Next Generation Healthcare Informatics (Studies in Computational Intelligence, 1039)

✍ Scribed by B. K. Tripathy (editor), Pawan Lingras (editor), Arpan Kumar Kar (editor), Chiranji Lal Chowdhary (editor)

• Publisher: Springer
• Year: 2022
• Tongue: English
• Leaves: 320
• Category: Library

✦ Synopsis

This edited book provides information on emerging fields of next-generation healthcare informatics with a special emphasis on emerging developments and applications of artificial intelligence, deep learning techniques, computational intelligence methods, Internet of medical things (IoMT), optimization techniques, decision making, nanomedicine, and cloud computing. The book provides a conceptual framework and roadmap for decision-makers for this transformation. The chapters involved in this book cover challenges and opportunities for diabetic retinopathy detection based on deep learning applications, deep learning accelerators in IoT and IoMT, health data analysis, deep reinforcement-based conversational AI agent in healthcare systems, examination of health data performance, multisource data in intelligent medicine, application of genetic algorithms in health care, mental disorder, digital healthcare system with big data analytics, encryption methods in healthcare data security, computation and cognitive bias in healthcare intelligence and pharmacogenomics, guided imagery therapy, cancer detection and prediction techniques, medical image processing for coronavirus, and imbalance learning in health care.

