Artificial Intelligence for Information Management: A Healthcare Perspective (Studies in Big Data, 88)

Description

This book discusses the advancements in artificial intelligent techniques used in the well-being of human healthcare. It details the techniques used in collection, storage and analysis of data and their usage in different healthcare solutions. It also discusses the techniques of predictive analysis in early diagnosis of critical diseases. The edited book is divided into four parts – part A discusses introduction to artificial intelligence and machine learning in healthcare; part B highlights different analytical techniques used in healthcare; part C provides various security and privacy mechanisms used in healthcare; and finally, part D exemplifies different tools used in visualization and data analytics. Preface Contents Editors and Contributors Introduction to Artificial Intelligence and Machine Learning in Healthcare Introduction to Healthcare Information Management and Machine Learning 1 Introduction 2 Health Information Management 3 Machine Learning in Health Care 4 What is Predictive Analytics in Health Care? 4.1 Forms of Healthcare Data Analytics 5 How Does Predictive Analytics Work in Health Care? 5.1 Regression Models [5] 5.2 Classification Models 6 Case Studies 6.1 SVM Model to Predict Diabetes [2] 6.2 Naive Bayes to Claim Fraud Diagnosis (Viaene, Derrig, & Dedene, 2004; (Peng, Kou, Sabatka, Matza, Chen, Khazanchi, & Shi, 2007) 6.3 Real-Time Applications of Neural Networks [10] 6.4 Real-Time Applications of Decision Trees 7 Conclusion References Introduction to Artificial Intelligence 1 Introduction 1.1 Types of AI (Based on Capabilities) 1.2 Types of AI (Based on Functionality) 1.3 Domains of AI 2 Subsets of Artificial Intelligence 2.1 Machine Learning 2.2 Challenges and limitation of ML 2.3 Deep Learning 3 Applications of Artificial Intelligence in Modern World 3.1 Agriculture 3.2 Business, Banking, and Finance 3.3 Education 3.4 Entertainment and Gaming 3.5 Health Care 3.6 Smart Cities and Transportation 3.7 Space Exploration 4 Artificial Intelligence for Advanced Medical Diagnosis 4.1 Database Management 4.2 Advanced Medical Devices 4.3 Drug Design 4.4 Digital Consultation 4.5 Genome Editing 5 Conclusion References Healthcare Data Analytics Using Artificial Intelligence 1 Introduction 1.1 Artificial Intelligence 1.2 Healthcare 1.3 Relationship Between Artificial Intelligence and Healthcare 2 Healthcare Data Collection and Storage System 2.1 Patient-Generated Health Data 2.2 Health Information System (HIS) 3 Medical Data Pre-processing 3.1 Data Cleaning 3.2 Data Integration 3.3 Data Transformation 3.4 Dimensionality Reduction 4 AI Algorithms for Healthcare 4.1 Artificial Neural Networks 4.2 Discriminant Analysis 4.3 K-Nearest Neighbor 4.4 Linear Regression 4.5 Logistic Regression 4.6 Naive Bayes 4.7 Random Forest 4.8 Support Vector Machine 5 AI Methodology for Medical and Medicinal Diagnosis 5.1 AI Applications in Medical Diagnostics 6 Selection and Extraction of Features Using AI 6.1 Feature Selection 6.2 Feature Extraction 7 Disease Diagnosis with AI 7.1 AI in Breast Cancer 7.2 Management of Alzheimer’s Disease with AI: 7.3 Management of Diabetic Complications Using AI 7.4 ANN in Diagnosis of Cardiovascular Diseases 8 Medical Image Processing with AI 8.1 Breast Imaging 8.2 Cardiovascular Imaging 8.3 Lung Imaging 8.4 Neurological Imaging 9 Patient Care and Treatment with AI 10 Conclusion References Data Collection and Processing in Health Care 1 Introduction to Data Collection 1.1 Importance of Data Collection 1.2 Challenges