Search

Browse Subject Areas

For Authors

Submit a Proposal

Explainable and Responsible Artificial Intelligence in Healthcare

Edited by Rishabha Malviya and Sonali Sundram
Copyright: 2025   |   Expected Pub Date:2025/03/30
ISBN: 9781394302413  |  Hardcover  |  
374 pages

One Line Description
This book presents the fundamentals of explainable artificial intelligence (XAI) and responsible artificial intelligence (RAI), discussing their potential to enhance diagnosis, treatment, and patient outcomes.

Audience
The main audience for this book is targeted to scientists, healthcare professionals, biomedical industries, hospital management, engineers, and IT professionals interested in using AI to improve human health.

Description
This book explores the transformative potential of explainable artificial intelligence (XAI) and responsible AI (RAI) in healthcare. It provides a roadmap for navigating the complexities of healthcare-based AI while prioritizing patient safety and well-being. The content is structured to highlight topics on smart health systems, neuroscience, diagnostic imaging, and telehealth. The book emphasizes personalized treatment and improved patient outcomes in various medical fields. In addition, this book discusses osteoporosis risk, neurological treatment, and bone metastases. Each chapter provides a distinct viewpoint on how XAI and RAI approaches can help healthcare practitioners increase diagnosis accuracy, optimize treatment plans, and improve patient outcomes.
Readers will find the book:
•explains recent XAI and RAI breakthroughs in the healthcare system;
•discusses essential architecture with computational advances ranging from medical imaging to disease diagnosis;
•covers the latest developments and applications of XAI and RAI-based disease management applications;
•demonstrates how XAI and RAI can be utilized in healthcare and what problems the technology faces in the future.

Back to Top
Author / Editor Details
Rishabha Malviya, PhD, is an associate professor in the Department of Pharmacy, School of Medical and Allied Sciences, Galgotias University. He has authored more than 150 research/review papers for national/international journals of repute. He has been granted more than 10 patents from different countries while a further 40 patents have either been published or under evaluation. His areas of interest include formulation optimization, nanoformulation, targeted drug delivery, localized drug delivery, and characterization of natural polymers as pharmaceutical excipients.

Sonali Sundram, PhD and MPharm, completed her doctorate in pharmacy and is an assistant professor at Galgotias University, Greater Noida. Her areas of interest are neurodegeneration, clinical research, and artificial intelligence. She has edited four books.

