Comparative performance of large language models in structuring head CT radiology reports: multi-institutional validation study in Japan
All three proprietary LLMs exhibited strong performance in structuring free-text head CT reports for intracranial hemorrhage and skull fractures. While the choice of prompting method influenced accuracy, all models demonstrated robust potential for clinical and research applications. Future work should refine the prompts and validate these approaches in prospective, multilingual settings.
Authors
- Yasuhito Mitsuyama (ORCID: https://orcid.org/0000-0001-7979-2300)
- Shannon Leigh Walston (ORCID: https://orcid.org/0000-0002-7268-8313)
- Shoya Ishimaru (ORCID: https://orcid.org/0000-0002-5374-1510)
- Hirotaka Takita (ORCID: https://orcid.org/0000-0003-2860-4503)
- Daiju Ueda (ORCID: https://orcid.org/0000-0002-3878-3616)
- Ko Watanabe (ORCID: https://orcid.org/0000-0003-0252-1785)
Institutions
- Osaka Prefecture University (JP)
- Osaka City University (JP)
- German Research Centre for Artificial Intelligence (DE)
- Osaka Metropolitan University (JP)
Publication Details
- Journal
- Japanese Journal of Radiology
- Published
- 2025-05-14
- DOI
- https://doi.org/10.1007/s11604-025-01799-1
- Citations
- 2
- Primary Topic
- Radiology practices and education
- Type
- article
- Field-Weighted Citation Impact
- 2.72