Handbook of Artificial Intelligence in Healthcare: Vol 2: Practicalities and Prospects (Intelligent Systems Reference Library, 212)

Artificial Intelligence (AI) has transformed many aspects of our daily activities. Health and well-being of humans stand as one of the key domains where AI has achieved significant progresses, saving time, costs, and potentially lives, as well as fostering economic resilience, particularly under the COVID-19 pandemic environments. This book is a sequel of the Handbook of Artificial Intelligence in Healthcare. The first volume of the Handbook is dedicated to present advances and applications of AI methodologies in several specific areas, i.e., signal, image, and video processing as well as information and data analytics. In this second volume of the Handbook, general practicality challenges and future prospects of AI methodologies pertaining to healthcare and related domains are presented in Part 1 and Part 2, respectively. It is envisaged that the selected studies will provide readers a general perspective on the issues, challenges, and opportunities in designing, developing, and implementing AI-based tools and solutions in the healthcare sector, bringing benefits to transform and advance health and well-being development of humans.. Preface Contents Part I Practicalities of AI Methodologies in Healthcare 1 Intelligent Paradigms for Diagnosis, Prediction and Control in Healthcare Applications 1.1 Introduction 1.2 Relevant References 1.3 Medical Decision-Making Based on Artificial Neural Networks 1.3.1 Skin Diseases Diagnosis 1.3.2 Hepatitis C Predictions 1.3.3 Coronary Heart Disease Prediction 1.4 Medical Image Analysis Using Artificial Neural Networks 1.5 Artificial Neural Networks Versus Naïve Bayesian Classifier 1.5.1 Hepatitis B Predictions 1.5.2 Stroke Risk Prediction 1.6 Prosthetic Hand Myoelectric-Based Modeling and Control Using Evolving Fuzzy Models and Fuzzy Control 1.6.1 Evolving Fuzzy Modeling Results 1.6.2 Fuzzy Control Results 1.7 Conclusions References 2 Artificial Intelligence in Healthcare Practice: How to Tackle the “Human” Challenge 2.1 Introduction 2.2 AI in Healthcare 2.3 A “third Wheel” Effect 2.3.1 “Confusion of the Tongues” 2.3.2 Decision Paralysis and Risk of Delay 2.3.3 Role Ambiguity 2.4 An Interface for AI 2.5 Identifying Personnel to Work with AI 2.6 Recommendations 2.7 Conclusion References 3 A Statistical Analysis Handbook for Validating Artificial Intelligence Techniques Applied in Healthcare 3.1 Introduction 3.2 Hypothesis Testing 3.2.1 Contingency Tables or Cross-Tabulation 3.2.2 Odds Ratio 3.2.3 Pearson’s χ2Test 3.3 Normality Tests 3.3.1 Kolmogorov–Smirnov Goodness of Fit (K-S) Test 3.3.2 Lilliefors Test 3.3.3 Shapiro Wilk W Test 3.4 Statistical Benchmarking Tests 3.4.1 T-test or Student’s T-test 3.4.2 T-test for Two Independent Groups of Observations 3.4.3 Equality of Variances: Levene’s Test 3.4.4 Equality of Variances: Bartlett’s Test 3.4.5 Mann–Whitney Test or Mann–Whitney Wilcoxon Test 3.4.6 One Way ANOVA 3.4.7 Tukey’s Honest Significant Difference Test 3.5 Conclusions References 4 Designing Meaningful, Beneficial and Positive Human Robot Interactions with Older Adults for Increased Wellbeing During Care Activities 4.1 Introduction 4.2 Social Robotics 4.2.1 The Nao Robot 4.2.2 The Need for Meaningful Activities and a Holistic Approach 4.3 Method: Learning from HCI Approaches for Exploring Social HRI 4.3.1 Situated Action 4.3.2 Participatory Design and Mutual Learning 4.3.3 Technology Probes 4.3.4 Motivational Goal Models and Technology Probes 4.3.5 Understanding Emotions 4.3.6 Iterative Visits in the Field and Data Collection 4.4 Four Case Studies Using the Nao in the Field 4.4.1 Preparing Considerations 4.4.2 Interaction stages 4.4.3 Overview 4.4.4 Case Study 1: Active Ageing Knitting Group 4.4.5 Case Study 2: Dementia Respite Care as Part of the Active Ageing Program 4.4.6 Case Study 3: Men’s Shed 4.4.7 Case Study 4: Residential Care 4.5 Discussion 4.5.1 Creating a Basis Through Humor and Turning Initial Negative Emotions into Positive 4.5.2 Increasing Wellbeing Through Activity and Application of Skills 4.5.3 Situated AI for Human Robot Interactions 4.5.4 Designing Social Interactions 4.6 Conclusions References 5 Wearable Accelerometers in Cancer Patients 5.1 Introduction 5.2 The Cancer Patient and Outcome Measures 5.2.1 Measuring Physical Activity 5.2.2 Measuring Physical Activity in the Cancer Patient 5.3 Harnessing Wearable Technology in Oncology 5.3.1 What Can Wearable Technology Be Used to Measure in Oncology, and Why Are These Parameters Relevant? 