Concepts of Artificial Intelligence and its Application in Modern Healthcare Systems

Cover
Half Title
Title Page
Copyright Page
Contents
Preface
About the Authors
Contributors
1. Artificial Intelligence (AI) in Healthcare: Issues, Applications, and Future
1.1 Introduction
1.2 Revolutions of Artificial intelligence (AI) in Medical Field
1.3 Application Areas of AI in Healthcare
1.3.1 Patient Care
1.3.2 Medical Imaging and Diagnostic
1.3.3 Research and Development
1.3.4 Healthcare Management
1.3.5 Artificial Intelligence in Statistical Analysis
1.3.5.1 Pharmaceutical Use
1.3.5.2 Outbreak Prevention and Tracking
1.3.5.3 Genetics
1.4 Use in the Development of Medicine and Vaccines
1.4.1 Challenges Faced in Drug Development
1.4.2 AI in Drug Development
1.4.3 AI in Pattern Recognition
1.5 Limitation of Artificial Intelligence in Healthcare
1.5.1 Security Concerns
1.5.2 Information Accessibility Training
1.5.3 Predisposition and Imbalance
1.5.4 Wounds and Blunders
1.6 Predictions of Future Artificial Intelligence (AI) in Healthcare
1.7 Conclusion and Future Work
References
2. Artificial Intelligence in Medical Imaging for Developing Countries: Challenges and Opportunities
2.1 Introduction
2.2 Machine Learning and Deep Learning
2.3 AI Healthcare in India
2.3.1 Government Initiatives
2.3.2 The Startups in India
2.4 Background and Related Work
2.4.1 Medical Imaging
2.5 Methodology
2.6 Issues and Challenges in Indian Healthcare Sector
2.7 Challenges of AI in Healthcare
2.8 Applications of AI
2.9 Opportunities in AI Healthcare
2.9.1 Medical Imaging
2.9.2 Pharmaceutical Discovery
2.9.3 Disease Identification
2.9.4 AI-enabled Surgery
2.9.5 Diseases Prediction
2.10 Study Findings
2.11 Present and Future Scope
2.12 Conclusion
Acknowledgments
References
3. Artificial Intelligence in Medical Imaging
3.1 Image Segmentation
3.2 Watershed Algorithm
3.2.1 Watershed with Distance Transform
3.2.2 Gradient-Based Method
3.2.3 Marker-Controlled Methods
References
4. Medical Image Fusion: Transforms Techniques-Based Comparative Analysis for Brain Disease
4.1 Introduction
4.1.1 Non-Subsampled Shearlet Transform (NSST)
4.1.2 Description of NSCT
4.2 Proposed Hybrid Algorithm (NSCT-NSST)
4.2.1 An Overview of Proposed (NSCT-NSST) Algorithm
4.2.2 Applying NSST to the NSCT Decomposed Image
4.3 Results and Discussion
4.4 Conclusion
References
5. Artificial Intelligence and Medical Visualization
5.1 Introduction
5.1.1 Artificial Intelligence
5.1.2 Artificial Intelligence in Healthcare
5.2 Fundaments of Medical Visualization
5.2.1 Early Stage
5.2.2 Current Trends
5.3 AI Techniques in Medical Visualization
5.3.1 ML in Medical Visualization
5.3.1.1 What Is Machine Learning?
5.3.1.2 Algorithm of Machine Learning
5.3.1.2.1 Neural Networks
5.3.1.2.2 K-nearest Neighbours
5.3.1.2.3 Support-Vector Machines
5.3.1.2.4 Decision Tree
5.3.1.2.5 Naive Bayes Algorithm
5.3.1.3 Application of ML
5.3.1.3.1 ML in Skin Cancer Detection
5.3.1.3.2 Machine Learning in COVID-19 Diagnosis
5.3.1.3.3 Machine Learning in Diagnosing Breast Cancer
5.3.1.3.4 ML in Diagnosing Eye Diseases
5.3.1.3.4.1 Fundus photography
5.3.1.3.4.2 Optical Coherence Tomography (OCT):
5.3.1.3.4.3 Slit Lamp
5.3.1.3.5 ML in Diagnosing Brain Disorder
5.3.2 Deep Learning in Medical Visualization
5.4 AI Software in Medical Visualization
5.5 AI-based Medical Image Segmentation for 3D Printing
5.5.1 Segmentation Techniques
5.5.2 Application of AI-based Segmentation for 3D Printing
5.6 Conclusion
References
6. Machine-Learning Models for Early Diagnosis of Depressive Mental Affliction
6.1 Introduction
6.2 Literature Review
6.2.1 Diagnostic Tools and Scales for Depression
6.3 Materials and Methods
6.3.1 Dataset
6.3.2 Cleaning and Standardizing the Dataset
6.3.3 Balancing the Dataset
6.3.4 Training and Cross-Validation
6.3.4.1 K-Nearest Neighbors Classifier
6.3.4.2 Decision Tree
6.3.4.3 Linear Discriminant Analysis
6.3.4.4 Gaussian Naive Bayes
6.3.4.5 Support-Vector Machine
6.4 Experimental Results
6.4.1 Tools and Set-up
6.4.1.1 Scikit Learn
6.4.1.2 Imblearn
6.4.1.3 Numpy
6.4.1.4 Pandas
6.4.1.5 Joblib
6.4.1.6 Kivy
6.4.2 Evaluating the Efficacy of Models
6.4.2.1 Accuracy
6.4.2.2 AUC-ROC
6.4.2.3 Precision
6.4.2.4 Recall
6.4.2.5 F1 score
6.5 Discussion
6.6 Limitations
6.7 Conclusion
References
7. Non-Invasive Technique of Breast Cancer Diagnosis Using Interpretation of Fractal Dimension of Cells Nuclei in Buccal Epithelium