Back to Top

Table of Contents
Foreword
Preface
1. Uncapping Explainable Artificial Intelligence–Centered Reinforcement Learning and Natural Language Processing in Smart Healthcare System
Bhupinder Singh, Rishabha Malviya, Christian Kaunert and Sathvik Belagodu Sridhar
1.1 Introduction
1.1.1 XAI in Healthcare: Relevance and Overview
1.1.2 Importance of Explainability in AI
1.1.3 Role of Reinforcement Learning and NLP in Smart Healthcare
1.1.4 Objectives of the Chapter
1.1.5 Structure of the Chapter
1.2 XAI-Based Reinforcement Learning in Smart Healthcare Systems
1.3 Natural Language Processing in Smart Healthcare Systems
1.3.1 Applications of NLP in Healthcare Industry
1.3.1.1 Deidentification of Clinical Records
1.3.1.2 Medical Text Mining
1.3.1.3 Extraction of Medical Information
1.3.1.4 Text Data Management
1.3.1.5 Health Information Graph
1.4 Incorporation of XAI-Based RL and NLP
1.5 Synergies Between XAI, RL, and NLP in Healthcare
1.5.1 Rule-Based Systems
1.5.2 Bayesian Networks
1.5.3 Decision Trees
1.5.4 Deep Learning Models
1.5.5 Enhanced Trust
1.5.6 Improved Understanding
1.5.7 Reduced Biases
1.5.8 Enhanced Adherence to Regulatory Standards
1.6 Patient Engagement and Care Management in Health Sector: XAI and NLP Methods
1.7 Conclusion and Future Scope—Implications for Healthcare Practice
References
2. Explainable and Responsible AI in Neuroscience: Cognitive Neurostimulation
Phool Chandra, Himanshu Sharma and Neetu Sachan
List of Abbreviations
2.1 Introduction
2.2 Foundations of Cognitive Neurostimulation
2.2.1 Neuroscience Basics
2.2.2 Introduction to Neuroscience
2.2.3 Cognitive Processes and Neural Networks
2.3 Cognitive Neurostimulation Techniques
2.3.1 Electrical Stimulation
2.3.2 Magnetic Stimulation
2.3.3 Other Modalities
2.4 Explainable AI in Cognitive Neurostimulation
2.4.1 Introduction to Explainable AI (XAI)
2.4.2 Importance of Explainability in Neurostimulation
2.4.3 Interpretable Models in Cognitive Neurostimulation
2.4.3.1 Model Architectures
2.4.3.2 Interpretability Techniques
2.5 Responsible Artificial Intelligence in Cognitive Neurostimulation
2.5.1 Ethical Considerations in Neurostimulation
2.5.2 Informed Consent
2.5.2.1 Privacy and Data Security
2.5.3 Risk Mitigation Strategies
2.5.4 Societal Implications of Cognitive Neurostimulation
2.6 Interdisciplinary Collaboration
2.6.1 Collaboration Between Neuroscientists and AI Experts
2.7 Case Studies in Explainable and Responsible AI in Cognitive Neurostimulation
2.8 Future Perspective
2.9 Conclusion
Acknowledgments
References
3. Diagnostic and Surgical Uses of Explainable AI (XAI)
Roja Rani Budha, Saba Wahid A.M. Khan, Tushar Lokhande, G.S.N. Koteswara Rao and Shams Aaghaz
List of Abbreviation
3.1 Introduction
3.2 Uncertainty of CNN Model Prediction by Leveraging XAI
3.3 Algorithms of XAI Techniques
3.3.1 Interpretable AI of LIME (Local Interpretable Model-Agnostic Explanations)
3.3.2 Enhanced Interpretability with SHAP (SHapley Additive exPlanations)
3.3.3 Enlightening Deep Learning Insights with CAM (Class Activation Mapping)
3.3.4 Grad-CAM (Gradient-Weighted Class Activation Mapping)
3.3.5 Counterfactual Explanations
3.3.6 Anchors
3.3.7 Influence Functions
3.4 Need for Using XAI
3.4.1 Applications
3.4.2 Application of Artificial Intelligence (AI) in Surgery
3.5 Scope of AI Surgery
3.5.1 AI/ML Applications Across Surgical Specialties
3.5.2 Intraoperative Surgical Decision-Making
3.5.3 Advancement of Minimally Invasive Surgery and Laparoscopic
3.5.3.1 Surgical Education
3.5.3.2 Postoperative Risk Assessment
3.5.4 Autonomous Robots and Artificial Intelligence
3.6 Limitations and Concerns
3.7 Conclusion and Future Implications for Surgeons and Future Perspective
References
4. Osteoporosis Risk Assessment and Individualized Feature Analysis Using Interpretable XAI and RAI Techniques
Shivam Rajput, Rishabha Malviya and Sathvik Belagodu Sridhar
4.1 Introduction
4.2 Responsible Artificial Intelligence (RAI)
4.3 Explainable Artificial Intelligence (XAI)
4.4 Key Principles of Explainable Artificial Intelligence (XAI)
