Can We Use Large Language Models for the Use of Contrast Media in Radiology?

There are many publications about large language models (LLM), the use of which has increased rapidly in the last year, including their use, possible benefits, and ethical concerns in the field of radiology ( 1 Bajaj S. Gandhi D. Nayar D. Potential applications and impact of ChatGPT in radiology. Acad Radiol. 2023; (Published online)https://doi.org/10.1016/j.acra.2023.08.039 Abstract Full Text Full Text PDF Scopus (0) Google Scholar ). Publications using ChatGPT created by OpenAI and Bard created by Google are becoming more frequent ( 2 Patil N.S. Huang R.S. van der Pol C.B. et al. Comparative performance of ChatGPT and bard in a text-based radiology knowledge assessment. Can Assoc Radiol J. 2023; 0: 1-7https://doi.org/10.1177/08465371231193716 Crossref Scopus (6) Google Scholar ). In these publications, topics such as patient appointments, structured reports, decision support systems in imaging, and decision support systems in radiology practice have been mentioned ( 3 Akinci D′Antonoli T. Stanzione A. Bluethgen C. et al. Large language models in radiology: fundamentals, applications, ethical considerations, risks, and future directions. Diagn Interv Radiol. 2023; https://doi.org/10.4274/dir.2023.232417 Crossref Google Scholar ). In this letter, we comment on the relationship between LLM and the use of contrast media, from two different points of view: clinical practice and academic study.