将大型语言模型整合进放射科工作流程:从摘要生成个性化报告模板的影响
这项回顾性研究将100例肿瘤患者CT随机均分为两组,比较传统报告与摘要式报告用时,并让GPT-4、Google Gemini和Claude Opus基于摘要和机构通用模板生成完整报告。摘要法平均报告时间6.76分钟,显著短于传统法8.95分钟(p<0.005);100份摘要中10份RADPEER评分劣于1分、3份有临床显著差异,仅1份LLM生成报告RADPEER评分劣于对应摘要;各模型间错误频率无显著差异,模板相关错误最常见(χ2=1.146,p=0.564)。
要点
- 摘要法平均报告时间6.76分钟,显著短于传统法8.95分钟(p<0.005)。
- 100份放射科医生摘要中10份RADPEER评分劣于1分,其中3份有临床显著差异。
- 仅1份LLM生成报告的RADPEER评分劣于其对应摘要。
核心结论
- 基于摘要的扫描报告并结合LLM使用通用模板生成完整个性化报告模板,可缩短报告时间并保持报告质量,但仍需人工监督以处理生成报告中的错误。
研究设计与样本
- 回顾性研究,纳入100例肿瘤患者的CT扫描并随机等分为两组,由两名放射科医生交叉生成传统报告与摘要报告,使用GPT-4、Google Gemini和Claude Opus三种LLM基于摘要和机构特定通用模板生成完整报告。
诊断标准与关键数值
- 由两名专家放射科医生以传统放射科医生报告为参考,采用ACR RADPEER评分系统对放射科医生摘要和LLM生成报告进行定性评估;100份摘要中10份RADPEER评分劣于1分、3份有临床显著差异,仅1份LLM生成报告RADPEER评分劣于对应摘要。
临床应用与阅片要点
- 原文未据此给出推荐。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
OBJECTIVE: To evaluate feasibility of large language models (LLMs) to convert radiologist-generated report summaries into personalized report templates, and assess its impact on scan reporting time and quality.
MATERIALS AND METHODS: In this retrospective study, 100 CT scans from oncology patients were randomly divided into two equal sets. Two radiologists generated conventional reports for one set and summary reports for the other, and vice versa. Three LLMs - GPT-4, Google Gemini, and Claude Opus - generated complete reports from the summaries using institution-specific generic templates. Two expert radiologists qualitatively evaluated the radiologist summaries and LLM-generated reports using the ACR RADPEER scoring system, using conventional radiologist reports as reference. Reporting time for conventional versus summary-based reports was compared, and LLM-generated reports were analyzed for errors. Quantitative similarity and linguistic metrics were computed to assess report alignment across models with the original radiologist-generated report summaries. Statistical analyses were performed using Python 3.0 to identify significant differences in reporting times, error rates and quantitative metrics.
RESULTS: The average reporting time was significantly shorter for summary method (6.76 min) compared to conventional method (8.95 min) (p < 0.005). Among the 100 radiologist summaries, 10 received RADPEER scores worse than 1, with three deemed to have clinically significant discrepancies. Only one LLM-generated report received a worse RADPEER score than its corresponding summary. Error frequencies among LLM-generated reports showed no significant differences across models, with template-related errors being most common (χ2 = 1.146, p = 0.564). Quantitative analysis indicated significant differences in similarity and linguistic metrics among the three LLMs (p < 0.05), reflecting unique generation patterns.
CONCLUSION: Summary-based scan reporting along with use of LLMs to generate complete personalized report templates can shorten reporting time while maintaining the report quality. However, there remains a need for human oversight to address errors in the generated reports.
RELEVANCE STATEMENT: Summary-based reporting of radiological studies along with the use of large language models to generate tailored reports using generic templates has the potential to make the workflow more efficient by shortening the reporting time while maintaining the quality of reporting.
引用
- Gupta A, Hussain M, Nikhileshwar K, et al. Integrating Large language models into radiology workflow: Impact of generating personalized report templates from summary. Eur J Radiol. 2025. PMID: 40435550. doi:10.1016/j.ejrad.2025.112198
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。