4.4.1 Transitioning from a “Black Box” to a “(Translucent) Glass Box”
4.4.2 Explainability: Transparent or Post-Hoc
4.4.3 Cooperation Between AI and Humans
4.4.4 Scientific Explainable Artificial Intelligence (sXAI)
4.5 Radiomics, Machine Learning, and Deep Learning
4.6 Diagnosis of Osteoporosis
4.6.1 ML- and DL-Based Osteoporosis Diagnosis
4.6.2 The AI-Based Diagnosis
4.7 General Workflow of AI-Based BMD Classification in CT
4.8 Conclusion
References
5. Spinal Metastasis—Imaging Using XAI and RAI Techniques
Arti A. Bagada and Priya V. Patel
List of Abbreviations
5.1 Introduction
5.2 Spinal Metastasis: Need of Artificial Intelligence for Imaging
5.2.1 The Fiscal Impact of Spine Surgery: Overseeing Cascading Monetary Implications and Price Hikes
5.2.2 Diverseness in Medical Care Administration and Investigation
5.2.3 AI in Spine Surgery
5.2.4 Artificial Intelligence Applications in the Spine
5.2.5 Principal ML Approaches Used in Spine Care
5.2.5.1 Supervised Learning
5.2.5.2 Reinforcement Learning
5.2.5.3 Unsupervised Learning
5.2.6 Obtaining and Reconstructing Images: Accelerate Medical Imaging
5.3 Artificial Intelligence Imaging Using XAI and RAI Technique
5.3.1 XAI Technique
5.3.1.1 Switched from “Black Box” to “(Translucent) Glass Box”
5.3.1.2 Interpretation Types
5.3.1.3 Model Accuracy
5.3.1.4 Explanation Areas
5.3.2 RAI (Responsible Artificial Intelligence) Technique
5.3.2.1 RAI Principles
5.4 Challenges and Future Directions and Research Needs
5.5 Conclusion
References
6. Explainable Artificial Intelligence and Responsible Artificial Intelligence for Dentistry
Tamanna Rai, Rishabha Malviya and Sathvik Belagodu Sridhar
6.1 Introduction
6.2 The Scope of AI in Healthcare
6.3 Responsible Artificial Intelligence (AI) in Dentistry
6.3.1 Ethical Applications of AI in Dentistry
6.3.2 Guidelines from Dental Associations
6.4 Explainable Artificial Intelligence (XAI) in Dentistry
6.5 Application of AI in Dentistry
6.5.1 AI in Periodontitis
6.5.2 AI in Oral and Maxillofacial Surgery
6.5.3 AI in Orthodontics
6.5.4 AI in Operative Dentistry
6.5.5 AI in Prosthodontics
6.5.6 In Forensic Odontology
6.5.7 Artificial Intelligence in Endodontics
6.6 Benefits of AI in Dentistry
6.6.1 Improved Diagnosis
6.6.2 Predicted Data Analytics
6.6.3 Therapy Planning Assistance
6.6.4 Method Optimization
6.6.5 Participation and Training of Patients
6.6.6 Research and Development
6.6.7 Digital Dentistry
6.6.8 Prosthetics and Orthodontics
6.6.9 Economical
6.7 Challenges of AI in Dentistry
6.8 Conclusion
References
7. Explainable Artificial Intelligence Technique in Deep Learning–Based Medical Image Analysis
Babita Gupta, Rishabha Malviya, Sonali Sundram and Sathvik Belagodu Sridhar
7.1 Introduction
7.2 Deep Learning (DL) in the Analysis of Medical Images
7.3 Guidelines for Clinical XAI
7.4 Factors to Examine about the Feasibility and Efficacy of Using the Product in the Clinical Environment
7.5 Factors to Consider During the Evaluation
7.5.1 A Framework for XAI
7.5.2 Comparison Between Model-Based and Post-Hoc Explanation
7.5.2.1 Model-Based Explanation
7.5.2.2 Post-Hoc Explanation
7.5.3 Comparing Model-Specific and Model-Agnostic Explanations
7.5.3.1 Model-Specific Explanation
7.5.3.2 Model-Agnostic Explanation
7.6 XAI in Medical Image Analysis
7.6.1 Visual Explanation
7.6.2 Textual Explanation
7.6.3 Image Description
7.6.4 Captioning Images with Accompanying Visual Description
7.6.5 Testing Using Concept Activation Vectors (TCAVs)
7.7 Non-Visual XAI Techniques in Medical Imaging
7.8 Challenges and Future Directions
7.8.1 Understanding and Enhancing Explanation
7.8.2 Application of XAI in Medical Imaging
7.8.3 Data-Focused XAI
7.8.4 Fusion/Hybrid Imaging for XAI
7.9 Conclusion
References
8. XAI Technique in Deep Learning–Based Medical Image Analysis
Deepak Kumar, Sejal Porwal, Rishabha Malviya and Sathvik Belagodu Sridhar
8.1 Introduction
8.2 XAI Method in Field of Medical Imaging
8.2.1 Attribution-Based
8.2.2 Perturbation-Based Explanations
8.2.3 Backpropagation-Based Explanations