in Healthcare Data Collections 2 Types of Healthcare Data 2.1 Electronic Health Record (EHR) 2.2 Administrative Data 2.3 Claims Data 2.4 Patient/Disease Registries 2.5 Health Surveys 2.6 Clinical Trials Data 3 Introduction to Data Processing 3.1 Importance of Data Processing 3.2 Factors Affecting Data Processing 4 Conclusion References Healthcare Analytics Sensor Data Analytics for Health Care 1 Introduction 2 Identification and Sensor Technology 2.1 Blood Pressure Monitor 2.2 Smart Bone Plates 2.3 Degradable Sensor for Blood Flow Monitor 2.4 Continuous Glucose Monitoring 2.5 Medication Adherence Monitors 2.6 Surgery Recovery Monitors 3 Case Studies 3.1 Background 3.2 Analysis Overview 3.3 ECG Analysis 3.4 PPG 3.5 Results and Discussion 4 Conclusion References Social Media Analytics for Health Care 1 Introduction 2 Approaches for Analytics in SM for Health Care 3 Real-World Applications of SMA in Health Care: Case Study 3.1 Navicent Health SM Case Study: [25] 3.2 St. Louis Hospital Case Study: [26] 3.3 Health Awareness 3.4 Professional Education 3.5 SM Utilization by Consumers 3.6 Patient Care 3.7 Health Insurance Company Uses 3.8 Pharmaceutical Company Uses 4 Research Areas Related to Analytics in SM (SM) for Health Care 4.1 SM (SM) Websites and Ethical Challenges 4.2 Dangers of SM in Health Care 4.3 Guidelines Issued by Professional Organizations to Be Followed by HCPs When Using SM 5 Conclusion References Multi-modal Data-Driven Analytics for Health Care 1 Introduction 2 Multi-modal Data for Health Care 2.1 Textual Data 2.2 Image Data 2.3 Video Data 3 Multi-modal Analytics for Health Care 3.1 Textual Analytics 3.2 Image Analytics 3.3 Video Analytics 4 Multi-modal Framework for Healthcare Analytics 4.1 Data Collection 4.2 Pre-processing 4.3 Framework and Architecture 4.4 Experiment and Results 5 Conclusion References Security, Privacy and Visualization Security and Privacy Issues in Health Care 1 Introduction 2 Overview of Flow of Information in Healthcare Systems 2.1 The Role of Information Security in Different Health Enterprises 3 Challenges Identified in HealthCare Information Security and Privacy 3.1 Threats to Information Privacy and Security 3.2 Privacy Concern Among Patient’s Health Records 3.3 Healthcare Provider Viewpoint of Regulatory Compliance 3.4 Information Access Control in Healthcare System 3.5 Data Interoperability and Information Security in the Healthcare System 3.6 Information Integrity in Healthcare and Adverse Effects of Faulty Design 3.7 Financial Risk in Healthcare System 4 Security and Privacy Issues in Cloud Computing for Health Care and Its Solutions 4.1 Cloud Computing Infrastructure 4.2 Cloud Computing in Healthcare Sector 4.3 Possible Risks Acquiring in Cloud for Healthcare Applications 4.4 Privacy and Security Control for Healthcare Cloud 5 Case Studies 5.1 Case Study on Security and Privacy for Healthcare Providers by Deloitte 5.2 Case Study on Security and Privacy for Healthcare Providers by Cisco 6 Conclusion References Healthcare Data Visualization 1 Introduction 2 Importance of Healthcare Management 3 Critical Attributes of Healthcare Data 4 Common Data Sources in Health Care 4.1 Dashboard-Based Advanced Data Visualizations 4.2 Types of Healthcare Dashboards 4.3 Population Health Analytics 5 Exploratory Data Analysis in Medical Dataset 5.1 History of EDA 5.2 Need for EDA 6 Healthcare Data Visualization with Process Mining 6.1 Process Discovery 7 Event Log 7.1 Event and Attribute 7.2 Case, Trace and Event log 7.3 Structure of Event Log 8 Control Perspective of Hospital Process Using Various Modelling Notations 8.1 