A comparative evaluation of large language models for simplifying prostate cancer pathology reports: ChatGPT and Gemini
LLMs adopt distinct trade-off strategies between simplifying pathology reports and preserving their structure and logic, influenced by prompt design and textual style. Their application shows potential to enhance patient comprehension and clinical communication. Future work should focus on domain-specific fine-tuning to ensure safe and reliable clinical integration.
Authors
- Haoyang Zeng (ORCID: https://orcid.org/0000-0003-1057-2865)
- Xiang Wu (ORCID: https://orcid.org/0000-0001-8872-7738)
- Hanlin Liu (ORCID: https://orcid.org/0000-0002-2673-5289)
- L.Z. Wang (ORCID: https://orcid.org/0000-0001-5048-1680)
- Yangguang Yuan
- Huancheng Yang
- Shimei Luo
- Kun Zhang
- Zixi Ye
- Haoyuan Yuan
Institutions
- Shantou University (CN)
- Second Affiliated Hospital of Guangzhou Medical University (CN)
- Shantou University Medical College (CN)
- Shenzhen Luohu People's Hospital (CN)
- Guangzhou Medical University (CN)
Publication Details
- Journal
- International Journal of Surgery
- Published
- 2026-02-02
- DOI
- https://doi.org/10.1097/js9.0000000000004454
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00