文献速递消化内镜消化道肿瘤与早癌

人工智能辅助结肠镜在三级临床环境中的结局评估

Outcomes of Artificial Intelligence-Enhanced Colonoscopy in a Tertiary Clinical Setting.
PubMed 文献 · Am J Gastroenterol · 2026-02-12

倾向性匹配后,CADe组腺瘤检出率(38.6% vs 34.2%)、息肉检出率(67.2% vs 59.4%)及每结肠镜腺瘤/息肉数均显著更高,但腺瘤检出率的提升主要归因于≤5 mm息肉的检出,其临床意义尚不确定。

要点

  • CADe可显著提高腺瘤检出率(38.6% vs 34.2%)和息肉检出率(67.2% vs 59.4%)。
  • CADe组每结肠镜腺瘤数(0.406 vs 0.359)和息肉数(1.297 vs 1.046)均显著增加。
  • 检出增益主要来自≤5 mm小息肉,其降低结直肠癌风险的临床意义不明确。

核心结论

  • 在临床实践中实施CADe显著改善了腺瘤检出率、息肉检出率、每结肠镜腺瘤数和息肉数。
  • 腺瘤检出率的提升似乎被≤5 mm息肉的检出所夸大,其临床意义尚不确定。

研究设计与样本

  • CADe系统在8个内镜室中的4个使用,形成CADe组和对照组,采用倾向性匹配校正年龄、性别、指征和医师。

主要发现

  • CADe组腺瘤检出率38.6% vs 对照组34.2%(RR=1.127,P<0.05)。
  • CADe组息肉检出率67.2% vs 对照组59.4%(RR=1.130,P<0.05)。
  • CADe组每结肠镜腺瘤数均值0.406(SD 0.637) vs 对照组0.359(SD 0.599)(RR=1.131,P<0.05)。
  • CADe组每结肠镜息肉数均值1.297(SD 1.188) vs 对照组1.046(SD 1.002)(RR=1.240,P<0.05)。
  • CADe带来的息肉切除增加主要由≤5 mm病变驱动,较大息肉的差异相对较小。

临床怎么用

  • CADe可用于标准化检测质量并提高结肠镜检查的腺瘤和息肉检出。
  • 需注意CADe对≤5 mm小息肉的过度检出,其临床获益尚待明确。

局限性

  • 单中心回顾性设计可能引入选择偏倚。
  • CADe组与对照组非随机分配,尽管进行了倾向性匹配。
  • ≤5 mm息肉的临床显著性在降低结直肠癌风险方面尚不确定。

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: Colonoscopies reduce colorectal cancer incidence and mortality, but challenges remain in detecting all precancerous lesions. Operator fatigue, technique variability, and subtle lesions can lead to missed adenomas, highlighting the need for tools that standardize detection quality. Computer-aided detection (CADe) systems use artificial intelligence to enhance lesion detection and improve screening colonoscopy quality. This study evaluates the impact of CADe on key quality and efficiency metrics in a clinical setting. METHODS: A single-center retrospective study at an academic tertiary center analyzed 4,028 colonoscopies from October 2022 to December 2023. The CADe system was used in 4 of 8 endoscopy suites, creating a CADe and control group. Propensity matching accounted for age, sex, indication, and physician. Primary outcomes included adenoma detection rate (ADR) and polyp detection rate (PDR). Adenomas per colonoscopy (APC) and polyps per colonoscopy (PPC) were also measured. Per-polyp analyses were performed as a tertiary outcome. RESULTS: ADR was significantly higher in the CADe group (38.6%) vs control (34.2%) (rate ratio [RR] = 1.127, P < 0.05). PDR was significantly higher in the CADe group (67.2%) vs control (59.4%) (RR = 1.130, P < 0.05). APC was significantly higher in the CADe group (M = 0.406, SD 0.637) vs control (M = 0.359, SD 0.599) (RR = 1.131, P < 0.05). PPC was significantly higher in the CADe group (M = 1.297, SD 1.188) vs control (M = 1.046, SD 1.002) (RR = 1.240, P < 0.05). The increase in polyp resection with CADe was driven predominantly by ≤5 mm lesions, with comparatively smaller differences for larger polyps. DISCUSSION: Implementing CADe in clinical practice significantly improved ADR, PDR, APC, and PPC. However, the increase in ADR seems inflated by the detection of polyps ≤5 mm, whose clinical significance in reducing colorectal cancer remains uncertain.

来源:Am J Gastroenterol,查看原文。版权归原作者所有。

引用

  1. Nayar KD, Yakout A, Bakheet N, et al. Outcomes of Artificial Intelligence-Enhanced Colonoscopy in a Tertiary Clinical Setting. Am J Gastroenterol. 2026. PMID: 41677150. doi:10.14309/ajg.0000000000003953

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。