Department of Gastroenterology, Beijing Friendship Hospital, Capital Medical University, Beijing, China.
National Clinical Research Center for Digestive Diseases, Beijing, China.
J Dig Dis. 2021 Jun;22(6):318-328. doi: 10.1111/1751-2980.12992.
To investigate systematically previous studies on the accuracy of artificial intelligence (AI)-assisted diagnostic models in detecting esophageal neoplasms on endoscopic images so as to provide scientific evidence for the effectiveness of these models.
A literature search was conducted on the PubMed, EMBASE and Cochrane Library databases for studies on the AI-assisted detection of esophageal neoplasms on endoscopic images published up to December 2020. A bivariate mixed-effects regression model was used to calculate the pooled diagnostic efficacy of AI-assisted system. Subgroup analyses and meta-regression analyses were performed to explore the sources of heterogeneity. The effectiveness of AI-assisted models was also compared with that of the endoscopists.
Sixteen studies were included in the systematic review and meta-analysis. The pooled sensitivity, specificity, positive and negative likelihood ratios, diagnostic odds ratio and area under the summary receiver operating characteristic curve regarding AI-assisted detection of esophageal neoplasms were 94% (95% confidence interval [CI] 92%-96%), 85% (95% CI 73%-92%), 6.40 (95% CI 3.38-12.11), 0.06 (95% CI 0.04-0.10), 98.88 (95% CI 39.45-247.87) and 0.97 (95% CI 0.95-0.98), respectively. AI-based models performed better than endoscopists in terms of the pooled sensitivity (94% [95% CI 84%-98%] vs 82% [95% CI 77%-86%, P < 0.01).
The use of AI results in increased accuracy in detecting early esophageal cancer. However, most of the included studies have a retrospective study design, thus further validation with prospective trials is required.
系统地调查以前关于人工智能（AI）辅助诊断模型在检测内镜图像中食管肿瘤准确性的研究，为这些模型的有效性提供科学依据。
检索 PubMed、EMBASE 和 Cochrane Library 数据库，查找截至 2020 年 12 月发表的关于 AI 辅助内镜图像中食管肿瘤检测的研究。使用双变量混合效应回归模型计算 AI 辅助系统的汇总诊断效能。进行亚组分析和 meta 回归分析，以探讨异质性的来源。还比较了 AI 辅助模型与内镜医生的效能。
系统评价和 meta 分析共纳入 16 项研究。AI 辅助检测食管肿瘤的汇总敏感性、特异性、阳性似然比、阴性似然比、诊断优势比和汇总受试者工作特征曲线下面积分别为 94%（95%置信区间 [CI] 92%-96%）、85%（95% CI 73%-92%）、6.40（95% CI 3.38-12.11）、0.06（95% CI 0.04-0.10）、98.88（95% CI 39.45-247.87）和 0.97（95% CI 0.95-0.98）。在汇总敏感性方面，AI 模型优于内镜医生（94%[95% CI 84%-98%]比 82%[95% CI 77%-86%，P<0.01]）。
使用 AI 可提高早期食管癌的检测准确性。然而，纳入的大多数研究为回顾性研究设计，因此需要前瞻性试验进一步验证。
