantageous Sectors of Machine Learning
3.2 Machine Learning Challenges
4 Machine Learning Tools
5 Proposed Machine Learning Model in the Healthcare Sector
5.1 Objective
5.2 Pre-processing of Data
5.3 Results and Discussions
6 Machine Learning Approaches
6.1 Supervised Learning Approach
6.2 Unsupervised Learning Applications in Healthcare
7 Conclusion
References
Unsupervised Learning on Healthcare Survey Data with Particle Swarm Optimization
1 Introduction
1.1 Machine Learning
1.2 Data Science in Healthcare
1.3 Related Terms
2 Unsupervised Learning
2.1 Types of Unsupervised Learning
2.2 Challenges of Unsupervised Learning
3 Clustering Algorithms
3.1 K-Means Algorithm
3.2 Expectation Maximization Algorithm
3.3 GenClust++
3.4 Density Based Clustering
4 Particle Swarm Optimization (PSO) Algorithm
4.1 PSO with Subset Evaluator
5 Designing an Experimental Setup
5.1 Healthcare Survey Dataset with Unsupervised Learning
5.2 Procedure and Techniques
5.3 Various Stages of Experimentation
6 Results
6.1 Outcome of IQR Filtered Dataset
6.2 Outcome of PSO Optimized Attribute Dataset
6.3 Discussion on the Result
7 Conclusion
References
Machine Learning for Healthcare Diagnostics
1 Introduction
2 Machine Learning
3 Machine Learning for Medical Diagnosis
3.1 Types of Machine Learning Systems
4 Role of Machine Learning in Healthcare
4.1 Hospital Management and Patient Care
5 Data Analysis in Public Health
5.1 Pattern Matching in Genetic Research
5.2 Disease Diagnostics
6 ML Applied in Medical Diagnostics
7 Datasets
8 Evaluation Metrics
8.1 Classification Accuracy
8.2 Logarithmic Loss
8.3 Confusion Matrix
8.4 Area Under Curve (AUC)—ROC
8.5 F1 Score
8.6 Kolmogorov Smirnov Chart
8.7 Mean Absolute Error
8.8 Mean Squared Error (MSE)
9 Conclusion
References
Disease Detection System (DDS) Using Machine Learning Technique
1 Introduction
2 Previous Related Works
3 System Implementation and Disease Detection Methodology
4 Proposed DDS Model
4.1 Architecture of DDS
4.2 Use Case Diagram of DDS
4.3 Context Diagram of the DDS
5 Accuracy Comparison
5.1 Accuracy Comparison of DDS with Previous Works
6 Simulation for Result
7 Conclusion
References
Knowledge Discovery (Feature Identification) from Teeth, Wrist and Femur Images to Determine Human Age and Gender
1 Introduction
2 Features of Teeth to Identify Age and Gender
2.1 Related Works on Teeth
2.2 Gender Assessment Using Canine Index Method
3 Features of Wrist Bone to Identify Age and Gender
3.1 Related Works on Wrist
3.2 Tanner-Whitehouse (TW) Method
3.3 Computer-Assisted Wrist Bone Age Assessment System
4 Features of Femur Bone to Identify Age and Gender
5 Related Works on Femur
5.1 Gender Identification Rule Based on Femoral Angle
6 Conclusion
7 Future Scope
Bibliography
Deep Learning Solutions for Skin Cancer Detection and Diagnosis
1 Introduction
1.1 Background
1.2 Motivation
1.3 Objective and Scope
2 Background
2.1 Convolutional Neural Network for Image Classification
2.2 Working of Convolution Neural Networks
2.3 Skin Lesion Classification Using CNN
3 Methods and Dataset
3.1 Dataset
3.2 Method Overview
3.3 Network Architecture
4 Results and Discussion
4.1 Performance Metrics
4.2 Hyperparameters
4.3 Model Performance
4.4 Comparison and Discussion
4.5 Conclusion
References
Security of Healthcare Systems with Smart Health Records Using Cloud Technology
