Aslam Muhammad Fawad, Bano Shehar, Khalid Mariam, Sarfraz Zouina, Sarfraz Azza, Sarfraz Muzna, Robles-Velasco Karla, Felix Miguel, Deane Kitson, Cherrez-Ojeda Ivan
Departments of Medicine.
Department of Research and Publications, Fatima Jinnah Medical University.
Ann Med Surg (Lond). 2023 Feb 1;85(2):80-91. doi: 10.1097/MS9.0000000000000079. eCollection 2023 Feb.
This meta-analysis aims to quantify the effectiveness of artificial intelligence (AI)-supported colonoscopy compared to standard colonoscopy in adenoma detection rate (ADR) differences with the use of computer-aided detection and quality control systems. Moreover, the polyp detection rate (PDR) intergroup differences and withdrawal times will be analyzed.
This study was conducted adhering to PRISMA guidelines. Studies were searched across PubMed, CINAHL, EMBASE, Scopus, Cochrane, and Web of Science. Keywords including the following 'Artificial Intelligence, Polyp, Adenoma, Detection, Rate, Colonoscopy, Colorectal, Colon, Rectal' were used. Odds ratio (OR) applying 95% CI for PDR and ADR were computed. SMD with 95% CI for withdrawal times were computed using RevMan 5.4.1 (Cochrane). The risk of bias was assessed using the RoB 2 tool.
Of 2562 studies identified, 11 trials were included comprising 6856 participants. Of these, 57.4% participants were in the AI group and 42.6% individuals were in in the standard group. ADR was higher in the AI group compared to the standard of care group (OR=1.51, =0.003). PDR favored the intervened group compared to the standard group (OR=1.89, <0.0001). A medium measure of effect was found for withdrawal times (SMD=0.25, <0.0001), therefore with limited practical applications.
AI-supported colonoscopies improve PDR and ADR; however, no noticeable worsening of withdrawal times is noted. Colorectal cancers are highly preventable if diagnosed early-on. With AI-assisted tools in clinical practice, there is a strong potential to reduce the incidence rates of cancers in the near future.
本荟萃分析旨在量化与标准结肠镜检查相比，使用计算机辅助检测和质量控制系统的人工智能（AI）辅助结肠镜检查在腺瘤检出率（ADR）差异方面的有效性。此外，还将分析息肉检出率（PDR）的组间差异和退镜时间。
本研究遵循PRISMA指南进行。在PubMed、CINAHL、EMBASE、Scopus、Cochrane和Web of Science上检索研究。使用了包括“人工智能、息肉、腺瘤、检测、率、结肠镜检查、结直肠癌、结肠、直肠”等关键词。计算了PDR和ADR的比值比（OR）并应用95%置信区间。使用RevMan 5.4.1（Cochrane）计算退镜时间的标准化均数差（SMD）及95%置信区间。使用RoB 2工具评估偏倚风险。
在识别出的2562项研究中，纳入了11项试验，共6856名参与者。其中，57.4%的参与者在AI组，42.6%的个体在标准组。与标准治疗组相比，AI组的ADR更高（OR = 1.51，P = 0.003）。与标准组相比，PDR有利于干预组（OR = 1.89，P < 0.0001）。退镜时间发现有中等程度的效应量（SMD = 0.25，P < 0.0001），因此实际应用有限。
AI辅助结肠镜检查可提高PDR和ADR；然而，未观察到退镜时间有明显延长。如果早期诊断，结直肠癌是高度可预防的。在临床实践中使用AI辅助工具，在不久的将来有很大潜力降低癌症发病率。
