This book brings together peer-reviewed contributions that address a central challenge in contemporary healthcare: turning artificial intelligence from a promising research tool into systems that clinicians can trust and health institutions can actually deploy. This book is distinctive in treating robustness, interpretability, safety, and regulatory compliance not as afterthoughts but as design requirements, and in grounding its research in the realities of health systems in emerging economies rather than idealized settings.

This book approaches medical AI through the lens of an alliance between medicine and engineering, arguing that progress depends less on algorithmic novelty alone than on how well clinical needs, computational methods, and institutional constraints are brought together. What is new in this approach is its emphasis on deployability and accountability: several contributions move beyond single predictive models toward agentic and multi-agent architectures, examine the passage from computational autonomy to clinical authority, and confront the implementation-stage safety evidence gap that limits the real-world adoption of generative AI in clinical workflows.

The scope is deliberately broad. The chapters are organized into six thematic parts spanning health information systems, governance, and population health; machine learning and deep learning for medical imaging, diagnostics, and bioinformatics; generative AI, large language models, and trustworthy AI in clinical practice and education; decision-making, optimization, and agentic AI; connected health, the Internet of Medical Things, and biomedical signal processing; and biomedical devices, instrumentation, and materials. A recurring concern with technological sovereignty, edge deployment, privacy-preserving methods, and compliance with national legal frameworks runs across these parts.

This book is intended for researchers, engineers, clinicians, doctoral students, and policymakers working at the intersection of artificial intelligence, emerging technologies, and healthcare. It serves as a reference for those developing or evaluating clinical AI systems, as a source of methodological approaches and case studies for graduate courses and research groups, and as a guide for decision-makers assessing the readiness, safety, and governance of AI in real healthcare environments. By combining methodological depth with attention to deployment context, it offers both a snapshot of current advances and a practical foundation for future work in medical intelligence.