Personalized Medicine Meets Artificial Intelligence: Beyond “Hype”, Towards the Metaverse

✍ Scribed by Alfredo Cesario (editor), Marika D'Oria (editor), Charles Auffray (editor), Giovanni Scambia (editor)

• Publisher: Springer
• Year: 2023
• Tongue: English
• Leaves: 275
• Category: Library

✦ Synopsis

The book provides a multidisciplinary outlook on using Artificial Intelligence (AI)-based solutions in the field of Personalized Medicine and its transitioning towards Personalized Digital Medicine.

The first section integrates different perspectives on AI-based solutions and highlights their potential in biomedical research and patient care. In the second section, the authors present several real-world examples that demonstrate the successful use of AI technologies in various contexts. These include examples from digital therapeutics, in silico clinical trials, and network pharmacology. In the final section of the book, the authors explore future directions in AI-enhanced biomedical technologies and discuss emerging technologies such as blockchain, quantum computing and the “metaverse”. The book includes discussions on the ethical, regulatory, and social implications for an AI-based personalized medicine.

The integration of heterogeneous disciplines brings together multiple stakeholders and decision makers involved in the personalization of care. Clinicians, students, and researchers from academia and the industry can benefit from this book, since it provides foundational knowledge to drive advances in personalized biomedical research and health care.

