Emerging Technologies for Combatting Pandemics: AI, IoMT, and Analytics

Description

The COVID-19 pandemic has significantly affected the healthcare sector across the globe. Artificial Intelligence (AI) and the Internet of Medical Things (IoMT) play important roles when dealing with emerging challenges. These technologies are being applied to problems involving the early detection of infections, fast contact tracing, decision-making models, risk profiling of cohorts, and remote treatment. Applying these technologies runs against challenges including interoperability, lack of unified structure for eHealth, and data privacy and security. Emerging Technologies for Combatting Pandemics: AI, IoMT, and Analytics examines multiple models and solutions for various settings including individual, home, work, and society. The world’s healthcare systems are battling the novel coronavirus, and government authorities, scientists, medical practitioners, and medical services are striving hard to surmount these challenges. This book focuses on the design and implementation of AI-based approaches in the proposed COVID-19 solutions that are enabled and supported by IoMT, sensor networks, cloud and edge computing, robotics, and analytics. It covers technologies under the umbrella of AI that include data science, big data, machine learning (ML), semantic technologies, analytics, and cyber security. Highlights of the book include: Epidemic forecasting modelsSurveillance and tracking systemsIoMT and Internet of Healthcare Things-based integrated systems for COVID-19Social network analysis systemsRadiological image- based diagnosis systemsComputational intelligence methods This reference work is beneficial for interdisciplinary students, researchers, and healthcare and technology professionals who need to know how computational intelligence could be used for surveillance, control, prevention, prediction, diagnosis, and potential treatment of the disease. Cover Half Title Title Page Copyright Page Table of Contents Foreword Preface Acknowledgments About the Editors Contributors Chapter 1 Artificial Intelligence Leveraged Internet of Medical Things and Continuous Health Monitoring and Combating … 1.1 Introduction 1.2 Defining the Role of AI From an IoMT Perspective 1.3 Relevance of AI During a Pandemic 1.3.1 Predictive Analytics 1.3.2 Current Challenges 1.4 Proposed Technology Framework for IoMT Mobile Apps 1.4.1 Example EHealth Standards for EHRs 1.4.2 EHRs in Developed Countries 1.4.2.1 Benefits 1.4.2.2 Limitations 1.4.3 EHR Resources for System Development 1.5 Kubernetes Advantages in AI-Based IoMT 1.5.1 Kubernetes Example 1.5.2 Distinctive Advantages of Kubernetes in the Medical Field 1.5.2.1 Password Management 1.5.2.2 Automated Deployment 1.5.2.3 Packaging Applications 1.5.2.4 Storage Management and Orchestration 1.5.2.5 Load-Balancing Mechanism 1.6 Prescription and Medicine Administration Using AI 1.7 Cybersecurity Challenges in AI-Based IoMT 1.7.1 Zero Trust Architecture for IoMT Devices 1.7.2 Role-Based Authentication in AI-Based IoMT 1.7.3 Workflow of Authentication 1.8 Scalability of IoMT 1.8.1 Introducing Edge Computing 1.8.2 Components of Edge Computing 1.8.3 Factors to Consider Before the Adoption of Edge Computing 1.8.4 Challenges in Implementing Edge Computing 1.9 Continuous Monitoring for the Availability of IoMT 1.9.1 Designing IoMT Systems for High Availability 1.10 Practical Uses of AI-Based IoMT in Pandemics 1.11 Predictive Analytics for Combating Pandemics 1.12 Conclusions References Chapter 2 Assessing the Economic Impact of COVID-19 2.1 Introduction 2.2 Economically Affected Indian Sectors By Pandemics 2.3 Impact of Medical Crisis On Economic Conditions 2.4 Start-Up Businesses 2.5 Effects On Indian GDP (2017–2021) 2.6 Comparing Inflation and Employment Between India and the UK 2.7 Stock Market Crashes Due to Pandemic 2.7.1 Black Days of the Stock Market 2.7.2 Effects On Travel and Tourism Services 2.7.9 Action Must Be Taken By the Government 2.7.10 Actions People Should Take 2.8 Challenges After Pandemics 2.8.1 Inflation 2.8.2 Market Recovery 2.8.3 Rise in Debt 2.8.4 Trade Impact 2.8.5 Sustainable Development 2.8.6 Social Issues 2.9 Future Scope 2.9.1 Possible