文献速递胸部技术与安全DR

放射科医师与人工智能生成的初步报告互动:一项纵向多阅片者研究

Radiologist Interaction with Artificial Intelligence-Generated Preliminary Reports: A Longitudinal Multireader Study.
PubMed 文献 · J Am Coll Radiol · 2025-09-20

该多病例多阅片者研究让5名放射科医师借助放射科专用多模态AI生成的初步报告解读756张公开胸部X线片,分7个连续批次各108张。结果显示阅片时间从第1批25.8秒降至第7批19.3秒(P<.001),无修改接受率从54.6%升至60.2%(P<.001),正常胸片接受率68.9%高于异常胸片52.6%(P<.001);异常胸片的一致性和质量评分波动显著。

要点

  • AI初步报告可缩短胸片阅片时间,第7批19.3秒较第1批25.8秒下降(P<.001)。
  • 无修改接受率正常胸片68.9%高于异常胸片52.6%(P<.001)。
  • 异常胸片的一致性和质量评分波动显著(均P<.05),需加强审核。

核心结论

  • AI生成的报告提高了胸片解读效率,接受度随时间上升,但异常病例的一致性和质量评分存在波动,强调对复杂胸片解读需加强监督。

研究设计与样本

  • 多病例、多阅片者研究,纳入756张公开胸部X线片,由5名放射科医师使用放射科专用多模态AI模型生成的初步报告进行解读,分为7个连续批次、每批108张;由2名胸部放射科医师采用RADPEER标准评估一致性、采用5点Likert量表评估质量。

诊断标准与关键数值

  • 一致性评估采用RADPEER标准,质量评估采用5点Likert量表,由2名胸部放射科医师完成。
  • 阅片时间从第1批25.8秒降至第7批19.3秒(P<.001)。
  • 无修改接受率从54.6%升至60.2%(P<.001);正常胸片接受率68.9% vs 异常胸片52.6%(P<.001)。
  • 正常胸片的一致性和质量评分中位数保持稳定,异常胸片则波动显著(均P<.05)。

临床应用与阅片要点

  • 作者认为对复杂胸片的解读需加强监督。

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

OBJECTIVES: To investigate the integration of multimodal AI-generated reports into radiology workflow over time, focusing on their impact on efficiency, acceptability, and report quality.

METHODS: A multicase, multireader study involved 756 publicly available chest radiographs interpreted by five radiologists using preliminary reports generated by a radiology-specific multimodal AI model, divided into 7 sequential batches of 108 radiographs each. Two thoracic radiologists assessed the final reports using RADPEER criteria for agreement and 5-point Likert scale for quality. Reading times, rate of acceptance without modification, agreement, and quality scores were measured, with statistical analyses evaluating trends across seven sequential batches.

RESULTS: Radiologists' reading times for chest radiographs decreased from 25.8 seconds in batch 1 to 19.3 seconds in batch 7 (P < .001). Acceptability increased from 54.6% to 60.2% (P < .001), with normal chest radiographs demonstrating high rates (68.9%) compared with abnormal chest radiographs (52.6%; P < .001). Median agreement and quality scores remained stable for normal chest radiographs but varied significantly for abnormal chest radiographs (all P < .05).

DISCUSSION: The introduction of AI-generated reports improved efficiency of chest radiograph interpretation, and acceptability increased over time. However, agreement and quality scores showed variability, particularly in abnormal cases, emphasizing the need for oversight in the interpretation of complex chest radiographs.

来源:J Am Coll Radiol,查看原文。版权归原作者所有。

引用

  1. Hong EK, Suh CH, Nukala M, et al. Radiologist Interaction with Artificial Intelligence-Generated Preliminary Reports: A Longitudinal Multireader Study. J Am Coll Radiol. 2025. PMID: 40983179. doi:10.1016/j.jacr.2025.09.015

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。