指南与共识消化、代谢与肾脏急症

提高影像报告对社会指南的依从性:利用超声放射科医师学会胆囊息肉指南的可行性研究

Increasing Adherence to Societal Recommendations in Radiology Reporting: A Feasibility Study Using Society of Radiologists in Ultrasound Guidelines for Incidentally Detected Gallbladder Polyps.
指南 / 共识 · Ultrasound Q · 2024-12-17
一句话结论基于大语言模型的GB-PRL工具在胆囊息肉风险分层与随访建议上准确率100%,优于主流大语言模型及回顾性影像报告,但清晰度与一致性改善未达统计学显著。

该可行性研究回顾性分析了2022年成人急诊患者胆囊超声检查,基于2021年超声放射科医师学会(SRU)指南开发了检索增强生成(RAG)交互工具GB-PRL。在假设性用户查询中,GB-PRL风险分类与随访建议准确率达100%(P < 0.001),优于领先的闭源和开源大语言模型;在回顾性数据上,其准确率也优于影像报告(P = 0.04)。GB-PRL在清晰度和一致性上表现更优,但相较影像报告的改善无统计学显著性(P = 0.22)。作者指出,在整合入临床实践前需对GB-PRL进行前瞻性测试。

要点

  • GB-PRL在假设性用户查询中风险分类与随访建议准确率达100%(P < 0.001),优于领先的闭源和开源大语言模型。
  • 在回顾性数据上,GB-PRL准确率优于影像报告(P = 0.04)。
  • GB-PRL清晰度和一致性优于影像报告,但差异无统计学意义(P = 0.22)。
  • 作者认为,在整合入临床实践前需对GB-PRL进行前瞻性测试。

适用人群与场景

  • 2022年成人急诊患者中接受胆囊超声检查者(回顾性分析)。

研究设计与关键结果

  • 研究类型为可行性研究,回顾性分析2022年成人急诊患者胆囊超声检查。
  • 基于2021年SRU指南开发交互工具GB-PRL,采用检索增强生成(RAG)与提示工程。
  • 由委员会认证的放射科医师测试准确性,由委员会认证的急诊医学医师评估清晰度和一致性。
  • 在假设性用户查询中,GB-PRL风险分类与随访建议准确率达100%(P < 0.001),优于领先的闭源和开源大语言模型。
  • 在回顾性数据上,GB-PRL准确率优于影像报告(P = 0.04)。
  • GB-PRL清晰度和一致性优于影像报告,但改善无统计学显著性(P = 0.22)。

证据类型、等级与局限

  • 证据类型:可行性研究(回顾性分析)。
  • 局限:进一步工作需对GB-PRL进行前瞻性测试,之后才能整合入临床实践。

对床旁实践的改变

  • 作者认为,在整合入临床实践前需对GB-PRL进行前瞻性测试。

指南或共识出处

  • Society of Radiologists in Ultrasound (SRU) 2021年指南:管理偶然发现的胆囊息肉。

提炼说明

  • 本条依据论文摘要整理;摘要未涉及「诊断标准与关键阈值」「处置流程与药物剂量」「红旗征与不能漏的情况」,故未列出这些栏目;全文请点「阅读原文」。
英文原文(摘要)· 点击展开

Incidental findings in diagnostic imaging are common, but follow-up recommendations often lack consistency. The Society of Radiologists in Ultrasound (SRU) issued guidelines in 2021 for managing incidentally detected gallbladder polyps, aiming to balance follow-up with avoiding overtreatment. There is variable adherence to these guidelines in radiology reports, however, which makes it difficult for the clinician to pursue appropriate follow-up for the patient. The purpose of this project is to test the feasibility of a Large Language Model (LLM)-based tool to incorporate SRU guidelines into radiology reports. Additionally, we propose a framework for closely integrating societal follow-up recommendations into radiology reports, using this tool as an example.Following institutional review board approval, we retrospectively reviewed gallbladder ultrasound examinations performed on adult ED patients in 2022. Data on patient demographics and radiology report content were collected. Using the 2021 SRU guidelines, we developed an interactive tool employing a retriever-augmented generator (RAG) and prompt engineering. A board-certified radiologist tested the accuracy, whereas a board-certified emergency medicine physician assessed the clarity and consistency of the recommendations.The interactive tool, GB-PRL, outperformed leading closed-source and open-source LLMs, achieving 100% accuracy in risk categorization and follow-up recommendations on hypothetical user queries (P < 0.001). The tool also showed superior accuracy compared to radiology reports on retrospective data (P = 0.04). Although GB-PRL demonstrated greater clarity and consistency, the improvement from the radiology reports was not statistically significant (P = 0.22). Further work is needed for prospective testing of GB-PRL before integrating it into clinical practice.

来源:Ultrasound Q,查看原文。版权归原作者所有。

参考来源

  1. Mugu VK, Carr BM, Olson MC, et al. Increasing Adherence to Societal Recommendations in Radiology Reporting: A Feasibility Study Using Society of Radiologists in Ultrasound Guidelines for Incidentally Detected Gallbladder Polyps. Ultrasound Q. 2024. PMID: 39690147. doi:10.1097/RUQ.0000000000000699

供执业医师抢救与诊疗参考,不替代临床判断;剂量请结合体重、肝肾功能和本院药品规格复核,以指南原文为准。