Wang Pu, Liu Xiao-Gang, Kang Min, Peng Xue, Shu Mei-Ling, Zhou Guan-Yu, Liu Pei-Xi, Xiong Fei, Deng Ming-Ming, Xia Hong-Fen, Li Jian-Jun, Long Xiao-Qi, Song Yan, Li Liang-Ping
Department of Gastroenterology, Sichuan Provincial People's Hospital, University of Electronic Science and Technology of China, Chengdu, Sichuan, P. R. China.
Department of Gastroenterology, The Affiliated Hospital of Southwest Medical University, Luzhou, Sichuan, P. R. China.
Gastroenterol Rep (Oxf). 2023 Jan 19;11:goac081. doi: 10.1093/gastro/goac081. eCollection 2023.
In colonoscopy screening for colorectal cancer, human vision limitations may lead to higher miss rate of lesions; artificial intelligence (AI) assistance has been demonstrated to improve polyp detection. However, there still lacks direct evidence to demonstrate whether AI is superior to trainees or experienced nurses as a second observer to increase adenoma detection during colonoscopy. In this study, we aimed to compare the effectiveness of assistance from AI and human observer during colonoscopy.
A prospective multicenter randomized study was conducted from 2 September 2019 to 29 May 2020 at four endoscopy centers in China. Eligible patients were randomized to either computer-aided detection (CADe)-assisted group or observer-assisted group. The primary outcome was adenoma per colonoscopy (APC). Secondary outcomes included polyp per colonoscopy (PPC), adenoma detection rate (ADR), and polyp detection rate (PDR). We compared continuous variables and categorical variables by using R studio (version 3.4.4).
A total of 1,261 (636 in the CADe-assisted group and 625 in the observer-assisted group) eligible patients were analysed. APC (0.42 vs 0.35, =0.034), PPC (1.13 vs 0.81, <0.001), PDR (47.5% vs 37.4%, <0.001), ADR (25.8% vs 24.0%, =0.464), the number of detected sessile polyps (683 vs 464, <0.001), and sessile adenomas (244 vs 182, =0.005) were significantly higher in the CADe-assisted group than in the observer-assisted group. False detections of the CADe system were lower than those of the human observer (122 vs 191, <0.001).
Compared with the human observer, the CADe system may improve the clinical outcome of colonoscopy and reduce disturbance to routine practice (Chictr.org.cn No.: ChiCTR1900025235).
在结肠镜检查筛查结直肠癌时，人类视觉的局限性可能导致病变漏诊率较高；人工智能（AI）辅助已被证明可提高息肉检测率。然而，仍缺乏直接证据证明在结肠镜检查期间，作为第二观察者，AI是否优于实习医生或经验丰富的护士以提高腺瘤检测率。在本研究中，我们旨在比较结肠镜检查期间AI辅助和人类观察者辅助的有效性。
2019年9月2日至2020年5月29日在中国的四个内镜中心进行了一项前瞻性多中心随机研究。符合条件的患者被随机分为计算机辅助检测（CADe）辅助组或观察者辅助组。主要结局是每次结肠镜检查的腺瘤数（APC）。次要结局包括每次结肠镜检查的息肉数（PPC）、腺瘤检测率（ADR）和息肉检测率（PDR）。我们使用R studio（版本3.4.4）比较连续变量和分类变量。
共分析了1261例符合条件的患者（CADe辅助组636例，观察者辅助组625例）。CADe辅助组的APC（0.42对0.35，=0.034）、PPC（1.13对0.81，<0.001）、PDR（47.5%对37.4%，<0.001）、ADR（25.8%对24.0%，=0.464）、检测到的无蒂息肉数量（683对464，<0.001）和无蒂腺瘤数量（244对182，=0.005）均显著高于观察者辅助组。CADe系统的假检测低于人类观察者（122对191，<0.001）。
与人类观察者相比，CADe系统可能改善结肠镜检查的临床结局并减少对常规操作的干扰（中国临床试验注册中心编号：ChiCTR1900025235）。