8.3 Application of XAI in Medical Imaging
8.3.1 Attribution-Based
8.3.1.1 Brain Image Analysis
8.3.1.2 Retinal Image Analysis
8.3.1.3 Breast Imaging Analysis
8.3.1.4 CT Imaging
8.3.1.5 X-Ray Imaging
8.3.1.6 Skin Imaging
8.3.2 Non-Attribution Based
8.3.2.1 Attention-Based
8.3.2.2 Concept Vectors
8.3.2.3 Expert Knowledge
8.3.2.4 Textual Justification
8.4 Conclusion
References
9. XAI-Enabled Telehealth
Pankaj Kumar Sharma and Neha Krishnarth
List of Abbreviations
9.1 Introduction
9.2 Significance of Telemedicine
9.3 Reasonable AI Consciousness (XAI)
9.3.1 Transparency
9.3.2 Trust
9.3.3 Accountability and Predisposition Alleviation
9.3.4 User Strengthening
9.3.5 Education and Learning
9.4 Simulated Intelligence in Telemedicine
9.5 Challenges in Executing XAI in Medical Services
9.6 Clinical Choice Help
9.7 Patient Observing
9.8 Medical Services Intercessions
9.9 The Requirement for Mindful Simulated Intelligence in Medical Care
9.10 Moral Contemplations in Artificial Intelligence Sending
9.10.1 Misdiagnosis and Treatment Mistakes
9.10.2 Data Inclination and Separation
9.10.3 Privacy and Security Concerns
9.10.4 Loss of Human Oversight
9.10.5 Regulatory and Legitimate Dangers
9.10.6 Ethical Quandaries
9.10.7 Algorithmic Straightforwardness and Responsibility
9.10.8 Financial Double-Dealing
9.11 AI (ML) in Artificial Intelligence
9.11.1 Types of AI
9.11.2 Algorithms
9.11.3 Deep Learning
9.11.4 Model Assessment and Improvement
9.11.5 Applications
9.12 Strategies for Interpretable AI Models
9.13 Layer-Wise Relevance Propagation
9.14 Local Interpretable Model-Agnostic Explanations
9.14.1 Subset-Based LIME (sp-LIME)
9.14.2 k-LIME
9.15 Partial Dependence Plots (PDPs)
9.15.1 SHAP (Shapley Additive Explanations)
9.15.2 Partial SHAP
9.15.3 Deep SHAP
9.16 Straight Forwardness in Artificial Intelligence Calculations
9.17 Difficulties of Reasonable Artificial Intelligence Logical
9.17.1 General Straightforwardness Versus Logic
9.17.2 Logic Precision Compromise Profound
9.18 Consolidating Computer-Based Intelligence in Medical Services Conveyance
9.18.1 Clinical Considerations
9.18.2 Healthcare Administration
9.18.3 Clinical Decision Support
9.18.4 Patient Monitoring
9.18.5 Healthcare Interventions
9.19 Functional Ramifications of XAI in Medical Services Reasonable
9.19.1 Worked on Quiet Results and Informed Navigation
9.19.2 Predisposition Discovery and Moderation
9.19.3 Decreased Clinical Blunders and Early Infection Location
9.19.4 Contextual Analyses and Experimental Proof
9.20 Available XAI Besides the Costs of Logic
9.21 Conversation
9.22 Conclusion
References
10. Intelligent Algorithm for Seizure Alignment Using EEG Clustering with Special Reference to Discrete Wavelet Transform Theory
Pankaj Kalita, Arup Sarmah, Chayanika Devi, Partha Pratim Kalita and Arnabjyoti Deva Sarma
10.1 Introduction
10.2 Different Intelligent/Computational Approaches for Seizure Classification
10.2.1 Machine Learning Techniques
10.2.1.1 Support Vector Machines (SVM)
10.2.1.2 Random Forests
10.2.1.3 Neural Networks
10.2.2 Feature Extraction Methods
10.2.2.1 Statistical Features
10.2.2.2 Frequency-Based Features
10.2.2.3 Wavelet Distortion
10.2.2.4 Nonlinear Features
10.2.3 Convolutional Neural Networks (CNNs)
10.3 The Architecture of EEG-Specific CNNs
10.3.1 Input Layer
10.3.2 Convolutional Layers
10.3.3 Pooling Layers
10.3.4 Fully Connected Layers
10.4 Training EEG-Specific CNNs
10.4.1 Data Preprocessing
10.4.2 Data Augmentation
10.4.3 Model Training
10.4.4 Validation and Hyperparameter Tuning
10.5 Significance of EEG CNNs
10.5.1 Automatic Feature Learning
10.5.2 Improved Accuracy
10.5.3 Generalization
10.5.4 Real-Time Applications
10.6 Challenges and Future Directions
10.6.1 Interpretability
10.6.2 Data Scarcity
10.6.3 Personalized Models
10.6.4 Multimodal Integration
10.7 Recurrent Neural Networks
10.7.1 Sequential Processing
10.7.2 Recurrent Connections
10.7.3 Long Short-Term Memory and Gated Recurrent Unit
10.8 Applications in EEG Analysis
10.8.1 Brain–Computer Interface (BCI)
10.8.2 Seizure Prediction and Detection
