Treffer: Letter to the Editor: The role of prompt engineering and referral completeness in evaluating GPT-4 for MRI protocols.
Title:
Letter to the Editor: The role of prompt engineering and referral completeness in evaluating GPT-4 for MRI protocols.
Authors:
Büyüktoka RE; Department of Radiology, Izmir Foça State Hospital, Izmir, Türkiye. rasiterenbuyuktoka@hotmail.com., Salbas A; Department of Radiology, Izmir Ataturk Education and Research Hospital, Izmir, Türkiye.
Source:
European radiology [Eur Radiol] 2025 Nov 14. Date of Electronic Publication: 2025 Nov 14.
Publication Model:
Ahead of Print
Publication Type:
Letter
Language:
English
Journal Info:
Publisher: Springer International Country of Publication: Germany NLM ID: 9114774 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1432-1084 (Electronic) Linking ISSN: 09387994 NLM ISO Abbreviation: Eur Radiol Subsets: MEDLINE
Imprint Name(s):
Original Publication: Berlin : Springer International, c1991-
References:
Terzis R, Kaya K, Schömig T et al (2025) GPT-4 for automated sequence-level determination of MRI protocols based on radiology request forms from clinical routine. Eur Radiol. https://doi.org/10.1007/s00330-025-11888-4.
Akinci D’Antonoli T, Stanzione A, Bluethgen C et al (2024) Large language models in radiology: fundamentals, applications, ethical considerations, risks, and future directions. Diagn Interv Radiol 30:80–90. https://doi.org/10.4274/dir.2023.232417. (PMID: 10.4274/dir.2023.2324173778967610916534)
Meskó B (2023) Prompt engineering as an important emerging skill for medical professionals: tutorial. J Med Internet Res 25:e50638. https://doi.org/10.2196/50638. (PMID: 10.2196/506383779243410585440)
Nguyen D, MacKenzie A, Kim YH (2024) Encouragement vs. liability: how prompt engineering influences ChatGPT-4’s radiology exam performance. Clin Imaging 115:110276. https://doi.org/10.1016/j.clinimag.2024.110276. (PMID: 10.1016/j.clinimag.2024.11027639288636)
Parillo M, Vaccarino F, Vertulli D et al (2024) Assessment of reason for exam imaging reporting and data system (RI-RADS) in inpatient diagnostic imaging referrals. Insights Imaging 15:268. https://doi.org/10.1186/s13244-024-01846-x. (PMID: 10.1186/s13244-024-01846-x3951406011549261)
Parillo M, Vaccarino F, Vertulli D et al (2024) Assessing the reliability of ChatGPT-4 in the appropriateness of radiology referrals. R Coll Radiol Open 2:100155. https://doi.org/10.1016/j.rcro.2024.100155. (PMID: 10.1016/j.rcro.2024.100155)
Potočnik J, Thomas E, Kearney D, Killeen RP, Heffernan EJ, Foley SJ (2025) Can ChatGPT and Gemini justify brain CT referrals? A comparative study with human experts and a custom prediction model. Eur Radiol Exp 9:24. https://doi.org/10.1186/s41747-025-00569-y. (PMID: 10.1186/s41747-025-00569-y3996626311836243)
Akinci D’Antonoli T, Stanzione A, Bluethgen C et al (2024) Large language models in radiology: fundamentals, applications, ethical considerations, risks, and future directions. Diagn Interv Radiol 30:80–90. https://doi.org/10.4274/dir.2023.232417. (PMID: 10.4274/dir.2023.2324173778967610916534)
Meskó B (2023) Prompt engineering as an important emerging skill for medical professionals: tutorial. J Med Internet Res 25:e50638. https://doi.org/10.2196/50638. (PMID: 10.2196/506383779243410585440)
Nguyen D, MacKenzie A, Kim YH (2024) Encouragement vs. liability: how prompt engineering influences ChatGPT-4’s radiology exam performance. Clin Imaging 115:110276. https://doi.org/10.1016/j.clinimag.2024.110276. (PMID: 10.1016/j.clinimag.2024.11027639288636)
Parillo M, Vaccarino F, Vertulli D et al (2024) Assessment of reason for exam imaging reporting and data system (RI-RADS) in inpatient diagnostic imaging referrals. Insights Imaging 15:268. https://doi.org/10.1186/s13244-024-01846-x. (PMID: 10.1186/s13244-024-01846-x3951406011549261)
Parillo M, Vaccarino F, Vertulli D et al (2024) Assessing the reliability of ChatGPT-4 in the appropriateness of radiology referrals. R Coll Radiol Open 2:100155. https://doi.org/10.1016/j.rcro.2024.100155. (PMID: 10.1016/j.rcro.2024.100155)
Potočnik J, Thomas E, Kearney D, Killeen RP, Heffernan EJ, Foley SJ (2025) Can ChatGPT and Gemini justify brain CT referrals? A comparative study with human experts and a custom prediction model. Eur Radiol Exp 9:24. https://doi.org/10.1186/s41747-025-00569-y. (PMID: 10.1186/s41747-025-00569-y3996626311836243)
Entry Date(s):
Date Created: 20251114 Latest Revision: 20251114
Update Code:
20251115
DOI:
10.1007/s00330-025-12150-7
PMID:
41238764
Database:
MEDLINE
Weitere Informationen
Compliance with ethical standards. Guarantor: The scientific guarantor of this publication is Raşit Eren Büyüktoka. Conflict of interest: The authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article. Statistics and biometry: No complex statistical methods were necessary for this paper. Informed consent: Written informed consent was not required for this study. Ethical approval: Institutional Review Board approval was not required. Study subjects or cohorts overlap: No study subjects or cohorts overlap. Methodology: Letter to the Editor