文献速递消化内镜消化道肿瘤与早癌

社区内结肠镜检查中计算机辅助检测的评估(AI-SEE):一项多中心随机临床试验

Evaluation of Computer-Aided Detection During Colonoscopy in the Community (AI-SEE): A Multicenter Randomized Clinical Trial.
PubMed 文献 · Am J Gastroenterol · 2023-03-09

AI-SEE 是一项在美国 4 个社区内镜中心开展的随机对照试验,2020 年 9 月 28 日至 2021 年 9 月 24 日纳入 769 例患者(CADe 组 387 例),评估计算机辅助检测(CADe)对息肉检出的影响。结果显示 CADe 组与非 CADe 组每次结肠镜检查的腺瘤数无显著差异(0.73 vs 0.67,P=0.496),腺瘤检出率(35.9 vs 37.2%,P=0.774)与锯齿状息肉检出率(6.5 vs 6.3%,P=1.000)相似;CADe 组非腺瘤性非锯齿状息肉检出数增加(0.90 vs 0.51,P<0.0001),平均退镜时间延长(11.7 vs 10.7 分钟,P=0.003)。

要点

  • 社区内镜中心中 CADe 未显著提高每次结肠镜检查的腺瘤检出数(0.73 vs 0.67,P=0.496)。
  • CADe 组腺瘤检出率与锯齿状息肉检出率与非 CADe 组相似(35.9 vs 37.2%,P=0.774;6.5 vs 6.3%,P=1.000)。
  • CADe 组非腺瘤性非锯齿状息肉检出数增加(0.90 vs 0.51,P<0.0001),平均退镜时间延长(11.7 vs 10.7 分钟,P=0.003)。

核心结论

  • 在社区非学术内镜中心,使用 CADe 未使每次结肠镜检查检出的腺瘤数出现统计学显著差异。
  • 需要进一步研究以更好理解为何部分内镜医师从 CADe 获得显著获益而另一些没有。

研究设计与样本

  • AI-SEE 为随机对照试验,于 2020 年 9 月 28 日至 2021 年 9 月 24 日在美国 4 个社区内镜中心开展。
  • 共纳入 769 例患者,采用区组随机分配至使用或不使用 CADe(EndoVigilant)的结肠镜检查,其中 CADe 组 387 例,两组患者人口学特征相似。

主要发现

  • 每次结肠镜检查的腺瘤数在 CADe 组与非 CADe 组间无显著差异(0.73 vs 0.67,P=0.496)。
  • 每次结肠镜检查的锯齿状息肉数两组无差异(0.08 vs 0.08,P=0.965)。
  • 每次结肠镜检查的非腺瘤性非锯齿状息肉数 CADe 组高于非 CADe 组(0.90 vs 0.51,P<0.0001),导致 CADe 组每次提取的腺瘤比例更低。
  • 腺瘤检出率(35.9 vs 37.2%,P=0.774)与锯齿状息肉检出率(6.5 vs 6.3%,P=1.000)在 CADe 组与非 CADe 组间相似。
  • 平均退镜时间 CADe 组较非 CADe 组长(11.7 vs 10.7 分钟,P=0.003);未发现息肉时两组平均退镜时间相似(9.1 vs 8.8 分钟,P=0.288)。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文指出需要进一步研究以更好理解为何部分内镜医师从 CADe 获得显著获益而另一些没有。

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)。

原文

INTRODUCTION: There has been increasing interest in artificial intelligence in gastroenterology. To reduce miss rates during colonoscopy, there has been significant exploration in computer-aided detection (CADe) devices. In this study, we evaluate the use of CADe in colonoscopy in community-based, nonacademic practices. METHODS: Between September 28, 2020, and September 24, 2021, a randomized controlled trial (AI-SEE) was performed evaluating the impact of CADe on polyp detection in 4 community-based endoscopy centers in the United States Patients were block-randomized to undergoing colonoscopy with or without CADe (EndoVigilant). Primary outcomes measured were adenomas per colonoscopy and adenomas per extraction (the percentage of polyps removed that are adenomas). Secondary end points included serrated polyps per colonoscopy; nonadenomatous, nonserrated polyps per colonoscopy; adenoma and serrated polyp detection rates; and procedural time. RESULTS: A total of 769 patients were enrolled (387 with CADe), with similar patient demographics between the 2 groups. There was no significant difference in adenomas per colonoscopy in the CADe and non-CADe groups (0.73 vs 0.67, P = 0.496). Although the use of CADe did not improve identification of serrated polyps per colonoscopy (0.08 vs 0.08, P = 0.965), the use of CADe increased identification of nonadenomatous, nonserrated polyps per colonoscopy (0.90 vs 0.51, P < 0.0001), resulting in detection of fewer adenomas per extraction in the CADe group. The adenoma detection rate (35.9 vs 37.2%, P = 0.774) and serrated polyp detection rate (6.5 vs 6.3%, P = 1.000) were similar in the CADe and non-CADe groups. Mean withdrawal time was longer in the CADe group compared with the non-CADe group (11.7 vs 10.7 minutes, P = 0.003). However, when no polyps were identified, there was similar mean withdrawal time (9.1 vs 8.8 minutes, P = 0.288). There were no adverse events. DISCUSSION: The use of CADe did not result in a statistically significant difference in the number of adenomas detected. Additional studies are needed to better understand why some endoscopists derive substantial benefits from CADe and others do not. ClinicalTrials.gov number: NCT04555135.

来源:Am J Gastroenterol,查看原文。版权归原作者所有。

引用

  1. Wei MT, Shankar U, Parvin R, et al. Evaluation of Computer-Aided Detection During Colonoscopy in the Community (AI-SEE): A Multicenter Randomized Clinical Trial. Am J Gastroenterol. 2023. PMID: 36892545. doi:10.14309/ajg.0000000000002239

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。