1 Introduction
1.1 Cloud Computing in Healthcare
2 Cloud Service Models
3 Deployment Models in Cloud Computing
4 Cloud Computing Security
4.1 Healthcare Data Security in the Cloud
5 Key Issues Pertaining to Cloud Computing Security in Healthcare Systems
6 Brief Description of Some Cloud Computing Algorithms and Their Comparison
7 Conclusion
References
Intelligent Heart Disease Prediction on Physical and Mental Parameters: A ML Based IoT and Big Data Application and Analysis
1 Introduction
1.1 Machine Vision
1.2 Medical Images
1.3 Analysis of Medical Images
1.4 Application of Machine Vision
1.5 BD and IoT Applications
1.6 Manage Lifestyle: Solution to the Issue Raised
1.7 Tension Type Headache
2 Literature Survey
2.1 TTH and Stress
2.2 Heart Disease Prediction
3 Product Perspective
3.1 System Interfaces
3.2 Product Functions
3.3 UML Diagrams
4 Experimental Setup and Product Configuration
4.1 Hardware Requirements
4.2 Software Requirements
4.3 Implementation Activities
4.4 Development
5 Results, Interpretation and Discussion
5.1 Implementation Snapshots of Interfaces
5.2 Graphical Analysis and Results Discussion
5.3 Performance Evaluation
6 Limitations of System
6.1 Limited Dataset
6.2 Lack of Suggestions Based on Risk
6.3 Lack of Trust on Machines
6.4 Assistive Tool
7 Recommendations
8 Novelty and Advantages of Experimental Work and Product
8.1 System Faster Diagnosis
8.2 Reduced Medical Errors and Misdiagnoses
8.3 Easy to Use
8.4 No Human Intervention Required
9 Future Scope and Possible Applications
10 Conclusions
Appendix
References
Medical Text and Image Processing: Applications, Issues and Challenges
1 Introduction
1.1 ML in Medical Text and Image Processing
1.2 Deep Learning (DL) in Medical Text and Image Processing
1.3 Natural Language Processing (NLP) in Medical Text Processing
1.4 Computer Vision for Medical Image Processing
2 Medical Images and Texts Datasets
2.1 Types of Medical Texts
2.2 Types of Medical Images
2.3 Medical Image Data Sets
2.4 Medical Data Processing Tools and Technologies
3 Challenges
4 Research Directions
5 Conclusion
References
Machine Learning Methods for Managing Parkinson’s Disease
1 Introduction
2 Current Scenario
2.1 Diagnosis
2.2 Treatment
3 Concerns and Challenges
3.1 Diagnosis
3.2 Treatment
4 Application of Machine Learning in Parkinson Disease
4.1 General Workflow
5 Implementation: Machine Learning in Parkinson Disease
5.1 Example 1: Voice Data Based Early Diagnosis
5.2 Example 2: Tappy Keystroke
5.3 Treatment Monitoring
6 Futuristic Developments
7 Conclusion
References
An Efficient Method for Computer-Aided Diagnosis of Cardiac Arrhythmias
1 Introduction
2 Methods
2.1 Feature Extraction Using EMD
2.2 Support Vector Machine (SVM)
2.3 Particle Swarm Optimization (PSO)
3 Proposed Method
3.1 ECG Data
3.2 Preprocessing
3.3 Localization of R-Wave and Heartbeat Segmentation
3.4 Input Representation in Lower Dimensions
3.5 Heartbeat Variability Features
3.6 Feature Classification
3.7 Performance Metrics
4 Simulation Results
4.1 Comparative Study
5 Conclusion
References
Clinical Decision Support Systems and Predictive Analytics
1 Introduction
2 History and Development of CDSS
2.1 History of Decision Making
2.2 The Problem of Points
2.3 The Game of Chance Problem
2.4 Growth of CDSS Literature
3 Emerging Trends in CDSS
