Cognitive Intelligence and Big Data in Healthcare

Description

COGNITIVE INTELLIGENCE AND BIG DATA IN HEALTHCARE Applications of cognitive intelligence, advanced communication, and computational methods can drive healthcare research and enhance existing traditional methods in disease detection and management and prevention. As health is the foremost factor affecting the quality of human life, it is necessary to understand how the human body is functioning by processing health data obtained from various sources more quickly. Since an enormous amount of data is generated during data processing, a cognitive computing system could be applied to respond to queries, thereby assisting in customizing intelligent recommendations. This decision-making process could be improved by the deployment of cognitive computing techniques in healthcare, allowing for cutting-edge techniques to be integrated into healthcare to provide intelligent services in various healthcare applications. This book tackles all these issues and provides insight into these diversified topics in the healthcare sector and shows the range of recent innovative research, in addition to shedding light on future directions in this area. Audience The book will be very useful to a wide range of specialists including researchers, engineers, and postgraduate students in artificial intelligence, bioinformatics, information technology, as well as those in biomedicine. Cover Half-Title Page Title Page Copyright Page Contents Preface 1 Era of Computational Cognitive Techniques in Healthcare Systems 1.1 Introduction 1.2 Cognitive Science 1.3 Gap Between Classical Theory of Cognition 1.4 Cognitive Computing’s Evolution 1.5 The Coming Era of Cognitive Computing 1.6 Cognitive Computing Architecture 1.6.1 The Internet-of-Things and Cognitive Computing 1.6.2 Big Data and Cognitive Computing 1.6.3 Cognitive Computing and Cloud Computing 1.7 Enabling Technologies in Cognitive Computing 1.7.1 Reinforcement Learning and Cognitive Computing 1.7.2 Cognitive Computing with Deep Learning 1.7.2.1 Relational Technique and Perceptual Technique 1.7.2.2 Cognitive Computing and Image Understanding 1.8 Intelligent Systems in Healthcare 1.8.1 Intelligent Cognitive System in Healthcare (Why and How) 1.9 The Cognitive Challenge 1.9.1 Case Study: Patient Evacuation 1.9.2 Case Study: Anesthesiology 1.10 Conclusion References 2 Proposal of a Metaheuristic Algorithm of Cognitive Computing for Classification of Erythrocytes and Leukocytes in Healthcare Informatics 2.1 Introduction 2.2 Literature Concept 2.2.1 Cognitive Computing Concept 2.2.2 Neural Networks Concepts 2.2.3 Convolutional Neural Network 2.2.4 Deep Learning 2.3 Materials and Methods (Metaheuristic Algorithm Proposal) 2.4 Case Study and Discussion 2.5 Conclusions with Future Research Scopes References 3 Convergence of Big Data and Cognitive Computing in Healthcare 3.1 Introduction 3.2 Literature Review 3.2.1 Role of Cognitive Computing in Healthcare Applications 3.2.2 Research Problem Study by IBM 3.2.3 Purpose of Big Data in Healthcare 3.2.4 Convergence of Big Data with Cognitive Computing 3.2.4.1 Smart Healthcare 3.2.4.2 Big Data and Cognitive Computing-Based Smart Healthcare 3.3 Using Cognitive Computing and Big Data, a Smart Healthcare Framework for EEG Pathology Detection and Classification 3.3.1 EEG Pathology Diagnoses 3.3.2 Cognitive–Big Data-Based Smart Healthcare 3.3.3 System Architecture 3.3.4 Detection and Classification of Pathology 3.3.4.1 EEG Preprocessing and Illustration 3.3.4.2 CNN Model 3.3.5 Case Study 3.4 An Approach to Predict Heart Disease Using Integrated Big Data and Cognitive Computing in Cloud 3.4.1 Cloud Computing with Big Data in Healthcare 3.4.2 Heart Diseases 3.4.3 Healthcare Big Data Techniques 3.4.3.1 Rule Set Classifiers 3.4.3.2 Neuro Fuzzy Classifiers 3.4.3.3 Experimental Results 3.5 Conclusion References 4 IoT for Health, Safety, Well-Being, Inclusion, and Active Aging 4.1 Introduction 4.2 The Role of