Bernards, Ann-KathrinPippow, AndreasLang, TobiasGillmann, ChristinaAurisano, JillianLaramee, Robert S.Nobre, Carolina2025-05-262025-05-262025978-3-03868-273-8https://doi.org/10.2312/eved.20251022https://diglib.eg.org/handle/10.2312/eved20251022Uncertainty is an inherent aspect of medical decision-making, influencing diagnostics, treatment planning, and prognosis. While uncertainty visualization can aid clinicians in interpreting probabilistic data and supporting shared decision-making with patients, traditional medical education often overlooks data interpretation and visualization training. This gap can hinder clinicians' ability to navigate and communicate complex medical data, potentially affecting patient care. To address this challenge, we developed a structured course that integrates new technologies, hybrid learning models, and practical visualization tools based on generative AI to teach uncertainty visualization effectively. By equipping clinicians with these skills, our approach aims to enhance evidence-based decision-making, improve communication of uncertain data, and ultimately foster better clinical outcomes.Attribution 4.0 International LicenseCCS Concepts: Social and professional topics → Adult education; Information technology education; Human-centered computing → Visualization design and evaluation methodsSocial and professional topics → Adult educationInformation technology educationHuman centered computing → Visualization design and evaluation methods10.2312/eved.202510229 pages