✦ Table of Contents

Preface
Contents
Editors and Contributors
Methods for the Recognition of Multisource Data in Intelligent Medicine: A Review and Next-Generation Trends
1 Introduction
2 Data Processing Steps
3 Machine Learning Methods
3.1 ID3
3.2 Linear Regression
3.3 Naive Bayesian
3.4 Support Vector Machines
3.5 K-NN
3.6 Artificial Neural Network
3.7 Long Short-Term Memory
4 Model Evaluation
4.1 Creating Confusion Matrix
4.2 Establishing Accuracy Criteria for Two-Class Modeling
4.3 n-Fold Cross Validation
4.4 Receiver Operating Characteristic
4.5 Kappa Coefficient
5 Multimodal Data Fusion
5.1 Early Fusion
5.2 Late Fusion
5.3 Intermediate Fusion
6 Singular Modeling Experiments
7 Multimodal Experiments
7.1 In Medical Data sets: Literature Studies Using Early Fusion Technique in Multimodal Decision-Based Data Fusion Technique
7.2 In Medical Data sets: Literature Studies Using Late Fusion Technique in Multimodal Decision-Based Data Fusion Technique
7.3 In Medical Data Sets: Literature Studies Using Intermediate Fusion Technique in Multimodal Decision-Based Data Fusion Technique
7.4 Contribution to Multimodal Models
8 Discussion and Conclusion
References
Deep Learning in Healthcare: Applications, Challenges, and Opportunities
1 Introduction
2 Deep Learning Applications in Healthcare
2.1 Medical Imaging and Diagnosis
2.2 Simplification of Clinical Trials
2.3 Drug Discovery
2.4 Enhanced Patient Monitoring and Health Records
2.5 Personalized Treatment
3 Deep Learning Frameworks in Healthcare
3.1 Convolutional Neural Networks (CNN)
3.2 Recurrent Neural Network (RNN)
3.3 Autoencoder (AE)
3.4 Deep Synthetic Minority Oversampling Technique (SMOTE)
3.5 Elastic Net
3.6 Generative Adversarial Network (GAN)
4 Data Types Used in the Automated Healthcare
4.1 Electronic Health Record (EHR)
4.2 Clinical Imaging
4.3 Genomics
5 Challenges of Using Deep Learning in Healthcare
5.1 The Volume of Healthcare Data
5.2 Quality of Healthcare Data
5.3 Handling Healthcare Data Stream
5.4 Temporality
5.5 Complexity in Domain
5.6 Interpretability
6 Opportunities of Using Deep Learning in Healthcare
6.1 Feature Enhancement
6.2 Federated Extrapolation
6.3 Privacy in Modeling
6.4 Integrating Expert Knowledge
6.5 Temporal Modeling
6.6 Explainable Modeling
6.7 Computation Complexity
6.8 Multitasking Using Deep Learning
6.9 Semi-Supervised Learning for Healthcare Data
7 Conclusions and Future Scopes
References
Examination of Health Data Depending on Creative Use of Optimization Methods and Machine Learning Algorithms
1 Introduction
2 Background
3 Literature Review
4 Experimentation
5 Results and Recommendations
6 Future Research Directions
7 Conclusion
References
Effect of Computation and Cognitive Bias in Healthcare Intelligence and Pharmacogenomics
1 Introduction
2 Related Research
3 The Evolution of Clinical Prediction Models
4 Bias and Its Effect in ML-Based Healthcare Predictions
4.1 Computational Bias
4.2 Effectiveness of Bias in Machine Learning Models
5 The Influence of Bias in Healthcare Predictions
5.1 Real-World Examples
5.2 Pharmacogenomics and Bias
6 Conclusion and Future Scope
References
Application of Genetic Algorithms in Healthcare: A Review
1 Introduction
2 Preliminary Concept
2.1 Problems in Healthcare
2.2 Genetic Algorithm
3 Variants of Genetic Algorithm in Healthcare
3.1 Binary GA in Healthcare
3.2 Chaotic GA in Healthcare
3.3 Parallel GA in Healthcare
3.4 Multiobjective GA in Healthcare
4 Applications of GA in Healthcare
4.1 Oncology
4.2 Radiology
4.3 Cardiology
4.4 Surgery
4.5 Obstetrics and Gynaecology
4.6 Radiotherapy
5 Conclusion and Future Scope
References
Decision-Making in Healthcare Nanoinformatics
1 Introduction
2 Data Integration and Knowledge Discovery
2.1 Development of Research Centers for Nanotechnology in Medicine
2.2 Information Technology for Nanotechnology
2.3 Development and Recognition of Standards
2.4 Translational Nanoinformatics
2.5 E-Health Records with Nano-Based Information
3 Decision-Making in Healthcare and Informatics
3.1 Assessment of Healthcare Decision-Making Capacity
4 Decision Analysis in Nanoinformatics
4.1 Multicriteria Decision Analysis
4.2 Value of Information
4.3 Weight of Information
4.4 Portfolio Decision Analysis
5 Nanoinformatics and Biomolecular Computing
5.1 DNA and RNA-Based Computing
5.2 RNA-Based Computers
5.3 Future of DNA and RNA Computing
6 Nanotechnology in Biomedical Applications
6.1 Nanodevices and Nanomedicines
6.2 Nanoinformatics for Precision Medicine
7 Nanotechnology to Handle COVID
8 Issues and Challenges
8.1 Obstacles for Implementation of Nanotechnology in Health Care
9 Future Scope
10 Conclusions
References
A Succinct Analytical Study of the Usability of Encryption Methods in Healthcare Data Security
1 Introduction
2 Encryption and Its Use in Healthcare Data
2.1 Public Keys
2.2 Private Keys
3 The Need of Encryption
3.1 Data Interception in Cyberspace
3.2 Lost and Stolen Unencrypted Devices
3.3 The Ease and Importance of Encryption
4 Different Types of Encryptions
4.1 Symmetric Cryptography
4.2 Asymmetric Cryptography
5 Existing Works in Healthcare Data Security Using Encryption
6 Example of a Health Data Networking Model
7 Problems with Cryptography
8 Encryption Likelihood of Health-Related Data
9 Conclusions
10 Future Scope
References
IoMT in Healthcare Industry—Concepts and Applications
1 Introduction
2 Literature Survey
3 Architecture of Healthcare IoT (HIoT)
4 HIoT Technologies
4.1 Identification Technology
4.2 Communication Technology
4.3 Location Technology
5 Technologies Enduing IoMT Implementation
5.1 Local Systems and Control Layer
5.2 Device Connectivity and Data Layer
5.3 Analytic Solutions Layer
6 Advantages and Disadvantages of IoMT
7 Open Issues in the Implementation of IoMT
8 Services of IoT in Health care
8.1 Ambient Assisted Living. Ambient Assisted Living
8.2 Mobile IoT
8.3 Wearable Devices
8.4 Community-Based Healthcare Services
8.5 Cognitive Computing
8.6 Adverse Drug Reaction
8.7 Blockchain