7.1 Introduction
7.2 Malignant-associated Changes in Buccal Epithelium
7.3 Breast Cancer Diagnosis Using Machine Learning
7.4 Materials and Methods
7.5 Fractal Analysis of Chromatin
7.6 Algorithm Adaboost
7.6.1 Algorithm Adaboost-SAMME
7.6.2 Decision Tree
7.6.3 Testing Adaboost
7.6.4 Conclusions on Adaboost
7.7 Algorithm Random Forest
7.7.1 Random Forest
7.7.2 Logistic Regression
7.7.3 Testing Random Forest
7.7.4 Conclusions on Random Forest
7.8 Conclusion
References
8. Fractionalization of Early Lung Tumour Regions and Detection Using a Low Intricacy Approach
8.1 Introduction
8.1.1 Significance of Lung Tumours
8.1.2 Issues with Lung Tumour Detection
8.1.3 Image Processing for Tumour Detection
8.1.4 Objectives
8.2 Literature Survey
8.2.1 Review for Image Preprocessing Techniques
8.2.2 Review for Feature Extraction
8.2.3 Review for OTSU Segmentation
8.2.4 Review for Quadtree Decomposition
8.3 Experimental Work/Methodology
8.3.1 Pre-processing Methodologies
8.3.1.1 Selection of CT Scan Images
8.3.1.2 Grayscale Conversion
8.3.1.3 Top-Hat Filtering
8.3.1.4 Plotting Histogram and Image Binarization
8.3.1.5 Distance Transformation
8.3.1.6 Watershed Transform
8.3.2 OTSU Segmentation
8.3.3 Analysis Using Quadtree Decomposition
8.3.4 Comparison Using Distribution Plots
8.4 Results and Discussion
8.4.1 Pre-processing Outputs
8.4.2 OTSU Segmentation Outputs
8.4.3 Analysis Using Quadtree Decomposition
8.4.4 Comparison of Histograms Using Distribution Plots
8.5 Conclusions and Further Work
References
9. Reshaping the Pathology: An AI Perspective
9.1 Introduction: Background and Driving Forces
9.1.1 How Does AI Operate?
9.1.2 The Three Cognitive Skills of AI
9.2 AI Advancement in Pathology: An Introduction
9.3 Literature Review
9.3.1 Artificial Intelligence in Pathology
9.3.1.1 Applications in Medical Imaging
9.3.1.2 Addressing Bio-disaster X Threats with Artificial Intelligence and 6G Technologies
9.3.1.3 Prostate Cancer Risk Stratification via Light Sheet Microscopy
9.3.1.4 The Applications of Artificial Intelligence in Chest Imaging of COVID-19 Patients
9.3.1.5 A Narrative Review of Digital Pathology and Artificial Intelligence Focusing on Lung Cancer
9.3.1.6 Artificial Intelligence-based Analysis of Genetic Data
9.3.1.7 First FDA-cleared AI Product in Digital Pathology
9.4 Methodology
9.5 Discussion
9.6 Future Scope
9.6.1 Challenges in the Implementation of Artificial Intelligence-based Diagnosis
9.7 Conclusion
References
10. Influence of Community Mobility Habits on the COVID-19 Pandemic: A Case Study on India
10.1 Introduction
10.2 COVID-19 and India
10.2.1 India During Lockdowns of COVID-19
10.2.2 COVID-19 Post-Lockdown Scenario in India
10.3 Method and Material
10.4 Results and Discussions
10.5 Conclusion
References
11. Impact of Social Media Platforms on Vaccination Drive during COVID-19 Pandemic in India
11.1 Introduction
11.1.1 How Does COVID-19 Spread?
11.1.2 Who is Most at Risk?
11.2 Proposed Approach
11.2.1 Dataset Description
11.2.2 Dataset Pre-Processing [3] and Visualisation
11.2.3 Feature Selection
11.2.4 Classification [3,5-7]
11.3 Conclusion and Future Work
Note
References
12. Pneumonia Detection Using Chest X-Ray with the Help of Deep Learning
12.1 Introduction
12.2 Literature Review
12.3 Technologies used in Pneumonia Detection
12.3.1 Deep Learning and NLP the Technologies Playing a Major Role in Real-Life Implementation