Transition Systems 8.2 Petri Net 8.3 Workflow Nets 8.4 Yet Another Workflow Language (YAWL) 8.5 Business Process Modelling Notation (BPMN) 8.6 Event-Driven Process Chains (EPC) 8.7 Causal Nets 9 Predictive Modelling Control Flow of a Process Using Fuzzy Miner 9.1 Hospital Process 9.2 Hospital Treatment Process 10 Open Challenges and Future Research Directions in Healthcare Data Visualization 11 Conclusion References Data Science Tools and Techniques for Healthcare Applications 1 Introduction 2 Machine Learning Techniques for Healthcare Applications 2.1 Clustering 2.2 Decision Trees 2.3 Random Forests 3 Cloud-Based Tools 3.1 Microsoft Azure 3.2 Google Colab 3.3 NVIDIA RAPIDS 4 Example of a Healthcare-Care Application Using Azure 4.1 Dataset and Scenario 4.2 Step-by-Step Analysis of Healthcare Data 4.3 Results and Discussion 4.4 Conclusion References Applications in Health Data Analytics Management of Dementia Through Self-help and Assistive Technologies 1 Introduction 2 Problems in Dementia 2.1 Problems Faced by the Dementia Patients 2.2 Problems Faced by the Caregivers 3 Management of Dementia 3.1 Self-help 3.2 Assistive Technologies 4 Consequences of Assistive Technology 4.1 Benefits 4.2 Limitations 5 Conclusion References Classification and Prediction of Leukemia Using Gene Expression Profile 1 Introduction 2 Research Methodology 2.1 Techniques 3 Theory and Experimentation 3.1 Proposed Solution 3.2 Architecture of RF 3.3 Dataset Generation 3.4 Methodology 3.5 Stage 1 3.6 Stage 2 3.7 Stage 3 3.8 Stage 4 4 Results 5 Conclusion References Estimation of Basic Reproduction Number and Herd Immunity for COVID-19 in India 1 Introduction 2 Data and Method 2.1 Data Collection 2.2 Data Design 2.3 Data Analysis 2.4 Tools Used 2.5 Forecasting Model 2.6 R0 Estimation Schemes 2.7 Herd Immunity Estimation 3 Results and Discussion 3.1 Histogram and Density Plots 3.2 Forecasting Model Parameters 3.3 Model Accuracy 3.4 Point Forecasting 3.5 R0 Estimation 3.6 HIT Estimation 4 Conclusion References Artificial Intelligence in Medicine: Diabetes as a Model 1 Introduction 1.1 Availability of Data 1.2 Scope and Need for AI in Clinical Care 1.3 Potential Applications of AI in Medical Care 1.4 Potential Concerns in Implementing AI in Medical Care 2 Application of Deep Neural Network Models in Non-communicable Diseases 2.1 Chronic Disease Prediction 2.2 Employing Machine Learning for Clustering of Cardiometabolic Risk Factors 2.3 Prediction of Different Aspects of Diabetes Using Machine Learning 3 Application of Machine Learning Techniques in Diabetes 3.1 Use of Deep Neural Network for Image Processing 3.2 Methods to Identify Diabetic Retinopathy 3.3 Concepts and Methods of AI in Diabetic Retinopathy (DR) 3.4 Study of Retinal Vessels Segmentation by Deep Learning Models 3.5 Critical Aspects in Application to Clinical Care 4 Studies in the Application of AI to Identify Diabetic Retinopathy 4.1 Employment of Retinal Fundus Camera to Identify Diabetic Retinopathy Using AI 4.2 Early Studies 4.3 Studies from Asia 4.4 Studies from Africa 4.5 Smart Phone Images to Identify Diabetic Retinopathy Using AI 4.6 AI to Predict Progression of DR 4.7 Health Economic and Safety Issues in AI Applications for DR Screening 4.8 Guidelines for Ocular Telehealth–Diabetic Retinopathy 5 Application of AI to Identify Conditions Other Than DR from Retinal Images 6 Current Status of AI in Ophthalmology 7 Outlook for the Future 8 Conclusion References Smart Healthcare: Using IoT and Machine Learning-Based Analytics 1 Introduction 2 Literature Survey 3 Design 4 Implementation and Results 5 Conclusion References