5.4 Accelerometers 5.4.1 Challenges with Wearable Accelerometer Data 5.5 Real-World Experience of Running a Digital Health Study 5.5.1 Device Considerations 5.5.2 Successes and Challenges of Running a Real-World Wearable Accelerometer Study 5.6 Clinical Studies in Cancer Patients Using Wearable Accelerometers 5.7 Ethical Issues with Wearable Accelerometer Data 5.7.1 Data Privacy and Security 5.7.2 Data Ownership 5.7.3 Insurance Premiums 5.8 Conclusion References 6 Online Application of a Home-Administered Parent-Mediated Program for Children with ASD 6.1 Introduction 6.2 Conceptual Framework and Aims of the Program 6.2.1 Behavioral Model of Communicative Failure 6.2.2 Structure of the Program 6.2.3 Technical Description and Parameters of the Program 6.2.4 Technical Specifications of the System 6.3 Pilot Testing of the Program—Qualitative Analysis 6.4 Conclusions References 7 Explainable AI, But Explainable to Whom? An Exploratory Case Study of xAI in Healthcare 7.1 Introduction 7.2 Related Work 7.2.1 Adoption and Use of AI in Healthcare 7.2.2 Drivers for xAI 7.2.3 Emergence of xAI 7.2.4 AI and xAI in the Fight Against the COVID-19 Pandemic 7.3 Method 7.3.1 Data Collection 7.3.2 Data Analysis 7.4 Case Setting 7.5 Findings 7.5.1 Development Team 7.5.2 Subject Matter Expert 7.5.3 Decision-Makers 7.5.4 Audience 7.6 Discussion and Concluding Remarks Appendix 1—Technical Aspects of LungX References 8 Pandemic Spreading in Italy and Regional Policies: An Approach with Self-organizing Maps 8.1 Introduction 8.2 Related Literature 8.3 Data and Research Questions 8.4 Methodology 8.5 Analysis 8.6 Analysis References 9 Biases in Assigning Emotions in Patients Due to Multicultural Issues 9.1 Introduction 9.2 The Non-Universality of Emotions 9.3 Emotions in Medical Contexts 9.4 Machine Learning, Data, Emotions, and Diagnosis 9.4.1 What is Affective Computing? 9.4.2 Data for Automatic Emotion Detection 9.4.3 Developing the Algorithm 9.5 Correcting Data Biases in Medical Diagnosis 9.6 Conclusions References Part II Prospects of AI Methodologies in Healthcare 10 Artificial Intelligence in Healthcare: Directions of Standardization 10.1 Introduction 10.2 Definition of Artificial Intelligence (AI) 10.3 History 10.4 AI Features and Development 10.5 Problems and Challenges 10.6 AI Systems in Healthcare 10.7 Quality and Safety of AI 10.8 Standardization of AI in Healthcare 10.9 Conclusion References 11 Development of Artificial Intelligence in Healthcare in Russia 11.1 Introduction 11.1.1 National Strategy for AI in Healthcare of the Russian Federation 11.1.2 The Work of Government Agencies and the Expert Community on the Development of AI in Healthcare 11.2 AI Regulations in Healthcare of the Russian Federation 11.2.1 Basic Principles of Regulations in Healthcare 11.2.2 Technical and Clinical Trials of Software as a Medical Device Created with the Application of AI Technologies 11.2.3 State Registration of Software as a Medical Device Created with the Application of AI Technologies 11.2.4 Post-registration Monitoring of Software as a Medicaldevice 11.3 Technical Regulations of Artificial Intelligence in the Russian Federation 11.4 Practical Experience of Artificial Intelligence in Healthcare of the Russian Federation 11.5 Chapter Summary References 12 Robotics in Healthcare 12.1 Introduction 12.2 Surgical Robots 12.2.1 Computer-Assisted Surgery 12.2.2 Mechanical Design and Control 12.2.3 Application 12.3 Rehabilitation Robots 12.3.1 Contact Therapy Robots 12.3.2 Assistive Robotics 12.3.3 Non-Contact Therapy Robots and Socially Assistive Robotics 12.4 Non-Medical Robots 12.5 Challenges 12.6 Conclusion References 13 Smart Healthcare, IoT and Machine Learning: A Complete Survey 13.1 Introduction 