✦ Table of Contents

Introduction
Contents
Part I: State of the Art
1: Personalized Medicine Through Artificial Intelligence: A Public Health Perspective
1.1 The International Landscape of Artificial Intelligence for Healthcare Purposes
1.1.1 Artificial Intelligence Systems Suitable for Public Health Applications
1.1.2 Improving Healthcare Services Using Artificial Intelligence
1.2 Current Limitations of AI Applications in Public Health
References
2: Artificial Intelligence and Digital Health: An International Biomedical Perspective
2.1 Introduction
2.2 The Role of Artificial Intelligence in Digital Health
2.2.1 Prognostic Outcomes and Risk Prediction
2.2.2 Clinical Diagnostics Personalization
2.2.3 Therapy Development or Improvement
2.2.4 Deep Data Collection and Analysis
2.3 Digital Health for Personalized Patient Compliance and Flow Management
2.3.1 Monitoring Patients´ Symptoms and Adherence to Therapy
2.3.2 Digitalization of Clinical Pathways
2.4 Investments in the AI and DH Environment
2.5 Further Considerations
References
3: GDPR as a First Step Towards Free Flow of Data in Europe
3.1 The GDPR Revolution
3.2 The DPO According to the GDPR and the Guidelines of the European Data Protection Board
3.3 Security Measures and Privacy´´ Crimes 3.4Sensitive´´ Personal Data
3.5 Data Monetization´´ 3.6 The Way Forward References 4: Digital Therapeutics: Scientific, Technological, and Regulatory Challenges 4.1 Introduction 4.2 Digital Health 4.3 Digital Medicine 4.4 Digital Therapeutics 4.4.1 Definition 4.4.2 Digital Forms 4.4.3 Mode of Action 4.4.4 Composition 4.4.5 Regulatory Classification 4.4.6 Research and Development (RandD) 4.4.6.1 Research and Discovery 4.4.6.2 Pilot Development 4.4.6.3 Full Development 4.4.6.4 Post-Marketing Surveillance 4.4.7 Digital Therapeutics and Drug Therapy 4.4.8 Challenges for Adoption in Medical Practice 4.4.8.1 Clinical Evidence 4.4.8.2 Technology Assessment 4.4.8.3 Reimbursement 4.4.8.4 Data Safety and Privacy 4.4.8.5 Information e Education 4.5 Conclusions References 5: Intelligence-Based Medicine: The Academic Perspective and Deep Humanism 5.1 Introduction 5.2 Understanding the Methodological Pathway 5.3 Current Deep Medicine Interventions 5.3.1 Patient Profiling and Deep Humanism 5.4 Safety in Research and Development 5.5 Outlook for an Intelligence-Based Medicine References Part II: Consolidated Evidence 6: The Role of Big Data and Artificial Intelligence in Clinical Research and Digital Therapeutics 6.1 Introduction 6.2 Big Data and RWD Collection 6.2.1 Attributes of RWD 6.2.2 Collecting RWD 6.2.3 Healthentia for RWD Collection and Management 6.3 AI in Clinical Research and Digital Therapeutics 6.3.1 AI for Patients´ Selection and Adherence 6.3.2 Discovering Digital Composite Biomarkers and Phenotypes 6.3.3 Virtual Coaching for DTx 6.3.4 Clinical Pathways 6.4 Patient Engagement 6.5 Conclusions References 7: Systems Pharmacology for Immunotherapy: A Network Analysis of Signaling Pathways in Multiple Sclerosis for Combination Ther... 7.1 Introduction 7.2 Systems Pharmacology for Combination Therapy in Multiple Sclerosis 7.2.1 Modeling Signaling Pathways from Ex Vivo Proteomic Assays in MS 7.3 Network Topology-Based Prediction of Targeted Combination Therapy 7.4 Lessons from Network Analysis to Understand MS 7.5 A System Pharmacology Approach for Designing Combination Therapies Beyond MS References 8: Approaches to Generating Virtual Patient Cohorts with Applications in Oncology 8.1 Introduction 8.2 Using Population Pharmacokinetic Models to Generate Patients 8.3 Establishing Theoretical Bounds from Experimental Measurements 8.4 Quantitative Systems Pharmacology Approaches 8.5 Discussion References 9: Artificial Intelligence and Deep Phenotyping in COVID-19 9.1 SARS-CoV-2 and COVID-19 9.2 Overview of Deep Phenotyping in COVID-19 9.3 Deep Phenotyping of COVID-19 Variants 9.3.1 Epitope: Antibody Background 9.3.2 Spike Protein and Variants 9.3.3 Spike-Antibody Interaction 9.4 Overview of AI for COVID-19 9.4.1 AI in Prediction and Tracking 9.4.2 AI in Contact Tracing and Population Control 9.4.3 AI in Monitoring of COVID-19 Cases 9.4.4 AI in Early Diagnosis 9.4.5 AI in Reducing the Burden for Healthcare Staff and Medical Practitioners 9.4.6 AI in Curbing the Spread of Misinformation 9.4.7 AI in COVID-19 Variants 9.5 Future Directions References 10: Multilevel Modelling with AI: The Synergy-COPD Endeavour 10.1 Multisource Predictive Modelling for Enhanced Clinical Risk Assessment 10.2 Computational Modelling for Enhanced Understanding and Management of COPD and Its Co-morbidities: The Synergy-COPD Project 10.3 Multilevel Data Integration and Advanced AI/ML: Beyond Synergy-COPD 10.4 From Systems Medicine to Integrated Care 10.5 Deployment and Adoption Strategies 10.6 Conclusions References 11: Artificial Intelligence and Radiotherapy: Impact on