About the Book
This book represents a unique and comprehensive resource for understanding the intersection of advanced artificial intelligence (AI) and neurology. By focusing on graph neural networks (GNNs), the book addresses a crucial gap in the current literature, providing valuable insights into the analysis and interpretation of complex brain networks and neurological data. Intended for a diverse audience, including clinicians, scientists, researchers, and students, it demystifies the complexities of GNNs and their applications in neurology. For clinicians and healthcare practitioners, the book illustrates how GNNs can enhance diagnostic accuracy, inform personalized treatment plans and predict disease progression. This leads to improved patient outcomes and a deeper understanding of neurological conditions such as Alzheimer's, Parkinson's, multiple sclerosis and epilepsy. Researchers will find the book particularly valuable as it delves into the methodologies and technical aspects of GNNs, showcasing their ability to handle diverse data sources including genetic, imaging and clinical information. By integrating these datasets, GNNs reveal hidden patterns and biomarkers, offering new avenues for research and potential therapeutic targets.
A Guide to Graph Neural Networks for Neurological Disorders addresses the challenge of missing data, a common issue in neurological research, and demonstrates how GNNs can manage and mitigate these gaps. For students, both undergraduate and postgraduate, the book serves as an educational tool, providing clear explanations and practical examples that make complex concepts accessible. It equips the next generation of neuroscientists and data scientists with the knowledge and skills needed to contribute to this rapidly evolving field. The book aims to provide a foundational understanding of GNNs, demonstrate their practical applications in neurology, and inspire further research and innovation. By bridging the gap between AI and medical practice, the book empowers readers to leverage cutting-edge technology in the quest to understand and treat neurological illnesses, ultimately enhancing the quality of care and advancing the field of neuroscience.
Table of Contents:
Understanding Graph Neural Networks: Foundations and Applications.- Neurological Disorders: An Overview of Classification and Diagnosis.- Graph Theory Fundamentals for Brain Network Modeling.- Graph Neural Network Architectures: A Comprehensive Review.- Genetic Influences on Brain Connectivity and Neurological Disorders.- Multi-modal Neuroimaging Data Fusion for GNNs.- Predictive Modeling of Neurological Disease Progression.- Diagnostic Applications of Graph Neural Networks.- Personalized Medicine Approaches in Neurology.- Ethical Considerations in GNN Research for Neurological Disorders.- Network Neuroscience: Bridging Gaps in Understanding Brain Connectivity.- GNNs for Studying Cognitive Disorders: Alzheimer's Disease and Dementia.- Parkinson's Disease: Insights from Graph Neural Network Analysis.- GNNs in Epilepsy Research: Seizure Prediction and Classification.- Neurodevelopmental Disorders and GNN Applications.- Brain Tumor Analysis using Graph Neural Networks.- Stroke and GNN-based Rehabilitation Strategies.- GNNs for Understanding Neurodegenerative Disorders.- Neuropsychiatric Disorders: Insights from Graph Neural Network Analysis.- Future Directions and Challenges in GNN Research for Neurology.
About the Author :
Md Mehedi Hassan is a dedicated Ph.D. researcher in Computer and Information Science at the University of South Australia, where his work lies at the forefront of AI-powered medical imaging and healthcare informatics. With a strong foundation in Computer Science and Engineering (B.Sc., M.Sc.), he specializes in developing robust, clinically explainable AI systems for automated disease diagnosis, particularly focusing on liver diseases through advanced CT image analysis. His research intersects medical image processing, radiomics, deep learning, and clinical decision support systems, with an emphasis on real-time, scalable, and interpretable diagnostic models. Through innovative computational frameworks--including 3D segmentation networks, hybrid CNN architectures, radiomic feature extraction, and multimodal learning--he aims to transform how medical conditions are detected, staged, and monitored. Mehedi's work addresses critical gaps in healthcare by targeting challenges such as the automation of radiology workflows, early and precise disease classification, and reducing the diagnostic burden on clinicians. His projects are deeply aligned with translational medicine goals, ensuring that the tools he develops are not just academically rigorous but also clinically deployable. In addition to his research, he contributes to the scientific community as a journal editor, reviewer, and AI educator. He actively collaborates with clinicians, industry experts, and interdisciplinary teams to push the boundaries of healthcare AI, ensuring that each innovation contributes meaningfully to improved patient outcomes, health system efficiency, and global digital health equity.
Anindya Nag obtained an M.Sc. in Computer Science and Engineering from Khulna University in Khulna, Bangladesh, and a B.Tech. in Computer Science and Engineering from Adamas University in Kolkata, India. He is currently a lecturer in the Department of Computer Science and Engineering at the Northern University of Business and Technology in Khulna, Khulna 9100, Bangladesh. His research focuses on health informatics, medical Internet of Things, neuroscience, and machine learning. He serves as a reviewer for numerous prestigious journals and international conferences. He has authored and co-authored about 47 publications, including journal articles, conference papers, and book chapters, and has co-edited nine books.
Herat Joshi is a visionary leader in the field of Healthcare Informatics, healthcare technology and data management, currently serving as the Vice Chair at IEEE Iowa Illinois Section. Holding a Ph.D. in Computer Science & Engineering, Herat has a distinguished track record of pioneering healthcare solutions that integrate AI, IoT, and high-performance computing to enhance clinical outcomes. His notable achievements include leading EHR implementations across multiple health systems, advancing interoperability, and receiving prestigious accolades such as the Outstanding Leadership Award at the Health 2.0 Conference. A recognized thought leader, Herat is a Fellow of the American College of Health Data Management (FACDM), Vice Chair of an American Medical Informatics Association (AMIA) Workgroup, Senior Member of IEEE, Vice Chair of IEEE Iowa-Illinois Section and a Gartner Ambassador. He also contributes as a reviewer and editor for leading scientific journals.
Dr Shariful Islam (FESC, PhD, MPH, MBBS) an accomplished Associate Professor at Deakin University's Institute for Physical Activity and Nutrition, boasts an impressive academic and professional portfolio focused on Global Health and Digital Health. With a diverse educational background, including a Ph.D. in Medical Research, an MPH, and an MBBS, his expertise spans the design and execution of large-scale epidemiological studies, clinical trials, and implementation research. Dr. Islam's leadership in the Global Burden of Disease Australia project and membership in esteemed organizations like the WHO-ITU Working Group on Artificial Intelligence for Health underscore his commitment to leveraging innovative information technologies for the prevention and management of diabetes and cardiovascular disease. Through a plethora of research grants, projects, honors, and awards, he continues to make significant contributions to the field, shaping the landscape of healthcare intervention strategies and digital health innovations globally.
