Comparison of CT referral justification using clinical decision support and large language models in a large European cohort
Question Can GPT-4 and Claude-3 Haiku justify CT referrals as accurately as independent experts, using the ESR iGuide as the gold standard? Findings Independent experts outperformed large language models in test justification. GPT-4 and Claude-3 showed comparable organ prediction but struggled with contrast selection, limiting full automation. Clinical relevance While independent experts remain most reliable, integrating AI with expert oversight may improve CT referral appropriateness, optimizing resource allocation and enhancing clinical decision-making.
Authors
- Monika Hierath (ORCID: https://orcid.org/0000-0001-9136-0105)
- Mor Saban (ORCID: https://orcid.org/0000-0001-6869-0907)
- Boris Brkljačić (ORCID: https://orcid.org/0000-0002-5353-5821)
- Clara Singer
- Osnat Luxenburg (ORCID: https://orcid.org/0000-0003-1756-0701)
- Yaniv Alon
- Jacob Sosna
- A. Schreiner
Institutions
- Tel Aviv University (IL)
- Hebrew University of Jerusalem (IL)
- Sheba Medical Center (IL)
- Hadassah Medical Center (IL)
- University Hospital Dubrava (HR)
- European Society of Radiology (AT)
- Israel Ministry of Health (IL)
Publication Details
- Journal
- European Radiology
- Published
- 2025-04-27
- DOI
- https://doi.org/10.1007/s00330-025-11608-y
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Tel Aviv University