Scope of Data Analysis 2.9.2 Change in Economic Structure 2.9.3 Self-Sufficiency 2.9.3.1 Atmanirbhar Bharat Rozgar Yojana 2.9.4 Digital Changes After COVID-19 2.10 Conclusions References Chapter 3 Assessing the Economic Impact of COVID-19 On the Implications of the Internet of Things Adoption On Small and … 3.1 Introduction 3.2 Methodology 3.3 SMEs Business Sustainability 3.4 The IoT 3.5 Contemporary Issues: A Malaysian’s Scenario 3.5.1 SMEs Ecology 3.5.1.1 Digitalisation 3.5.1.2 Cyber Security 3.5.2 Establishing a High-Level Tasks Force to Promote IoT/IR4.0 3.6 Discussion 3.6.1 Increasing SMEs’ Productivity Effectiveness 3.6.2 Adoption Challenges 3.7 Limitations 3.8 Suggestions for Future Research 3.9 Conclusions References Chapter 4 Impact of COVID-19: Insights From Key Sectors of the Indian Economy 4.1 Introduction 4.2 Sectoral Implications of the Pandemic 4.2.1 Primary Sector 4.2.2 Secondary Sector 4.2.2.1 Mega Challenge 4.2.3 Service Sector 4.3 Becoming a Global Hub 4.4 Thriving Amid COVID-19: Positive Implications 4.5 Impact of the Second Wave 4.5.1 Agriculture 4.5.2 Manufacturing 4.5.3 Services 4.6 Overall Impact On GDP 4.7 Revival Strategies for Businesses 4.8 Policies to Combat COVID-19 4.9 COVID-19 and Other Economies 4.10 Future Scope and Limitations 4.11 Conclusions References Chapter 5 Future Scope of Artificial Intelligence in Healthcare for COVID-19 5.1 Introduction 5.2 Basic Terminology 5.3 COVID-19 Diagnosis and Detection Using Chest CT/X-Ray Scans 5.4 Contactless Healthcare Services With AI 5.5 Future Scope 5.5.1 ML and DL in Drug Design 5.5.2 Addressing Security and Privacy Issues With Blockchain 5.5 Future Challenges 5.6 Conclusions References Chapter 6 Patient Recovery and Tracing Repercussions for COVID-19 in Discharged Patients 6.1 Introduction: Patient Recovery and Tracing Repercussions of Coronavirus in Discharged Patients 6.2 Post-COVID Conditions: What Are They? 6.2.1 COVID-19’s Multiorgan Impact 6.2.1.1 COVID-19 Organ Damage Over Time (Multiorgan Dysfunction) 6.2.1.2 Clots in the Blood and Difficulties With the Blood Vessels 6.2.2.3 Problems With Mood Changes and Exhaustion 6.2.1.4 COVID-19 Has Several Long-Term Consequences That Are Still Unclear 6.2.1.5 Inability to Tolerate Physical Activity 6.2.1.6 Complications in the Lungs Or Respiratory System 6.2.1.7 Cardiac Complications 6.2.1.8 Injury to Cardiac Muscle 6.2.1.9 Complications of Renal Injury Or Failure 6.2.1.10 Diabetes 6.2.1.11 Brain Disease: Acute Necrotising Encephalopathy 6.2.1.12 Complications in the Vascular System 6.2.1.13 Complications With Psychiatric Illness 6.2.1.14 Depression and Anxiety 6.2.1.15 Insomnia 6.2.1.16 Complications in Other Organs 6.2.1.17 Adult MIS and MIS-C 6.2.2 COVID-19 Illness Or Hospitalisation Effects 6.2.3 Long-Term Effects of Coronavirus After Recovery, Post-COVID Complications 6.2.3.1 What Is Long COVID Syndrome Or Post-COVID Syndrome? 6.2.3.2 Who Are at Risk of Post-COVID Problems, as Well as Long-Term Coronavirus Effects? 6.3 Diagnosis of Post-COVID Syndrome Or Long COVID 6.4 What Measures Should You Take After You’ve Recovered From COVID? 6.5 Importance of Self-Observation After Recovering From COVID-19 6.6 Conclusions References Chapter 7 The Impact of COVID-19 On the Maritime Economy: A Study On Bangladesh 7.1 Introduction 7.2 Maritime Economy of Bangladesh 7.2.1 Economy and Maritime Economy 7.2.2 Seaborne Trade in Bangladesh 7.3 The Empirical Model 7.3.1 EDA 7.3.2 Linear Regression Analysis 7.3.2.1 Import Volume and COVID-19 7.3.2.2 Export Volume and COVID-19 7.3.2.3 Total Seaborne Trade Volume and COVID-19 7.4 Discussion 7.5 Limitations and Future Research 7.6 Conclusions References Chapter 8 Intelligent Optimization and Computational Learning Techniques for Mitigating Pandemics 8.1 Introduction 8.2 Review On IOCLT for Mitigating Pandemics 8.2.1 AI 8.2.2 Blockchain 8.2.3 Open Source Technologies 8.2.4 3D Printing 8.2.5 Telehealth Technologies 8.2.6 Comparative Analysis of IOCT 8.3 Materials and Methods 8.3.1 Deep Learning for Computational Learning Techniques 8.3.2 Categorization of Deep Learning Algorithm for Computational Intelligence 8.3.2.1 CNNs 8.3.2.2 LSTMs 8.3.2.3 RNNs 8.3.2.4 Generative Adversarial Networks 8.3.3 Optimization