Radiotherapy Workflow and Clinical Example 11.1 Introduction 11.2 Impact of AI and Automation in External Beam Radiotherapy Workflow 11.2.1 First Patient Consultation 11.2.2 Delineation 11.2.3 Treatment Planning 11.2.4 Setup 11.2.5 Treatment Delivery 11.2.6 End of Treatment 11.3 Impact of AI and Automation in Interventional Radiotherapy (IRT) Workflow 11.3.1 First Patient Consultation 11.3.2 Implant 11.3.3 Delineation 11.3.4 Treatment Planning 11.3.5 Treatment Session Delivery 11.3.6 End of Treatment 11.4 Large Databases 11.5 Conclusion References 12: Artificial Intelligence in Surgery 12.1 Introduction 12.2 Surgical Data and Fundamentals AI Concepts 12.3 Potential Application of AI in Surgery 12.3.1 Perioperative Applications 12.3.2 Intraoperative Applications 12.4 The Future Ahead References Part III: Emerging and Future Technologies 13: How Start-ups and Established Organisations Together Can Drive Meaningful Healthcare Innovation in Personalised Medicine a... 13.1 Landscape: Why Are Partnerships Between Start-ups and Established Organisations Relevant for Personalised Medicine and AI? 13.1.1 Problem 13.1.2 From Inside Out to Outside in: Applying AI 13.2 The Power of Design and Open Innovation 13.2.1 A Closer Look: The Need for Meaningful Collaboration 13.2.2 The Advantages 13.2.3 The Challenges 13.2.4 Beyond the Challenges: Understanding the Risks 13.3 A Decision Perspective Framework 13.3.1 Framework for Artificial Intelligence Clinical Product Development 13.3.1.1 Phases 13.3.1.2 Domains 13.4 Discussion and Conclusion References Untitled 14: Artificial Intelligence Augmented Medtech: Toward Personalized Patient Treatment 14.1 A Definition of Personalized Medtech 14.2 A Definition of Artificial Intelligence for Medtech Applications 14.3 Misconceptions of Artificial Intelligence 14.4 Toward a Regulatory Framework for AI in MedTech 14.5 AI Learning Schemes and Regulatory Compliance 14.5.1 AI Learning Schemes 14.5.1.1 Locked Learning Scheme 14.5.1.2 Discrete Learning Scheme 14.5.1.3 Continuous Learning Scheme 14.5.2 Regulatory Compliance 14.6 AI Technology Overview 14.6.1 Reasoning 14.6.2 Learning 14.6.3 Robotics 14.7 Successful AI Applications 14.8 Examples of AI Usage in Medical Technology 14.8.1 Optimization of Patient´s Medication Administration 14.8.2 Improvement of Visual Analysis 14.8.3 Assisted Diagnostics by AI 14.8.4 Automated Insulin Delivery System 14.9 Data Sources and Data Quality 14.9.1 Data Sources 14.9.2 Data Quality 14.9.3 Sensitivity of Data 14.9.4 Digression Data Sources 14.10 Ethics, Acceptance, and Liability 14.10.1 Ethics 14.10.1.1 Ethics Guidelines & Recommendations 14.10.2 Acceptance 14.10.3 Liability 14.11 Conclusion References 15: Quantum Computing: Promises and Challenges 15.1 Introduction 15.2 Quantum Computing: Basic Concepts 15.3 Quantum Computing Models and Algorithms 15.3.1 Computing Models Examples: Quantum Gate Array and Quantum Annealer 15.3.2 Algorithms Implemented on QC: Some Examples 15.4 Healthcare Use Cases 15.4.1 Genome Analysis 15.4.2 Machine Learning for Precision Medicine 15.4.3 Natural Language Processing for Medical Reports 15.5 Discussion References 16: Metaverse Means Better: How the Metaverse Continuum Is Evolving Healthcare to the Next Level 16.1 Introduction 16.2 Enter the Metaverse Continuum 16.3 It Is Time to Pause and Reimagine Healthcare 16.3.1 WebMe: What It Means 16.3.2 Programmable World: What It Means 16.3.3 The Unreal: What It Means 16.3.4 Computing the Impossible: What It Means 16.4 It Is Happening Already 16.5 Immersive Training 16.6 Patient Education 16.7 Digital Therapeutics and Diagnosis 16.8 Augmented Health 16.9 Care Plan and Delivery 16.10 Introducing Meta-Care 16.11 How Does One Neutralize Potential Healthcare-Related Anxiety? 16.12 Meta-Care Is Key, But It Is Not Enough 16.13 It Takes an Ecosystem: You Can´t Do It Alone References 17: Patients´ Reactions to Anthropomorphic Technologies in Healthcare. The Predictor Roles of Perceived Anthropomorphism and H... 17.1 Introduction 17.2 Overview of the Study 17.2.1 Anthropomorphic Technologies 17.2.2 Human-Like Interaction Level 17.3 Methodology 17.4 Results 17.5 Discussion and Conclusion References 18: Some Ethical and Educational Perspectives on Using Artificial Intelligence in Personalized Medicine and Healthcare 18.1 Introduction 18.2Are Algorithms Racist?,´´ Is LaMDA Sentient?,´´ and Other Wonder-Full Questions 18.3 Behavior, Identity, and the Metaverse 18.4 Health, Salvation, and Dignity: Are we Ready for Deep Humanism? References 19: TheHuman Factor´´ Beyond Humans: Perspectives for an AI-Guided Personalized Medicine
19.1 Big Data, Machine Learning, and Complex Adaptive Systems
19.2 Machines, Artificial Intelligence, and Human Augmentation
19.3 Some Differentiating Challenges in Human-Machine Interaction
19.4 Modern and Future Directions
References
Conclusion