AGA 动态临床实践指南:计算机辅助检测辅助结肠镜检查
美国胃肠病学会(AGA)基于 GRADE 框架,综合系统评价、微观模拟研究、患者价值观与偏好及医疗提供者信任度证据,评估计算机辅助检测(CADe)辅助结肠镜检测结直肠息肉的效果。因关键结局证据确定性极低,专家组未做出推荐或不推荐 CADe 辅助结肠镜的结论,但承认腺瘤检出率提高 8%(95%CI 6%-10%)。
要点
- 专家组未对 CADe 辅助结肠镜做出推荐或不推荐,因关键结局证据确定性极低。
- CADe 使腺瘤检出率提高 8%(95%CI 6%-10%),进展期腺瘤和/或无蒂锯齿状病变检出率提高 2%(95%CI 0%-4%)。
- 每万人中结直肠癌减少 11 例、结直肠癌死亡减少 2 例,但每万人增加 635 例更密集监测结肠镜。
核心结论
- 指南强调 CADe 有利与不利效应之间权衡接近,且当前证据有限,不足以支持做出推荐。
- 专家组承认 CADe 作为迭代人工智能应用有持续改进的潜力,正在发表的有关关键结局的证据将有助于未来推荐。
研究设计与样本
- 美国胃肠病学会(AGA)指南,由多学科专家组(内容专家与指南方法学家)采用 GRADE 框架制定。
- 证据来源包括:CADe 辅助结肠镜利弊的系统评价、估计 CADe 对长期患者重要结局影响的微观模拟研究、结肠镜患者价值观与偏好的系统检索、以及评估胃肠病学中医疗提供者对人工智能技术信任度的系统评价。
主要发现
- 关键结局证据确定性极低,有利与不利效应包括:每万人结直肠癌减少 11 例、结直肠癌死亡减少 2 例。
- 每万人增加 635 例更密集的监测结肠镜检查。
- 腺瘤检出率提高 8%(95%CI 6%-10%),进展期腺瘤和/或无蒂锯齿状病变检出率提高 2%(95%CI 0%-4%)。
关键数值与推荐
- 专家组结论:因关键结局证据确定性极低,无法对 CADe 辅助结肠镜做出推荐或不推荐。
- 专家组注意到腺瘤检出率提高 8%(95%CI 6%-10%)。
- 专家组注意到进展期腺瘤和/或无蒂锯齿状病变检出率提高 2%(95%CI 0%-4%)。
临床怎么用
- 原文未据此给出推荐。
局限性
- 关键结局证据确定性极低。
- 当前证据有限,不足以支持做出推荐。
- 有利与不利效应之间权衡接近。
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
BACKGROUND & AIMS: This American Gastroenterological Association (AGA) guideline is intended to provide an overview of the evidence and support endoscopists and patients on the use of computer-aided detection (CADe) systems for the detection of colorectal polyps during colonoscopy. METHODS: A multidisciplinary panel of content experts and guideline methodologists used the Grading of Recommendations Assessment, Development and Evaluation framework and relied on the following sources of evidence: (1) a systematic review examining the desirable and undesirable effects (ie, benefits and harms) of CADe-assisted colonoscopy, (2) a microsimulation study estimating the effects of CADe on longer-term patient-important outcomes, (3) a systematic search of evidence evaluating the values and preferences of patients undergoing colonoscopy, and (4) a systematic review of studies evaluating health care providers' trust in artificial intelligence technology in gastroenterology. RESULTS: The panel reached the conclusion that no recommendation could be made for or against the use of CADe-assisted colonoscopy in light of very low certainty of evidence for the critical outcomes, desirable and undesirable (11 fewer colorectal cancers per 10,000 individuals and 2 fewer colorectal cancer deaths per 10,000 individuals), increased burden of more intensive surveillance colonoscopies (635 more per 10,000 individuals), and cost and resource implications. The panel acknowledged the 8% (95% CI, 6%-10%) increase in adenoma detection rate and 2% (95% CI, 0%-4%) increase in advanced adenoma and/or sessile serrated lesion detection rate. CONCLUSIONS: This guideline highlights the close tradeoff between desirable and undesirable effects and the limitations in the current evidence to support a recommendation. The panel acknowledged the potential for CADe to continually improve as an iterative artificial intelligence application. Ongoing publications providing evidence for critical outcomes will help inform a future recommendation.
引用
- Sultan S, Shung DL, Kolb JM, et al. AGA Living Clinical Practice Guideline on Computer-Aided Detection-Assisted Colonoscopy. Gastroenterology. 2025. PMID: 40121061. doi:10.1053/j.gastro.2025.01.002
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。