Back to all papers

Vibe Coding in Radiology: Claude Code and ChatGPT Codex Leading to the Rise of the Radiologist-Developer.

April 16, 2026pubmed logopapers

Authors

Bera K,Bittencourt LK,Ramaiya N,Tirumani SH

Affiliations (4)

  • Department of Radiology, University Hospitals Cleveland Medical Center, Cleveland, OH. Electronic address: [email protected].
  • Professor and Vice Chair of Innovation, Department of Radiology, University Hospitals Cleveland Medical Center, Cleveland, OH.
  • Clinical Associate Professor, Department of Radiology, University Hospitals Cleveland Medical Center, Cleveland, OH.
  • Professor, Section Chief, Abdominal Imaging and Vice Chair of Research, Department of Radiology, University Hospitals Cleveland Medical Center, Cleveland, OH.

Abstract

Just as physicians including radiologists were getting familiar with large language models (LLMs) and finding ways to use them to streamline their workflow, the rapid rise of dedicated LLM based coding solutions has been an exciting development. These coding agents, Claude Code and ChatGPT Codex to name the most popular, had already been making waves for software developers with reports of a majority of the code now being written by agents. This led to coining the word 'vibe coding'. Radiologists, who are always at the forefront of technology are in prime position to make use of these technologies. While software development was traditionally gatekept due to the technical skill required, costs involved and the significant time commitment, with the advent of these tools, a radiologist now only needs an idea with the coding agent doing the rest from coding to implementation to successful deployment. In this opinion, we lay out the exciting prospect of a Radiologist-Developer and outline a few ways these coding agents can be used to develop quick solutions especially in advancing radiology education but also in daily clinical use and research. As with every AI tool, the fast pace of development needs to be effectively balanced with ethical principles, with thoughtful oversight and supervision to verify the accuracy and legitimacy of the output.

Topics

Journal Article

Ready to Sharpen Your Edge?

Subscribe to join 11k+ peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.