文献速递消化内镜消化道肿瘤与早癌

系统综述与荟萃分析:人工智能在食管疾病诊断中的应用

Systematic review with meta-analysis: artificial intelligence in the diagnosis of oesophageal diseases.
PubMed 文献 · Aliment Pharmacol Ther · 2022-01-30

本系统综述与荟萃分析检索了 MEDLINE、EMBASE、EMBASE Classic 和 Cochrane 图书馆,采用双变量随机效应模型汇总人工智能模型与内镜医师对恶性及良性食管疾病的诊断效能。结果显示,人工智能在巴雷特瘤变、食管鳞状细胞癌、异常上皮内乳头状毛细血管袢及基于问卷的胃食管反流病诊断中均表现出较高性能。

要点

  • 人工智能诊断巴雷特瘤变的汇总 AUROC 为 0.90,灵敏度 0.89,特异度 0.86。
  • 人工智能诊断食管鳞状细胞癌的汇总 AUROC 为 0.97,灵敏度 0.95,特异度 0.92。
  • 基于问卷诊断胃食管反流病时,人工智能的汇总 AUROC 为 0.99,灵敏度 0.97,特异度 0.97。

核心结论

  • 人工智能在食管疾病的临床和内镜诊断中表现出较高性能。

研究设计与样本

  • 系统综述与荟萃分析,检索 MEDLINE、EMBASE、EMBASE Classic 和 Cochrane 图书馆,采用双变量随机效应模型汇总人工智能模型与内镜医师的诊断效能,参考标准为肿瘤的组织学以及胃食管反流病的临床和仪器诊断。

主要发现

  • 诊断巴雷特瘤变时,人工智能的汇总 AUROC 为 0.90,灵敏度 0.89,特异度 0.86,阳性似然比 6.50,阴性似然比 0.13,诊断比值比 50.53。
  • 人工智能模型诊断巴雷特瘤变的性能与内镜医师相当(P = 0.35)。
  • 诊断食管鳞状细胞癌时,人工智能的汇总 AUROC 为 0.97,灵敏度 0.95,特异度 0.92,阳性似然比 12.65,阴性似然比 0.05,诊断比值比 258.36。
  • 在诊断食管鳞状细胞癌方面,人工智能表现优于内镜医师,但差异无统计学意义。
  • 检测异常上皮内乳头状毛细血管袢时,人工智能的汇总 AUROC 为 0.98,灵敏度 0.94,特异度 0.94,阳性似然比 14.75,阴性似然比 0.07,诊断比值比 225.83。

局限性

  • 原文未报告局限性。

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: Artificial intelligence (AI) has recently been applied to endoscopy and questionnaires for the evaluation of oesophageal diseases (ODs). AIM: We performed a systematic review with meta-analysis to evaluate the performance of AI in the diagnosis of malignant and benign OD. METHODS: We searched MEDLINE, EMBASE, EMBASE Classic and the Cochrane Library. A bivariate random-effect model was used to calculate pooled diagnostic efficacy of AI models and endoscopists. The reference tests were histology for neoplasms and the clinical and instrumental diagnosis for gastro-oesophageal reflux disease (GERD). The pooled area under the summary receiver operating characteristic (AUROC), sensitivity, specificity, positive and negative likelihood ratio (PLR and NLR) and diagnostic odds ratio (DOR) were estimated. RESULTS: For the diagnosis of Barrett's neoplasia, AI had AUROC of 0.90, sensitivity 0.89, specificity 0.86, PLR 6.50, NLR 0.13 and DOR 50.53. AI models' performance was comparable with that of endoscopists (P = 0.35). For the diagnosis of oesophageal squamous cell carcinoma, the AUROC, sensitivity, specificity, PLR, NLR and DOR were 0.97, 0.95, 0.92, 12.65, 0.05 and DOR 258.36, respectively. In this task, AI performed better than endoscopists although without statistically significant differences. In the detection of abnormal intrapapillary capillary loops, the performance of AI was: AUROC 0.98, sensitivity 0.94, specificity 0.94, PLR 14.75, NLR 0.07 and DOR 225.83. For the diagnosis of GERD based on questionnaires, the AUROC, sensitivity, specificity, PLR, NLR and DOR were 0.99, 0.97, 0.97, 38.26, 0.03 and 1159.6, respectively. CONCLUSIONS: AI demonstrated high performance in the clinical and endoscopic diagnosis of OD.

来源:Aliment Pharmacol Ther,查看原文。版权归原作者所有。

引用

  1. Visaggi P, Barberio B, Gregori D, et al. Systematic review with meta-analysis: artificial intelligence in the diagnosis of oesophageal diseases. Aliment Pharmacol Ther. 2022. PMID: 35098562. doi:10.1111/apt.16778

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。