文献速递胸部DRCT

人工智能在健康筛查人群中改善胸片肺结节检测:一项随机对照试验

AI Improves Nodule Detection on Chest Radiographs in a Health Screening Population: A Randomized Controlled Trial.
PubMed 文献 · Radiology · 2023-02-07

该单中心、实用性、开放标签随机对照试验纳入2020年7月至2021年12月在健康筛查中心接受胸片检查的10476名参与者,随机分为AI组和非AI组各5238人。AI组由指定放射科医师参考AI计算机辅助检测结果阅片,主要结局为3个月内CT证实的可操作肺结节检出率;AI组为0.59%(31/5238),非AI组为0.25%(13/5238),比值比2.4(95%CI 1.3, 4.7;P=.008),恶性肺结节检出率AI组0.15%(8/5238)高于非AI组0.0%(0/5238)(P=.008)。

要点

  • AI辅助使胸片可操作肺结节检出率从0.25%升至0.59%,OR 2.4(95%CI 1.3, 4.7;P=.008)。
  • 可操作结节定义为实性结节>8 mm或亚实性结节实性部分>6 mm(Lung-RADS 4类)。
  • AI组与非AI组假转诊率(45.9% vs 56.0%,P=.14)和阳性报告率(2.3% vs 1.9%,P=.14)无显著差异。

核心结论

  • 在健康体检参与者中,基于人工智能的软件改善了胸片上可操作肺结节的检测。

研究设计与样本

  • 单中心、实用性、开放标签随机对照试验,共纳入10476名参与者(中位年龄59岁,IQR 50-66岁;5121名男性),AI组5238人、非AI组5238人;由三名指定放射科医师(经验13-36年)之一阅片,AI组参考AI计算机辅助检测结果;参考标准为3个月内CT证实的可操作肺结节。

诊断标准与关键数值

  • 可操作结节定义为实性结节大于8 mm或亚实性结节实性部分大于6 mm(Lung-RADS 4类);AI组可操作结节检出率0.59%(31/5238)vs 非AI组0.25%(13/5238),OR 2.4(95%CI 1.3, 4.7;P=.008);AI组恶性结节检出率0.15%(8/5238)vs 非AI组0.0%(0/5238)(P=.008);假转诊率AI组45.9%(56/122)vs 非AI组56.0%(56/100)(P=.14);阳性报告率AI组2.3%(122/5238)vs 非AI组1.9%(100/5238)(P=.14)。

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

Background The impact of artificial intelligence (AI)-based computer-aided detection (CAD) software has not been prospectively explored in real-world populations. Purpose To investigate whether commercial AI-based CAD software could improve the detection rate of actionable lung nodules on chest radiographs in participants undergoing health checkups. Materials and Methods In this single-center, pragmatic, open-label randomized controlled trial, participants who underwent chest radiography between July 2020 and December 2021 in a health screening center were enrolled and randomized into intervention (AI group) and control (non-AI group) arms. One of three designated radiologists with 13-36 years of experience interpreted each radiograph, referring to the AI-based CAD results for the AI group. The primary outcome was the detection rate, that is, the number of true-positive radiographs divided by the total number of radiographs, of actionable lung nodules confirmed on CT scans obtained within 3 months. Actionable nodules were defined as solid nodules larger than 8 mm or subsolid nodules with a solid portion larger than 6 mm (Lung Imaging Reporting and Data System, or Lung-RADS, category 4). Secondary outcomes included the positive-report rate, sensitivity, false-referral rate, and malignant lung nodule detection rate. Clinical outcomes were compared between the two groups using univariable logistic regression analyses. Results A total of 10 476 participants (median age, 59 years [IQR, 50-66 years]; 5121 men) were randomized to an AI group (n = 5238) or non-AI group (n = 5238). The trial met the predefined primary outcome, demonstrating an improved detection rate of actionable nodules in the AI group compared with the non-AI group (0.59% [31 of 5238 participants] vs 0.25% [13 of 5238 participants], respectively; odds ratio, 2.4; 95% CI: 1.3, 4.7; P = .008). The detection rate for malignant lung nodules was higher in the AI group compared with the non-AI group (0.15% [eight of 5238 participants] vs 0.0% [0 of 5238 participants], respectively; P = .008). The AI and non-AI groups showed similar false-referral rates (45.9% [56 of 122 participants] vs 56.0% [56 of 100 participants], respectively; P = .14) and positive-report rates (2.3% [122 of 5238 participants] vs 1.9% [100 of 5238 participants]; P = .14). Conclusion In health checkup participants, artificial intelligence-based software improved the detection of actionable lung nodules on chest radiographs. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Auffermann in this isssue.

来源:Radiology,查看原文。版权归原作者所有。

引用

  1. Nam, Hwang, Kim, et al. AI Improves Nodule Detection on Chest Radiographs in a Health Screening Population: A Randomized Controlled Trial. Radiology. 2023. PMID: 36749213. doi:10.1148/radiol.221894

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。