AI辅助胶囊内镜检测克罗恩病溃疡与糜烂的多中心验证研究
该多中心横断面研究纳入259例小肠胶囊内镜检查,验证深度学习模型辅助阅读对克罗恩病溃疡和糜烂的检测效能。AI辅助阅读敏感性90.2%,优于标准阅读的69.6%(P < .001),且中位报告时间仅172秒/例。
要点
- AI辅助阅读敏感性90.2%,显著高于标准阅读的69.6%(P < .001)。
- AI辅助阅读检出600处专家复核病灶中的568处(94.7%)。
- AI辅助阅读中位报告时间172秒/例,可大幅缩短阅片时间。
核心结论
- AI辅助小肠胶囊内镜阅读诊断效能优于标准阅读,且显著缩短阅片时间。
研究设计与样本
- 多中心横断面队列研究,2021至2024年纳入欧洲和美国中心,使用PillCamSB3和Olympus EC-10两种设备,分析259例小肠胶囊内镜检查。
- 以独立复核委员会定义的参考标准,比较AI辅助阅读与标准阅读的效能。
主要发现
- 93例(35.9%)患者检出溃疡和糜烂。
- 标准阅读敏感性69.6%、特异性99.4%、阳性预测值98.5%、阴性预测值85.6%、准确率88.8%。
- AI辅助阅读敏感性90.2%、特异性84.4%、阳性预测值76.1%、阴性预测值94.0%、准确率86.5%。
- AI辅助阅读检出率优于标准阅读(P < .001)。
- AI辅助医师阅读检出专家复核600处病灶中的568处(94.7%),中位报告时间172秒/例。
临床怎么用
- AI辅助阅读可提高小肠胶囊内镜对克罗恩病溃疡和糜烂的检出敏感性,并缩短阅片时间。
- AI辅助阅读特异性略低于标准阅读,阳性预测值较低,需结合临床判断。
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 & AIMS: Small bowel capsule endoscopy (SBCE) is limited by lengthy, variable interpretation. Artificial intelligence (AI) offers a transformative approach, enabling faster and more accurate lesion detection. This multicenter study aimed to validate an AI model for ulcers and erosions across different SBCE devices. METHODS: A multicenter, cross-sectional cohort study was conducted from 2021 to 2024, involving centers in Europe and the United States. Two SBCE devices (PillCamSB3 and Olympus EC-10) were used. The performance of AI-assisted reading, generated by a deep learning model, was compared with standard-of-care (SoC) reading using a reference standard defined by an independent review board. The study utilized 2 SBCE devices (PillCamSB3, Olympus EC-10) and analyzed 259 SBCE exams. The performance of AI-assisted reading generated by the deep learning model was compared with SoC reading against a reference standard defined by an independent review board. RESULTS: Ulcers and erosions were detected in 93 (35.9%) patients. SoC had 69.6% sensitivity, 99.4% specificity, 98.5% positive predictive value, 85.6% negative predictive value, and 88.8% accuracy. AI-assisted reading detected ulcers and erosions with 90.2% sensitivity, 84.4% specificity, 76.1% positive predictive value, 94.0% negative predictive value, and 86.5% accuracy. The detection yield of AI-assisted reading was superior (P < .001) to conventional SoC reading. The AI-assisted physician SBCE reading identified 568 lesions (94.7%) out of 600 identified by expert board review. The median AI-assisted CE reporting time was 172 seconds per exam. CONCLUSIONS: The AI-assisted SBCE reading achieved superior diagnostic performance compared with SoC, with a substantial decrease in reading time.
引用
- Ribeiro Andrade AP, Mascarenhas M, Mendes F, et al. AI-Assisted Capsule Endoscopy for Detection of Ulcers and Erosions in Crohn's Disease: A Multicenter Validation Study. Clin Gastroenterol Hepatol. 2025. PMID: 41076040. doi:10.1016/j.cgh.2025.09.036
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。