Artificial intelligence (AI) is increasingly being integrated into clinical practice across multiple medical specialties, supporting tasks such as diagnostic interpretation, risk prediction, treatment planning, and workflow optimization. While interest in AI continues to grow, clinicians and researchers often face challenges related to practical implementation, including data preparation, model validation, integration into clinical workflows, and evaluation of real-world performance.

This collection aims to present practical, step-by-step approaches to developing and implementing AI tools across diverse areas of medicine. Contributions will focus on reproducible methods, including data curation, model development, performance assessment, and strategies for integrating AI into clinical decision-making. By emphasizing real-world workflows and practical considerations, the collection seeks to bridge the gap between technical innovation and routine clinical use.

Urolithiasis will serve as a focused clinical use case to demonstrate the application of AI across the continuum of care, including imaging-based detection, procedural planning, outcome prediction, and longitudinal follow-up. As a condition that involves imaging, intervention, and ongoing management, urinary stone disease provides a practical framework to illustrate common challenges and solutions relevant to many specialties.

Through methodological demonstrations and real clinical examples, this collection will provide actionable insights to support clinicians, researchers, and healthcare systems in adopting AI tools safely, effectively, and responsibly.