人工智能辅助检测上消化道病变的准确性:系统评价与荟萃分析
该荟萃分析纳入23项研究共969318张图像,评估人工智能检测胃、巴雷特食管、鳞状食管肿瘤性病变及幽门螺杆菌状态的诊断准确性,AUC分别为.96、.96、.88和.92,且人工智能在胃、巴雷特食管及幽门螺杆菌检测中优于内镜医师,但多数研究基于回顾性图像需前瞻性验证。
要点
- 人工智能检测胃和巴雷特食管肿瘤性病变的AUC均为.96,鳞状食管为.88,幽门螺杆菌状态为.92。
- 窄带成像人工智能检测鳞状食管肿瘤性病变优于白光成像(.92 vs .83,P < .001)。
- 人工智能检测胃、巴雷特食管肿瘤性病变及幽门螺杆菌状态均优于内镜医师(P < .001)。
核心结论
- 人工智能检测上消化道肿瘤性病变和幽门螺杆菌感染状态具有准确性。
- 多数研究基于对选定图像的回顾性回顾,需在前瞻性试验中进一步验证。
研究设计与样本
- 系统评价与荟萃分析,检索Embase、PubMed、Medline、Web of Science和Cochrane数据库。
- 纳入23项研究,共969318张图像。
- 使用诊断准确性研究质量评估工具评估研究质量,采用随机效应模型的双变量荟萃分析,绘制分层汇总受试者工作特征曲线,以曲线下面积(AUC)确定诊断准确性。
主要发现
- 人工智能检测胃肿瘤性病变的AUC为.96(95%CI,.94-.99)。
- 人工智能检测巴雷特食管肿瘤性病变的AUC为.96(95%CI,.93-.99)。
- 人工智能检测鳞状食管肿瘤性病变的AUC为.88(95%CI,.82-.96)。
- 人工智能检测幽门螺杆菌状态的AUC为.92(95%CI,.88-.97)。
- 人工智能使用窄带成像检测鳞状食管肿瘤性病变优于白光成像(.92 vs .83,P < .001)。
关键数值与推荐
- 人工智能检测胃肿瘤性病变优于内镜医师(AUC,.98 vs .87;P < .001)。
- 人工智能检测巴雷特食管肿瘤性病变优于内镜医师(AUC,.96 vs .82;P < .001)。
- 人工智能检测幽门螺杆菌状态优于内镜医师(AUC,.90 vs .82;P < .001)。
临床怎么用
- 原文未据此给出推荐。
局限性
- 多数研究基于对选定图像的回顾性回顾,需在前瞻性试验中进一步验证。
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
BACKGROUND AND AIMS: Artificial intelligence (AI)-assisted detection is increasingly used in upper endoscopy. We performed a meta-analysis to determine the diagnostic accuracy of AI on detection of gastric and esophageal neoplastic lesions and Helicobacter pylori (HP) status. METHODS: We searched Embase, PubMed, Medline, Web of Science, and Cochrane databases for studies on AI detection of gastric or esophageal neoplastic lesions and HP status. After assessing study quality using the Quality Assessment of Diagnostic Accuracy Studies tool, a bivariate meta-analysis following a random-effects model was used to summarize the data and plot hierarchical summary receiver-operating characteristic curves. The diagnostic accuracy was determined by the area under the hierarchical summary receiver-operating characteristic curve (AUC). RESULTS: Twenty-three studies including 969,318 images were included. The AUC of AI detection of neoplastic lesions in the stomach, Barrett's esophagus, and squamous esophagus and HP status were .96 (95% confidence interval [CI], .94-.99), .96 (95% CI, .93-.99), .88 (95% CI, .82-.96), and .92 (95% CI, .88-.97), respectively. AI using narrow-band imaging was superior to white-light imaging on detection of neoplastic lesions in squamous esophagus (.92 vs .83, P < .001). The performance of AI was superior to endoscopists in the detection of neoplastic lesions in the stomach (AUC, .98 vs .87; P < .001), Barrett's esophagus (AUC, .96 vs .82; P < .001), and HP status (AUC, .90 vs .82; P < .001). CONCLUSIONS: AI is accurate in the detection of upper GI neoplastic lesions and HP infection status. However, most studies were based on retrospective reviews of selected images, which requires further validation in prospective trials.
引用
- Lui TKL, Tsui VWM, Leung WK, et al. Accuracy of artificial intelligence-assisted detection of upper GI lesions: a systematic review and meta-analysis. Gastrointest Endosc. 2020. PMID: 32562608. doi:10.1016/j.gie.2020.06.034
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。