Large Language Models in Summarizing Radiology Report Impressions for Lung Cancer in Chinese: Evaluation Study
Current LLMs can produce radiology impressions with high completeness and correctness but fall short in conciseness and verisimilitude, indicating they cannot yet fully replace impressions written by radiologists.
Authors
- Shanyuan Zhang (ORCID: https://orcid.org/0000-0002-3051-4454)
- Danqing Hu (ORCID: https://orcid.org/0000-0003-0810-4819)
- Zhu Xiaofeng
- Bing Liu (ORCID: https://orcid.org/0000-0001-8271-4530)
- Qing Liu (ORCID: https://orcid.org/0009-0008-7432-9729)
Institutions
- Peking University (CN)
- Nanjing University of Science and Technology (CN)
- Peking University Cancer Hospital (CN)
- Zhejiang Lab (CN)
Publication Details
- Journal
- Journal of Medical Internet Research
- Published
- 2025-04-03
- DOI
- https://doi.org/10.2196/65547
- Citations
- 22
- Primary Topic
- Topic Modeling
- Type
- article
- Field-Weighted Citation Impact
- 54.58