12.3.2 Chest X-ray of Different Stages in Case of Pneumonia
12.4 Proposed Methodology
12.4.1 Techniques and Architecture of Deep Learning Used in the Project as a Differentiating Factor
12.4.1.1 Neural Network
12.4.1.2 Artificial Neural Network (ANN)
12.4.1.3 Recurring Neural Networks (RNNs)
12.4.1.4 Convolution Neural Network (CNN)
12.4.1.5 ResNet
12.4.1.6 The Ideology of Natural Language Processing (NLP)
12.4.2 Methodologies Differentiating from Other Models
12.4.3 Use of Another Modern Resnet
12.4.4 Residual Block-Responsible for Establishing Skip Connection
12.5 Results and Discussion
12.6 Conclusion
References
13. AI Technique from Type CN2 Rule Induction for Industry 4.0 with Healthcare Problem
13.1 Introduction
13.2 Related Works
13.2.1 Coronavirus
13.2.2 Concept of Coronavirus
13.3 Coronavirus Patterns
13.4 Symptoms of Coronavirus
13.5 Coronavirus Transmission Methods
13.6 Rule Induction
13.7 Proposed System
13.8 Steps of Analysis
13.8.1 Collection of Data
13.8.2 Tools Used for the Analysis
13.9 Analysis of Results
13.10 Results of Answering and Debating the Study's First Question
13.10.1 In the Community, What is the Degree of Health Awareness?
13.10.2 Field 1, Symptoms of Transmission of the Virus
13.10.3 IF Conditions Then Action
13.10.3.1 Results of Addressing and Explaining the Second Question in the Analysis
13.11 Conclusion and Recommendations
Acknowledgement
References
14. Artificial Intelligence Issues in Healthcare
14.1 Introduction
14.2 Healthcare
14.3 AI in Healthcare
14.4 Elementary Issues
14.4.1 Privacy Issues
14.4.2 Security Issues
14.4.3 Integrity Issues
14.5 Data Collection
14.6 Data Analysis
14.7 Regulation Issues
14.8 Societal Issues
14.8.1 Human Surveillance Issues
14.8.2 Societal Issues
14.9 Unemployment Effects
14.10 Implementation Issues
14.10.1 Data Collection
14.10.2 Relevance
14.10.3 Sample Size
14.10.4 Discriminatory Biases
14.10.5 Emergence of New Trends
14.10.6 Diagnosis
14.10.7 Ethical Issues
14.11 Conclusion
References
15. Wearable Technologies in AI and Smart HealthCare
15.1 Introduction
15.2 Literature Survey
15.3 Popular Wearable Devices
15.4 Wearable Devices and ML
15.5 Facial Expression Recognition Deep Transfer Learning Using a Highly Imbalanced Dataset: A Case Study
15.5.1 Background and Objective
15.5.2 CNN Architecture and Training
15.5.3 Fine Tuning
15.5.4 Pool-Based Sampling Techniques
15.5.4.1 Greedy Sampling
15.5.5 Affect Net Database
15.5.6 Results
15.6 The Usage of Statistical Learning Methods on Wearable Devices and a Case Study: Activity Recognition on Smartwatches
15.6.1 Overview of Statistical Learning
15.6.2 Activity Recognition on Smartwatches Using Statistical Learning Method
15.6.3 Classification with Statistical Learning Methods
15.7 Challenges for ML Application on Wearable Devices
15.7.1 Data Availability and Reliability
15.7.2 Model Selection & Reliability
15.7.3 Storage Limitation
15.7.4 Deployment Alternatives
15.7.5 User Acceptance
15.7.6 Power Consumption
15.7.7 Communication
15.7.8 Security & Privacy
15.8 Conclusion & Future Scope
References
16. A Heterogeneous Medical-Imaging Social Security Analysis in Wireless Sensor Network
16.1 Introduction
16.2 Networks
16.2.1 Social Networking Site (Facebook)
16.3 Related Work
16.4 Fundamentals of Social Networks in Graph
16.4.1 Graph Theory in Facebook
16.4.2 Graph Theory in Twitter
