AI in Radiology: Hype, Reality, and What Comes Next | with Dr. Woojin Kim

What happens when large language models (LLMs) move from casual conversations into clinical practice? In this episode of Imaging Informatics Unplugged, Dr. Woojin Kim joins Jason Nagels to explore the hype, reality, and future of AI in radiology.Dr. Kim is the Chief Strategy Officer and CMIO at HOPPR, Chief Medical Officer at the ACR Data Science Institute, and a musculoskeletal radiologist at the Palo Alto VA Medical Center. He’s also a proven entrepreneur, co-founding Montage Healthcare Solutions and Equium Intelligence, both acquired by major players in imaging AI.We cover: How Dr. Kim consumes 4–6 hours of AI research daily using tools like Notebook LM and Recall  The underestimated risk of silent degradation in clinical AI models and why continuous monitoring matters  The difference between prompt engineering vs. context engineering for PACS and RIS integration  Opportunities and pitfalls of structured reporting with LLMs  Critical discussions on bias, fairness, and synthetic data in radiology AI  Where Dr. Kim sees the field heading: multimodal models, agentic AI, and the evolving role of the radiologist If you’ve ever wondered how much we can really trust AI in clinical imaging, this episode offers an unfiltered look at the challenges and opportunities shaping the next decade.🔔 Don’t forget to like, subscribe, and hit the bell to stay updated on future episodes exploring the intersection of imaging, informatics, and AI.👉 Learn more at:🌐 https://www.nagelsconsulting.com📘 https://learn.nagelsconsulting.com