Technology in an Aging Society 4.3 Literature Survey 4.4 Health Monitoring 4.5 Nutrition Monitoring 4.6 Stress-Log: An IoT-Based Smart Monitoring System 4.7 Active Aging 4.8 Localization 4.9 Navigation Care 4.10 Fall Monitoring 4.10.1 Fall Detection System Architecture 4.10.2 Wearable Device 4.10.3 Wireless Communication Network 4.10.4 Smart IoT Gateway 4.10.5 Interoperability 4.10.6 Transformation of Data 4.10.7 Analyzer for Big Data 4.11 Conclusion References 5 Influence of Cognitive Computing in Healthcare Applications 5.1 Introduction 5.2 Bond Between Big Data and Cognitive Computing 5.3 Need for Cognitive Computing in Healthcare 5.4 Conceptual Model Linking Big Data and Cognitive Computing 5.4.1 Significance of Big Data 5.4.2 The Need for Cognitive Computing 5.4.3 The Association Between the Big Data and Cognitive Computing 5.4.4 The Advent of Cognition in Healthcare 5.5 IBM’s Watson and Cognitive Computing 5.5.1 Industrial Revolution with Watson 5.5.2 The IBM’s Cognitive Computing Endeavour in Healthcare The IBM Watson Health and Watson Health Cloud Usage of Cognitive Application to Augment the Electronic Medical Record 5.6 Future Directions 5.6.1 Retail 5.6.2 Research 5.6.3 Travel 5.6.4 Security and Threat Detection 5.6.5 Cognitive Training Tools 5.7 Conclusion References 6 An Overview of the Computational Cognitive from a Modern Perspective, Its Techniques and Application Potential in Healthcare Systems 6.1 Introduction 6.2 Literature Concept 6.2.1 Cognitive Computing Concept 6.2.1.1 Application Potential 6.2.2 Cognitive Computing in Healthcare 6.2.3 Deep Learning in Healthcare 6.2.4 Natural Language Processing in Healthcare 6.3 Discussion 6.4 Trends 6.5 Conclusions References 7 Protecting Patient Data with 2FAuthentication 7.1 Introduction 7.2 Literature Survey 7.3 Two-Factor Authentication 7.3.1 Novel Features of Two-Factor Authentication 7.3.2 Two-Factor Authentication Sorgen 7.3.3 Two-Factor Security Libraries 7.3.4 Challenges for Fitness Concern 7.4 Proposed Methodology 7.5 Medical Treatment and the Preservation of Records 7.5.1 Remote Method of Control 7.5.2 Enabling Healthcare System Technology 7.6 Conclusion References 8 Data Analytics for Healthcare Monitoring and Inferencing 8.1 An Overview of Healthcare Systems 8.2 Need of Healthcare Systems 8.3 Basic Principle of Healthcare Systems 8.4 Design and Recommended Structure of Healthcare Systems 8.4.1 Healthcare System Designs on the Basis of these Parameters 8.4.2 Details of Healthcare Organizational Structure 8.5 Various Challenges in Conventional Existing Healthcare System 8.6 Health Informatics 8.7 Information Technology Use in Healthcare Systems 8.8 Details of Various Information Technology Application Use in Healthcare Systems 8.9 Healthcare Information Technology Makes it Possible to Manage Patient Care and Exchange of Health Information Data, Details are Given Below 8.10 Barriers and Challenges to Implementation of Information Technology in Healthcare Systems 8.11 Healthcare Data Analytics 8.12 Healthcare as a Concept 8.13 Healthcare’s Key Technologies 8.14 The Present State of Smart Healthcare Application 8.15 Data Analytics with Machine Learning Use in Healthcare Systems 8.16 Benefit of Data Analytics in Healthcare System 8.17 Data Analysis and Visualization: COVID-19 Case Study in India 8.18 Bioinformatics Data Analytics 8.18.1 Notion of Bioinformatics 8.18.2 Bioinformatics Data Challenges 8.18.3 Sequence Analysis 8.18.4 Applications 8.18.5 COVID-19: A Bioinformatics Approach 8.19 Conclusion References 9 Features Optimistic Approach for the Detection of Parkinson’s Disease 9.1 Introduction 9.1.1 Parkinson’s Disease 9.1.2 Spect Scan 9.2 Literature Survey 9.3 Methods and Materials 9.3.1 Database Details 9.3.2 Procedure 9.3.3 Pre-Processing Done by PPMI 9.3.4 Image Analysis and Features Extraction 9.3.4.1 Image Slicing 9.3.4.2 Intensity Normalization 9.3.4.3 Image Segmentation 9.3.4.4 Shape Features Extraction 9.3.4.5 SBR Features 9.3.4.6 Feature