文献速递腹部技术与安全CTMR

基于AI工具自动生成腹部放射报告印象的性能评价

Automated generation of impressions in abdominal radiology reports using an artificial intelligence-based tool: performance compared to manual impressions.
PubMed 文献 · Abdom Radiol (NY) · 2026-07-15

结果显示GI在38%报告中被优先选择,并且在多数质量指标上被评为等同或优于RI。

要点

  • AI生成印象在连贯性、全面性、事实一致性方面总体表现不低于人工印象。
  • AI生成的印象可用于辅助腹部报告书写,但仍需医生审核确认。
  • 单一中心回顾性设计限制了结果的普遍适用性。

核心结论

  • AI生成的印象在临床上可接受,并在多数报告的质量指标上被评为等同或优于放射科医生生成的印象。

研究设计与样本

  • 每份报告生成一个AI印象,与原始放射科医生印象配对。
  • 评价指标包括连贯性、全面性和事实一致性,采用5分Likert量表。

诊断标准与关键数值

  • GI在38%的报告中被优先选择(95% CI 32-45%),RI在45%被优先选择(95% CI 39-50%),17%无偏好。
  • 混合效应逻辑回归显示GI被评为等同或优于RI的比值比为1.34(95% CI 1.004-1.788,p=0.02)。
  • 在连贯性方面,79%的病例中GI被评为等同或优于RI。
  • 在全面性方面,66%的病例中GI被评为等同或优于RI。
  • 在事实一致性方面,77%的病例中GI被评为等同或优于RI。

临床应用与阅片要点

  • AI生成的印象可集成到听写软件中,用于自动生成报告印象,减轻报告书写负担。
  • 该工具可作为报告质量辅助工具,但尚不能完全替代人工审核。

局限性

  • 单中心回顾性研究,样本量有限,可能影响结果外推。
  • 评价基于人工评分,存在主观性。
  • 原文未报告AI工具的具体算法、训练数据及与不同设备或序列的适配情况。

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: Recent years have seen a rapid development of artificial intelligence (AI) tools to enhance radiologists' workflow, but most have focused on image acquisition and interpretation. Generating radiology reports is a critical element of practice but remains a source of inefficiency and cognitive load.

PURPOSE: To investigate the performance of an AI based tool integrated into dictation software to automate generation of report impressions and compare it with radiologist generated impressions.

METHODS: One hundred consecutive abdominal radiology reports were retrospectively selected in January 2024 from a single center. An AI-generated impression (GI) was created for each report and compared with the original radiologist impression (RI). Ten subspecialty abdominal radiologists evaluated the blinded, randomized pairs. Each impression was evaluated on a 5-point Likert scale for coherence, comprehensiveness, and factual consistency, and an overall preference for the impression was recorded. Cumulative link mixed models and binomial logistic regression were used where appropriate.

RESULTS: GI was preferred in 38% of reports (95% CI 32-45%), RI in 45% (95% CI 39-50%), with no preference in 17% of instances. Mixed-effects logistic regression demonstrated that GI was rated as equivalent or preferred to RI (odds ratio 1.34, 95% CI 1.004-1.788, p = 0.02). Radiologists rated GI equivalent or superior to RI in 79% of cases for coherence, 66% for comprehensiveness, and 77% for factual consistency.

CONCLUSION: The AI generated impressions were clinically acceptable and rated equivalent or superior to radiologist-generated impressions in the majority of cases across key quality metrics.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Mojtahed, Ghosh, Goiffon, et al. Automated generation of impressions in abdominal radiology reports using an artificial intelligence-based tool: performance compared to manual impressions. Abdom Radiol (NY). 2026. PMID: 42455325. doi:10.1007/s00261-026-05688-7

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。