文献速递胸部技术与安全DR

使用人工智能识别无异常胸部X线片以自动生成报告

Using AI to Identify Unremarkable Chest Radiographs for Automatic Reporting.
PubMed 文献 · Radiology · 2024-01-01

本回顾性研究纳入丹麦四家医院2020年1月1日至12日连续成人胸部X线片1961例,由两名胸部放射科医师盲法判定影像是否异常作为参考标准,评估商用AI工具在不同敏感度下排除病变的特异度。AI在敏感度≥98%时特异度为24.5%–52.7%;在敏感度≥95.4%时AI严重漏诊率≤1.1%,与放射科报告相当或更低。作者指出结果需在前瞻性研究中确认。

要点

  • AI在敏感度99.9%、99.0%、98.0%时,对无异常胸片特异度分别为24.5%、47.1%、52.7%。
  • 参考标准判定37.2%(730/1961)胸片无异常,62.8%(1231/1961)有异常。
  • AI敏感度≥95.4%时,严重漏诊率≤1.1%。

核心结论

  • 商用AI工具在敏感度≥98%时可正确排除24.5%–52.7%无异常胸片中的病变。
  • AI在敏感度≥95.4%时严重漏诊率与放射科报告相当或更低;作者指出结果需在前瞻性研究中确认。

研究设计与样本

  • 回顾性研究,纳入丹麦四家医院2020年1月1日至12日连续成人(≥18岁)胸部X线片,每例患者一张,共1961例(中位年龄72岁,IQR 58–81岁;993例女性)。
  • 排除标准为放射报告不充分或AI输出错误;由两名对AI输出不知情的胸部放射科医师依据预定义无异常表现将胸片判为「有异常」或「无异常」作为参考标准,放射报告按同样方式分类。
  • 商用AI工具经调整输出胸片「异常」概率,用于计算不同AI敏感度下的特异度;AI和/或放射报告漏诊的胸片由一名胸部放射科医师分级为严重、有临床意义或无临床意义。
  • 配对比例比较采用McNemar检验。

诊断标准与关键数值

  • 参考标准将1231/1961(62.8%)胸片判为有异常、730/1961(37.2%)判为无异常。
  • AI敏感度99.9%时特异度24.5%(179/730,95%CI 21–28)。
  • AI敏感度99.0%时特异度47.1%(344/730,95%CI 43–51)。
  • AI敏感度98.0%时特异度52.7%(385/730,95%CI 49–56)。
  • AI敏感度固定为与放射报告相近的87.2%时,AI漏诊中严重2.2%(27/1231)、有临床意义4.1%(51/1231)、无临床意义6.5%(80/1231),放射报告分别为1.1%(14/1231,P=.01)、3.6%(44/1231,P=.46)、8.1%(100/1231,P=.11)。

局限性

  • 作者指出结果需在前瞻性研究中确认。

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

Background Radiology practices have a high volume of unremarkable chest radiographs and artificial intelligence (AI) could possibly improve workflow by providing an automatic report. Purpose To estimate the proportion of unremarkable chest radiographs, where AI can correctly exclude pathology (ie, specificity) without increasing diagnostic errors. Materials and Methods In this retrospective study, consecutive chest radiographs in unique adult patients (≥18 years of age) were obtained January 1-12, 2020, at four Danish hospitals. Exclusion criteria included insufficient radiology reports or AI output error. Two thoracic radiologists, who were blinded to AI output, labeled chest radiographs as "remarkable" or "unremarkable" based on predefined unremarkable findings (reference standard). Radiology reports were classified similarly. A commercial AI tool was adapted to output a chest radiograph "remarkableness" probability, which was used to calculate specificity at different AI sensitivities. Chest radiographs with missed findings by AI and/or the radiology report were graded by one thoracic radiologist as critical, clinically significant, or clinically insignificant. Paired proportions were compared using the McNemar test. Results A total of 1961 patients were included (median age, 72 years [IQR, 58-81 years]; 993 female), with one chest radiograph per patient. The reference standard labeled 1231 of 1961 chest radiographs (62.8%) as remarkable and 730 of 1961 (37.2%) as unremarkable. At 99.9%, 99.0%, and 98.0% sensitivity, the AI had a specificity of 24.5% (179 of 730 radiographs [95% CI: 21, 28]), 47.1% (344 of 730 radiographs [95% CI: 43, 51]), and 52.7% (385 of 730 radiographs [95% CI: 49, 56]), respectively. With the AI fixed to have a similar sensitivity as radiology reports (87.2%), the missed findings of AI and reports had 2.2% (27 of 1231 radiographs) and 1.1% (14 of 1231 radiographs) classified as critical (P = .01), 4.1% (51 of 1231 radiographs) and 3.6% (44 of 1231 radiographs) classified as clinically significant (P = .46), and 6.5% (80 of 1231) and 8.1% (100 of 1231) classified as clinically insignificant (P = .11), respectively. At sensitivities greater than or equal to 95.4%, the AI tool exhibited less than or equal to 1.1% critical misses. Conclusion A commercial AI tool used off-label could correctly exclude pathology in 24.5%-52.7% of all unremarkable chest radiographs at greater than or equal to 98% sensitivity. The AI had equal or lower rates of critical misses than radiology reports at sensitivities greater than or equal to 95.4%. These results should be confirmed in a prospective study. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Yoon and Hwang in this issue.

来源:Radiology,查看原文。版权归原作者所有。

引用

  1. Plesner LL, Müller FC, Brejnebøl MW, et al. Using AI to Identify Unremarkable Chest Radiographs for Automatic Reporting. Radiology. 2024. PMID: 39162628. doi:10.1148/radiol.240272

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。