3.1 CDSS for Cost Reduction and Risk of Readmission
3.2 Use of Big Data
3.3 Fuzzy Logic and Artificial Intelligence (AI)
4 Major Issues in the Implementation of CDSS
4.1 Conversion of Research into Practice
4.2 Information Flow
4.3 Reluctance of the Stakeholders
5 Types of CDSS
5.1 Knowledge-Based and Non-knowledge-Based CDSS
5.2 Active and Passive CDSS
5.3 Classification of CDSS Based on Type of Intervention
5.4 Classification Based on Application of CDSS
6 Artificial Intelligence (AI) in CDSS
6.1 SVM in CDSS
6.2 ANN in CDSS
6.3 Natural Language Processing (NLP) in CDSS
7 Predictive Analytics in CDSS
7.1 Data Mining and Predictive Analytics
7.2 Classification Technique
7.3 Clustering Techniques
7.4 Association Rule Technique
8 Conclusion
References
Yajna and Mantra Science Bringing Health and Comfort to Indo-Asian Public: A Healthcare 4.0 Approach and Computational Study
1 Introduction
1.1 Status of Healthcare in Indian Context
1.2 Need of Health Research
1.3 Computational Intelligence
1.4 Mist and Edge Computing
2 Yajna and Mantra Science
2.1 Effect of Mantra and Yajna
2.2 Societal Impact of Yajna and Mantra Therapy
2.3 Yajna and Mantra Science: Future and Alternate Therapy
3 Healthcare 4.0 with Fog Computing on Inhaling Therapies
3.1 Role of Technology in Addressing the Problem of Integration of Healthcare System
3.2 Scientific Study on Impact of Yajna on Air Purification
3.3 Expert System Design
3.4 Robotics
3.5 Computer Control System Design
3.6 Machine Learning Algorithms
3.7 Expert System
3.8 Ambient Computing
3.9 Computer Application in Information and Communication Technology
3.10 Hybrid Intelligent Systems
3.11 Symbolic Machine Learning
3.12 Neuro-Fuzzy System
3.13 Nature Inspired Computing
4 Literature Survey
5 Methodology
5.1 Instruments Required
5.2 Experimental Setup of an Expert System
5.3 Flow Chart of Healthcare Expert System
5.4 Parameters and Factors Under Study
6 Results and Discussion
6.1 Results, Interpretation and Analysis on Healthcare Experiments
6.2 Asthma Related Experiments
7 Novelty in Our Work
8 Recommendations
9 Future Scope, Limitations, Applications of Yagya and Mantra Therapy
9.1 Future Scope
9.2 Limitations
9.3 Applications
10 Conclusion
References
Identifying Diseases and Diagnosis Using Machine Learning
1 Introduction
2 Inevitability of Machine Learning in Healthcare
3 Learning Healthcare System (LHS)
4 Population Health Management
5 The Goal of Using ML Algorithms in Healthcare
5.1 ML in Medical Imaging
5.2 Healthcare Accuracy Medication
5.3 Assembling Patient Testified Consequences and Full Pathway Prices for Value-Based Healthcare
5.4 Enhancing Workflows in Healthcare
5.5 Contamination Inhibition, Estimate and Control
5.6 Public Decision Support
5.7 Home-Based Care
5.8 Scientific Research
6 Spread Over Machine Learning Towards Health Care
6.1 Machine Learning Algorithms
7 Machine Learning in Health Care Diagnostics
7.1 Resolving Medical Diagnostic and Prognostic Difficulties Using Machine Learning System
7.2 Disease Prediction Using Machine Learning
8 Applications of Machine Learning in Medical Diagnosis
8.1 Identification of Diseases and Diagnosis
8.2 Medication Discovery and Manufacturing
8.3 Health Imaging Diagnosis
8.4 Personalized Medicine
8.5 Smart Health Records
8.6 Clinical Trial and Research
9 Conclusion
References