Set Analysis 9.3.4.7 Surface Fitting 9.3.5 Classification Modeling 9.3.6 Feature Importance Estimation 9.3.6.1 Need for Analysis of Important Features 9.3.6.2 Random Forest 9.4 Results and Discussion 9.4.1 Segmentation 9.4.2 Shape Analysis 9.4.3 Classification 9.5 Conclusion References 10 Big Data Analytics in Healthcare 10.1 Introduction 10.2 Need for Big Data Analytics 10.3 Characteristics of Big Data 10.3.1 Volume 10.3.2 Velocity 10.3.3 Variety 10.3.4 Veracity 10.3.5 Value 10.3.6 Validity 10.3.7 Variability 10.3.8 Viscosity 10.3.9 Virality 10.3.10 Visualization 10.4 Big Data Analysis in Disease Treatment and Management 10.4.1 For Diabetes 10.4.2 For Heart Disease 10.4.3 For Chronic Disease 10.4.4 For Neurological Disease 10.4.5 For Personalized Medicine 10.5 Big Data: Databases and Platforms in Healthcare 10.6 Importance of Big Data in Healthcare 10.6.1 Evidence-Based Care 10.6.2 Reduced Cost of Healthcare 10.6.3 Increases the Participation of Patients in the Care Process 10.6.4 The Implication in Health Surveillance 10.6.5 Reduces Mortality Rate 10.6.6 Increase of Communication Between Patients and Healthcare Providers 10.6.7 Early Detection of Fraud and Security Threats in Health Management 10.6.8 Improvement in the Care Quality 10.7 Application of Big Data Analytics 10.7.1 Image Processing 10.7.2 Signal Processing 10.7.3 Genomics 10.7.4 Bioinformatics Applications 10.7.5 Clinical Informatics Application 10.8 Conclusion References 11 Case Studies of Cognitive Computing in Healthcare Systems: Disease Prediction, Genomics Studies, Medical Image Analysis, Patient Care, Medical Diagnostics, Drug Discovery 11.1 Introduction 11.1.1 Glaucoma 11.2 Literature Survey 11.3 Methodology 11.3.1 Sclera Segmentation 11.3.1.1 Fully Convolutional Network 11.3.2 Pupil/Iris Ratio 11.3.2.1 Canny Edge Detection 11.3.2.2 Mean Redness Level (MRL) MBP Mean Blue Mean S m S 11.3.2.3 Red Area Percentage (RAP) 11.4 Results and Discussion 11.4.1 Feature Extraction from Frontal Eye Images 11.4.1.1 Level of Mean Redness (MRL) 11.4.1.2 Percentage of Red Area (RAP) 11.4.2 Images of the Frontal Eye Pupil/Iris Ratio 11.4.2.1 Histogram Equalization 11.4.2.2 Morphological Reconstruction 11.4.2.3 Canny Edge Detection 11.4.2.4 Adaptive Thresholding 11.4.2.5 Circular Hough Transform 11.4.2.6 Classification 11.5 Conclusion and Future Work References 12 State of Mental Health and Social Media: Analysis, Challenges, Advancements 12.1 Introduction 12.2 Introduction to Big Data and Data Mining 12.3 Role of Sentimental Analysis in the Healthcare Sector 12.4 Case Study: Analyzing Mental Health 12.4.1 Problem Statement 12.4.2 Research Objectives 12.4.3 Methodology and Framework 12.4.3.1 Big 5 Personality Model 12.4.3.2 Openness to Explore 12.4.3.3 Methodology 12.4.3.4 Detailed Design Methodologies 12.4.3.5 Work Done Details as Required 12.5 Results and Discussion 12.6 Conclusion and Future References 13 Applications of Artificial Intelligence, Blockchain, and Internet-of-Things in Management of Chronic Disease 13.1 Introduction 13.2 Artificial Intelligence and Management of Chronic Diseases 13.3 Blockchain and Healthcare 13.3.1 Blockchain and Healthcare Management of Chronic Disease 13.4 Internet-of-Things and Healthcare Management of Chronic Disease 13.5 Conclusions References 14 Research Challenges and Future Directions in Applying Cognitive Computing in the Healthcare Domain 14.1 Introduction 14.2 Cognitive Computing Framework in Healthcare 14.3 Benefits of Using Cognitive Computing for Healthcare 14.4 Applications of Deploying Cognitive Assisted Technology in Healthcare Management 14.4.1 Using Cognitive Services for a Patient’s Healthcare Management 14.4.2 Using Cognitive Services for Healthcare Providers 14.5 Challenges in Using the Cognitive Assistive Technology in Healthcare Management 14.6 Future Directions for Extending Heathcare Services Using CATs 14.7 Addressing CAT Challenges in Healthcare as a General Framework 14.8 Conclusion References Index EULA