Yang Linda S, Perry Evelyn, Shan Leonard, Wilding Helen, Connell William, Thompson Alexander J, Taylor Andrew C F, Desmond Paul V, Holt Bronte A
Department of Gastroenterology, St. Vincent's Hospital and the University of Melbourne, Fitzroy, Victoria, Australia.
Department of Surgery, Faculty of Medicine, Dentistry and Health Sciences, the University of Melbourne, Fitzroy, Victoria, Australia.
Endosc Int Open. 2022 Jul 15;10(7):E1004-E1013. doi: 10.1055/a-1846-0642. eCollection 2022 Jul.
Artificial intelligence (AI) technology is being evaluated for its potential to improve colonoscopic assessment of inflammatory bowel disease (IBD), particularly with computer-aided image classifiers. This review evaluates the clinical application and diagnostic test accuracy (DTA) of AI algorithms in colonoscopy for IBD. A systematic review was performed on studies evaluating AI in colonoscopy of adult patients with IBD. MEDLINE, Embase, Emcare, PsycINFO, CINAHL, Cochrane Library and Clinicaltrials.gov databases were searched on 28 April 2021 for English language articles published between January 1, 2000 and April 28, 2021. Risk of bias and applicability were assessed with the Quality Assessment of Diagnostic Accuracy Studies-2 tool. Diagnostic accuracy was presented as median (interquartile range). Of 1029 records screened, nine studies with 7813 patients were included for review. AI was used to predict endoscopic and histologic disease activity in ulcerative colitis, and differentiation of Crohn's disease from Behcet's disease and intestinal tuberculosis. DTA of AI algorithms ranged between 52-91 %. The sensitivity and specificity for AI algorithms predicting endoscopic severity of disease were 78 % (range 72-83, interquartile range 5.5) and 91 % (range 86-96, interquartile range 5), respectively. AI has been primarily used to assess disease activity in ulcerative colitis. The diagnostic performance is promising and suggests potential for other clinical application of AI in IBD colonoscopy such as dysplasia detection. However, current evidence is limited by retrospective data and models trained on still images only. Future prospective multicenter studies with full-motion videos are needed to replicate the real-world clinical setting.
人工智能（AI）技术正在接受评估，以确定其改善炎症性肠病（IBD）结肠镜评估的潜力，特别是通过计算机辅助图像分类器。本综述评估了AI算法在IBD结肠镜检查中的临床应用和诊断测试准确性（DTA）。对评估成年IBD患者结肠镜检查中AI的研究进行了系统综述。于2021年4月28日在MEDLINE、Embase、Emcare、PsycINFO、CINAHL、Cochrane图书馆和Clinicaltrials.gov数据库中检索了2000年1月1日至2021年4月28日发表的英文文章。使用诊断准确性研究质量评估-2工具评估偏倚风险和适用性。诊断准确性以中位数（四分位间距）表示。在筛选的1029条记录中，纳入了9项研究，共78仁名患者进行综述。AI被用于预测溃疡性结肠炎的内镜和组织学疾病活动，以及区分克罗恩病与白塞病和肠结核。AI算法的DTA在52%-91%之间。AI算法预测疾病内镜严重程度的敏感性和特异性分别为78%（范围72%-83%，四分位间距5.5）和91%（范围86%-96%，四分位间距5）。AI主要用于评估溃疡性结肠炎的疾病活动。其诊断性能很有前景，表明AI在IBD结肠镜检查的其他临床应用（如发育异常检测）中具有潜力。然而，目前的证据受到回顾性数据和仅基于静态图像训练的模型的限制。未来需要进行全动态视频的前瞻性多中心研究，以复制真实世界的临床环境。