13.2 Architecture and Pipeline 13.2.1 Research Questions and Methodology Adopted 13.3 The General Picture of Levels 13.3.1 Architectures for the Local Integration Level—The Edge Level 13.3.2 Task Allocation and Resource Management—The Fog Level 13.3.3 Global Integration of Tasks and Resources—The Cloud Level 13.3.4 Algorithms and Data Analytics 13.3.5 Architectural Configurations 13.4 Data Pipeline and Data Storage 13.5 Conclusion References 14 Digital Business Models in the Healthcare Industry 14.1 Introduction 14.2 Role of the Healthcare Sector 14.3 Current Trends of Digitalization in Healthcare 14.4 Potential Benefits of Digital Business Models in the Healthcare Industry 14.4.1 Research Method 14.4.2 Industry-Dependent Determinants of Digitalization 14.4.3 Digital Technologies Along the Care Pathway 14.4.4 Challenges of Digitalization in Healthcare 14.4.5 Study Results 14.4.6 Interpretation 14.5 Conclusion 14.6 Outlook: The Role of AI in Healthcare References 15 Advances in XAI: Explanation Interfaces in Healthcare 15.1 Introduction 15.2 Related Work 15.3 Method 15.4 Findings 15.4.1 Prediction Tasks 15.4.2 Diagnosis Tasks 15.4.3 Automated Tasks 15.5 Conclusions References 16 Medical Knowledge Graphs in the Discovery of Future Research Collaborations 16.1 Introduction 16.2 Background Issues 16.2.1 Graph Measures and Indices 16.2.2 Graph-Based Text Representations 16.2.3 Graph-Based Feature Selection 16.2.4 Graph-Based Text Categorization 16.2.5 Graph-Based Link Prediction 16.3 The Proposed Framework 16.3.1 Graph-Based Text Representation 16.3.2 Graph-Based Feature Selection 16.3.3 Graph-Based Text Categorization 16.3.4 Graph-Based Link Prediction 16.4 Experiments 16.4.1 Cord-19 16.4.2 Experimental Setup 16.4.3 Evaluation 16.5 Conclusions References 17 Biometric System De-identification: Concepts, Applications, and Open Problems 17.1 Introduction 17.2 Literature Review and Classification of Biometric De-identification 17.3 New Types of Biometric De-identification 17.3.1 Sensor-Based Biometric De-identification 17.3.2 Emotion-Based De-identification 17.3.3 Social Behavioral Biometrics-Based De-identification 17.3.4 Psychological Traits-Based De-identification 17.3.5 Aesthetic-Based Biometric De-identification 17.4 Multi-Modal De-identification System 17.4.1 Definition and Motivation 17.4.2 Deep Learning Architecture 17.4.3 Multi-Modal De-identification Methodology 17.4.4 Potential Applications of Multi-Modal Biometric De-identification 17.5 Potential Applications in Risk Assessment and Public Health 17.6 Open Problems 17.6.1 Open Problems of Sensor-Based Biometric De-identification 17.6.2 Open Problems of Gait and Gesture De-identification 17.6.3 Open Problems of Emotion-Based De-identification 17.6.4 Open Problems of Social Behavioral De-identification 17.6.5 Open Problems of Psychological Traits-Based De-identification 17.6.6 Open Problems of Aesthetic-Based Biometric De-identification 17.6.7 Open Problems of Multi-Modal De-identification 17.7 Conclusion References This Book Is A Sequel Of The Handbook Of Artificial Intelligence In Healthcare. Artificial Intelligence (ai) Has Transformed Many Aspects Of Our Daily Activities. Health And Well-being Of Humans Stand As One Of The Key Domains Where Ai Has Achieved Significant Progresses, Saving Time, Costs, And Potentially Lives, As Well As Fostering Economic Resilience, Particularly Under The Covid-19 Pandemic Environments. The First Volume Of The Handbook Is Dedicated To Present Advances And Applications Of Ai Methodologies In Several Specific Areas, I.e., Signal, Image, And Video Processing As Well As Information And Data Analytics. In This Second Volume Of The Handbook, General Practicality Challenges And Future Prospects Of Ai Methodologies Pertaining To Healthcare And Related Domains Are Presented In Part 1 And Part 2, Respectively. It Is Envisaged That The Selected Studies Will Provide Readers A General Perspective On The Issues, Challenges, And Opportunities In Designing, Developing, And Implementing Ai-based Tools And Solutions In The Healthcare Sector, Bringing Benefits To Transform And Advance Health And Well-being Development Of Humans.