8.8 Child Health Information
9 Healthcare Applications of IoT
9.1 ECG Monitoring
9.2 Glucose Level Monitoring
9.3 Temperature Monitoring
9.4 Blood Pressure Monitoring
9.5 Oxygen Saturation Monitoring
9.6 Asthma Monitoring
9.7 Mood Monitoring
9.8 Medication Management
9.9 Wheelchair Management
9.10 Rehabilitation System
9.11 Other Notable Applications
10 Case Study—Internet of Medical Things (IoMT) for Orthopaedic in COVID-19 Pandemic
10.1 Working Process of IoMT for Orthopaedic During COVID-19
10.2 Digital Connectivity of Hospital During COVID-19 Pandemic Using IoMT
10.3 Key-Roles of IoMT in Orthopaedic Field During COVID-19 Pandemic
11 Conclusion and Future Scope
References
The Effect of Heuristic Methods Toward Performance of Health Data Analysis
1 Introduction
2 Heuristic Methods
2.1 Biology-based Algorithms
2.2 Swarm Intelligence Algorithms
3 Heuristic Methods for the Health Data Analysis
3.1 Heuristic Methods for the Problems of Missing Value and Unbalanced Dataset in Health Data
3.2 Heuristic Methods for Feature Selection in Health Data
3.3 Heuristic Methods for Detection and Prediction of Diseases in Health Data
4 Results
5 Conclusion
References
AI for Stress Diagnosis at Home Environment
1 Introduction
1.1 Challenges
1.2 Major Goals and Contributions
1.3 Overview of the Proposed Approach
1.4 Area of Application
1.5 Structure of the Paper
2 Related Works and Analysis
2.1 Keystroke Dynamics-Based Stress Detections
3 Proposed Method
3.1 Event Monitoring
3.2 Pre-processing
3.3 Feature Selection
3.4 Bootstrapping and Building Model
3.5 Classification and Decision
4 Dataset and Implementation
4.1 Dataset
4.2 Feature Extraction and Selection
4.3 Windowing and Sampling
4.4 Outlier Detection and Removal
4.5 Statistical Features Extraction
4.6 Normalization
4.7 Classification and Evaluation
5 Experimental Results
5.1 Performance of the Proposed Model
6 Discussion
7 Performance Comparison
7.1 Model Complexity
7.2 Challenges, Advances, and Opportunities
8 Conclusions
References
Contemporary Technologies to Combat Pandemics and Epidemics
1 Introduction
2 Background
3 Main Focus of the Chapter
4 Issues, Controversies, Problems
4.1 Hindrance During the Spanish Flu
4.2 Hindrance During the SARS (2003)
4.3 Hindrance During the Zika Virus
4.4 Hindrance During the COVID-19
4.5 Comparing the Statistics
5 Solutions and Recommendations
5.1 Role of Technology
5.2 Information Gathering and Privacy Protection
5.3 Current Status
6 Future Scope
7 Conclusions
References
Deep Learning for Diabetic Retinopathy Detection: Challenges and Opportunities
1 Introduction
2 The Fundus Image
3 Diabetic Retinopathy
4 Deep Learning
4.1 Artificial Neural Network
4.2 Convolutional Neural Networks
4.3 Generative Adversarial Network
4.4 U-Net
4.5 Transfer Learning
4.6 Ensemble Learning
5 Preprocessing
5.1 Fundus Image Denoising
5.2 Fundus Image Normalization
5.3 Fundus Image Color Channel Extraction
5.4 Fundus Image Contrast Enhancement
5.5 Fundus Image Cropping and Resizing
5.6 Data Augmentation
6 A Brief Comparison of the Techniques Proposed for DR Detection and Segmentation
7 DL Challenges in DR Classification/Segmentation
7.1 Data-Related Challenges
7.2 Challenges in Terms of Availability of Ophthalmologists
7.3 Production Issues
7.4 Black Box Problem
7.5 Class Imbalance Problem
7.6 Data Privacy and Legal Issues
8 DL Opportunities
9 Conclusion
10 Future Scope
References
Deep Reinforcement-Based Conversational AI Agent in Healthcare System
1 Introduction
2 Literature Review
3 Methodology
3.1 Natural Language Understanding
3.2 Dialog Management
3.3 Natural Language Generation
3.4 Textual Question Answering
3.5 Text Summarization
3.6 Visual Question Answering
3.7 Anomaly Detection
4 Results
5 Conclusion
References
Deep Learning Empowered Fight Against COVID-19: A Survey
1 Introduction
2 Methodology Used in This Survey
2.1 Sources
2.2 Keywords
2.3 Inclusion and Exclusion Criteria
3 Deep Learning-Based Systems Used for Diagnosis and Prevention of COVID-19
3.1 Collecting Samples
3.2 Radiology
3.3 Surgery
3.4 Medicine and Antiviral Therapeutics
3.5 Convalescent Plasma Therapy is a New Medication Approach
3.6 Prediction
3.7 Detection
3.8 Response and Recovery
3.9 Hospital
3.10 Drone Technology and Delivery of Goods
3.11 Surveillance
3.12 Robotics Technologies
4 Discussion
5 Summary
References
Application of GAN in Guided Imagery Therapy
1 Guided Imagery (GI) Therapy
2 Applications of Guided Image (GI) Therapy
3 Introduction to Generative Adversarial Networks (GAN)
4 Different Types of GAN
5 Application of DCGAN in Guided Imagery Therapy
6 The Proposed Methodology
7 Conclusion and Future Work
References
Digital Transformation in Healthcare Industry: A Survey
1 Introduction
1.1 Healthcare with AI and ML
2 Healthcare Industry Application Programming Interface
2.1 Importance of APIs in the Development of Human Health
3 Challenges in Digital Transformation of Healthcare
4 Future of Healthcare Technology
4.1 Technology Trends in Healthcare
5 Contribution of Digital Transformation
6 Relevant Case Studies
6.1 Case Study of Africa
6.2 Case Study of Poland
7 Conclusions and Scope for Future Studies
References
Application of Deep Learning in Mental Disorder: Challenges and Opportunities
1 Introduction
2 Mental Disorder
2.1 Fundamental of Mental Disorder
2.2 Taxonomy of Mental Disorder
3 Deep Learning Techniques and Architecture
3.1 Fundamental of Deep Learning in Healthcare
3.2 Architecture of Deep Learning
3.3 Deep Learning Architecture for Mental Disorder
4 Challenges and Opportunities
4.1 Challenges in Mental Disorder
4.2 Challenges and Limitations When Applying Deep Learning to Mental Disorder
4.3 Data Creation and Annotation
4.4 How Accurately and Precisely Measure Mental Disorder Similarity
4.5 Quality Global Healthcare
5 Deep Learning Implementation
5.1 Mental Disorder Dataset
5.2 Experiments and Performance Measures Used
5.3 Experimental Results and Discussion
6 Conclusions and Future Scope of Research
References