Techniques 8.3.3.1 Genetic Algorithm 8.3.3.2 Adam Algorithm 8.3.3.3 GD Algorithm 8.3.3.4 Adaptive Gradient Algorithm 8.3.4 Evaluation Metrics 8.3.5 IOCLT 8.4 Results and Discussion 8.4.1 Data Description 8.4.2 Data Analysis and Modeling 8.4.3 Results Analysis 8.5 Limitations and Future Scopes 8.6 Conclusions References Chapter 9 Various Deep Learning Methodologies for COVID-19 Diagnosis 9.1 Introduction: Background and AI in COVID-19 9.1.1 AI and COVID-19 9.2 Materials and Diagnosis Methodologies for COVID-19 9.2.1 DL 9.2.2 Prerequisites for a Search to Diagnose COVID-19 9.2.3 Extraction of Data 9.3 COVID-19 Detection Using AI-Based ML and DL for Medical Image Inception 9.3.1 Detection From Chest CT Images 9.3.2 Using CXR Images for Detection 9.3.3 Various Severity Levels of COVID-19 Classification Using DL and CXR Images 9.4 Vaccine and Drug Development Using ML and DL Techniques for the Treatment of COVID-19 9.4.1 Vaccine Development Using ML and DL 9.4.2 Drug Development 9.5 Limitations and Future Direction 9.5.1 Limitations 9.5.1.1 Regulations 9.5.1.2 Large-Scale Training Data Is Scarce and Unavailable 9.5.1.3 Data That Is Noisy, as Well as Fake Rumors 9.5.1.4 There Is a Gap Between Medicine and Computer Science 9.5.1.5 Data Security and Privacy 9.5.1.6 Early Detection of COVID-19 Through CXRs and CT Scans 9.5.1.7 Structurally Incorrect Data and Data That Is Not Structurally Correct (E.g., Image, Text, and Numerical Data) 9.5.1.8 Patients Are Screened and Triaged, Functional Therapy and Cures Are Sought, and Risk Assessments Are Conducted 9.5.2 Future Research Direction 9.5.2.1 Contactless Detection of Diseases During a Pandemic 9.5.2.2 Video Diagnostics and Consultations Via the Internet 9.5.2.3 Research in Biological Field 9.5.2.4 Vaccination and Drug Development 9.5.2.5 Fake Information Is Identified and Screened 9.5.5.6 Assessment and Evaluation of the Impact 9.5.2.7 COVID-19 Patient Tracking 9.5.2.8 AI Robots 9.5.2.9 More Research Work On Descriptive AI-Based DL Algorithms in the Future 9.5.2.10 What Is the Significant Aspect of COVID-19 Diagnosis and Treatment? 9.6 Conclusions References Chapter 10 Hybridization of Decision Tree Algorithm Using Sequencing Predictive Model for COVID-19 10.1 Introduction 10.2 COVID-19 Virus 10.3 Detection and Diagnosis of COVID-19 Infection 10.3.1 Molecular Detection 10.3.2 Medical Imagery Detection 10.3.3 Symptomatic Detection 10.4 The Role of ML 10.5 ML 10.5.1 Types of ML 10.5.2 Statistical Inference 10.5.3 Learning Techniques 10.5.4 Learning Problems 10.5.5 Hybrid Learning Problems 10.5.6 DL 10.5.7 Evolutionary Learning 10.6 DT Algorithm 10.6.1 Regression Tree Modeling 10.6.2 Classification Trees 10.6.3 BART 10.7 DT Hybridized Ensembles 10.8 DT Hybridized Ensemble Modeling 10.8.1 Single DT Ensemble 10.8.2 Multilevel DT Ensemble 10.8.3 Two-Level DT Ensemble 10.8.4 Hybrid DT Ensemble 10.9 HDT Disease Detection 10.10 Results and Discussion 10.10.1 Fitting Classification Trees 10.10.2 Fitting Regression Trees 10.10.3 Hybridization of Bag and Random Forest 10.10.4 Boosting 10.10.5 BART 10.11 Limitations and Future Work 10.12 Conclusions References Chapter 11 CoVICU: A Smart Model for Predicting the Intensive Care Unit Stay of COVID-19 Patients Using Machine Learning ... 11.1 Introduction 11.2 Related Works 11.3 Proposed System 11.3.1 Data Preprocessing 11.3.2 Classification 11.4 Implementation and Results 11.5 Conclusions 11.6 Future Work References Chapter 12 Long Short-Term Memory-Based Recurrent Neural Network Model for COVID-19 Prediction in Different States of India 12.1 Introduction 12.2 Related Work 12.3 Methodology 12.3.1 Dataset Description 12.3.2 Proposed Methodology 12.4 Experimental Results and Discussion 12.4.1 Prediction for Active Cases Per Day 12.4.2 Prediction for Confirmed Cases Per Day 12.4.3 Prediction for Cumulative Confirmed Cases 12.5 Conclusions 12.6 Limitation and Future Scope References Chapter 13 Dengue in the Presence of COVID-19: Evaluation of Tree-Based Classifiers Using Stratified K-Fold On Dengue Dataset 13.1 Introduction 13.2 Related Works 13.3 Proposed Model 13.3.1 Model Architecture 13.4 Data Collection 13.5 Train the Test Dataset 13.6 Results 13.7 Discussion 13.8 Conclusions References Index