10.8.3 Cognitive State Classification
10.8.4 Brain Signal Denoising
10.9 Ensemble Methods
10.9.1 Application of Ensemble Methods to EEG Analysis
10.9.1.1 Bagging (Bootstrap Aggregating)
10.9.1.2 Boosting
10.9.1.3 Random Forests
10.9.1.4 Stacking
10.9.1.5 Voting Classifiers
10.10 Transfer Learning
10.10.1 Pre-Trained Models
10.10.2 Feature Extraction
10.10.3 Fine-Tuning
10.10.4 Domain Adaptation
10.10.5 Multi-Task Learning
10.10.6 Data Augmentation
10.10.7 Hybrid Approaches
10.11 Seizure EEG Clustering Using Discrete Wavelet Transform Algorithm
10.11.1 Pre-Processing of the EEG Data
10.11.2 Feature Extraction and Fusion
10.11.3 Classification
10.12 Present Findings
10.12.1 Seizure Prediction Using Computational Biology Approach
10.12.2 Feature Extraction
10.12.3 Quality Assessment Parameters
10.13 Conclusion
References
11. Analysis of Biomedical Data with Explainable (XAI) and Responsive AI (RAI)
Arjun K.R., Girish Kanavi K., Varshitha B.R., Mythreyi R., Sridhar Muthusami, Nandini G. and Kanthesh M. Basalingappa
Abbreviations
11.1 Introduction
11.2 Explainable Artificial Intelligence Modeling for Biomedical Data Analysis Using a Correlation-Based Feature Selection Method
11.3 Biomedical Data Analysis of Various Diseases: The Functions of XAI and RAI
11.3.1 Diagnosis and Analysis of Cardiovascular Diseases
11.3.2 Diagnosis and Analysis of Respiratory Diseases
11.4 A Comparative Study Between Manual Analysis and Analysis with XAI and RAI
11.5 Differentiation of AI and XAI/RAI Methods
11.5.1 Interpretation or Analysis
11.5.2 Transparency
11.6 Analyzing Data Using Traditional Methods Versus Using AI can Differ Significantly in Several Aspects
11.7 Advantages of AI
11.8 Comparison of AI’s Pros and Cons
11.9 Future Aspects
11.10 Conclusion
References
12. Classify Chronic Wounds: The Need of Explainable AI and Responsible AI
Saurav Sarkar, Soma Das, Ananya Chanda and Sayan Biswas
List of Abbreviation
12.1 Introduction
12.1.1 Background on Chronic Wounds
12.1.2 Importance of Accurate Classification
12.1.3 Role of AI in Wound Classification
12.2 Understanding Chronic Wounds
12.2.1 Definition and Types of Chronic Wounds
12.2.2 Causes and Complications
12.2.3 Current Methods of Wound Classification
12.3 The Rise of AI in Wound Classification
12.3.1 Overview of AI Technologies
12.3.2 Applications in Healthcare and Wound Management
12.3.3 Benefits and Challenges
12.4 Explainable AI: Unravelling the Black Box
12.4.1 Importance of Explainability in Healthcare AI
12.4.2 Techniques for Making AI Models Interpretable
12.4.2.1 SHapley Additive exPlanations
12.4.2.2 Local Interpretable Model-Agnostic Explanations
12.5 Responsible AI in Wound Classification
12.5.1 Ethical Considerations in AI Development
12.5.2 Addressing Bias and Fairness
12.5.3 Regulatory Frameworks and Guidelines
12.6 Case Studies and Applications
12.6.1 Real-World Example of AI in Wound Classification
12.6.2 Success Stories and Challenges Faced
12.7 Conclusion
12.7.1 Recap of Key Points
12.7.2 Future Prospects and Areas of Further Research
References
13. Bone Metastases: Explainable AI and Responsible AI
Avipsa Hazra, Gowrav Baradwaj, Sushma R., Sudipta Choudhury, Mythreyi R. and Kanthesh B.M.
Abbreviations
13.1 Introduction to Bone Metastases
13.2 Traditional Diagnostic and Therapeutic Method] for Bone Metastasis
13.2.1 Morphologic Imaging
13.2.1.1 Magnetic Resonance Imaging
13.2.2 Functional Imaging
13.2.2.1 Bone Scintigraphy
13.2.2.2 Positron Emission Tomography (PET)
13.2.2.3 Hybrid Images
13.2.3 Imaging in Treatment Planning of Radiotherapy
13.2.4 Biopsy of Bone Metastasis
13.2.5 Therapeutic Approaches to BM
13.2.5.1 Locoregional Treatments
13.2.5.2 Systemic Treatments (Classification has been Depicted via Figure 13.3)
13.3 AI Involvement in Diagnosis and Therapy of Bone Metastasis
13.4 Case Studies of Current AI Success in Bone Metastasis
13.5 Recent Advancements and Future Perspectives
13.6 Conclusion
References
Index

Back to Top



Description
Author/Editor Details
Table of Contents
Bookmark this page