16.4.3 Designing Transportation Networks
16.4.4 Communication Networks
16.4.5 WWW
16.4.6 Social Network
16.4.7 Brief Thought on Social Networks
16.4.8 Social and Economic Network
16.4.9 Data Network
16.4.10 All Friends
16.4.11 Complementary/Reciprocal Communication
16.4.12 Single Direction/One-way Communication
16.4.13 Looked after Maintained Relationships
16.5 Research Methods
16.6 Perspective of Social Network User Behavior
16.6.1 User Behavior Analysis
16.6.2 Behavior Characterization
16.6.3 Behavior Recognition
16.6.4 Behavior Prediction
16.7 Types of Attacks
16.8 Types of User Behavior
16.9 Result and Discussion
16.10 Conclusion
References
17. Wearable Technology: Concepts, Classification and Applications
17.1 Introduction
17.2 Fundamental Concept of Wearable Technology
17.2.1 Key Terms Used in Wearable Technology
17.2.1.1 User
17.2.1.2 Wearer
17.2.1.3 Wearable Devices
17.2.1.4 Processing Module
17.2.2 Fundamental Properties of Wearable Technology Devices
17.2.2.1 Longer Work Duration
17.2.2.2 Comfortable
17.2.2.3 Less Distraction
17.2.2.4 Good Performance
17.2.2.5 Good Connectivity
17.3 Classification of Wearable Technology Devices
17.3.1 Classification According to the Location of Installation
17.3.1.1 Body-Implantable Wearable Devices
17.3.1.2 Skin Patchable Wearable Devices
17.3.1.3 Textile-Integrated Wearable Devices
17.3.1.4 Accessory Type Wearable Devices
17.3.2 Classification According to the Application
17.3.2.1 Wearable Devices for Healthcare
17.3.2.2 Wearable Devices for Sports and Fitness
17.3.2.3 Wearable Devices in Workplace
17.3.2.4 Wearable Devices for Fashion
17.3.2.5 Consumer Electronics
17.4 Future Applications of Wearable Technology Devices
17.4.1 Safety and Security
17.4.2 Professional Upgradation
17.4.3 Travel and Exploration
17.4.4 People with Impairments
17.4.5 Production and Sales
17.4.6 Armed Forces
17.4.7 Space Exploration
17.5 Advantages and Disadvantages of Wearable Technology Devices
17.5.1 Advantages of Wearable Technology Devices
17.5.1.1 Increased Productivity
17.5.1.2 Increased Job Satisfaction
17.5.1.3 Tracking Location
17.5.1.4 View Text Messages
17.5.1.5 Hands Free and Portable
17.5.1.6 Monitor Fitness Levels
17.5.2 Disadvantages of Wearable Technology Devices
17.5.2.1 Short Battery Life
17.5.2.2 Repeated Removal and Charging Process
17.5.2.3 Approximate Measurement of Data
17.5.2.4 No Universal Device Design
17.5.2.5 Security Issues
17.5.2.6 Application Limitation
17.5.2.7 Distraction Issue
17.6 Proposed Solution for Selected Issues in Wearable Technology
17.6.1 Proposal 1 (Analysis)
17.6.2 Proposal 2 (Storage)
17.6.3 Proposal 3 (Security)
17.7 Conclusion
References
18. Analysis of Cardiac Dynamics and Assessment of Arrhythmia by Classifying Heartbeat Using Electrocardiogram
18.1 Introduction
18.1.1 Types of Arrhythmias
18.1.1.1 ECG (Electrocardiogram) and the Different Types of Arrhythmic Heartbeats
18.2 Implementation
18.3 Visualization and Deploying
18.3.1 Streamlit
18.3.2 Contents of the Dashboard
18.3.2.1 Dataset Visualization
18.3.3 About the Dataset
18.3.4 Information about the Model
18.3.5 Metrics from the Model
18.3.6 Menu Bar
18.3.7 Section - 1: Visualization of Datasets
18.3.8 Section -2: Selecting Dataset
18.3.9 Section - 3: Selecting Base Classifier
18.3.10 Section - 4: Selecting Deep Learning Classifier
18.3.11 Section - 5: Parameters
18.4 Conclusion
References
Index