Department of Internal Medicine, Inje University Haeundae Paik Hospital, Busan 48108, South Korea.
Department of Digital Health, Samsung Advanced Institute for Health Science and Technology, Sungkyunkwan University, Seoul 06351, South Korea.
World J Gastroenterol. 2022 Jun 28;28(24):2721-2732. doi: 10.3748/wjg.v28.i24.2721.
Bleeding is one of the major complications after endoscopic submucosal dissection (ESD) in early gastric cancer (EGC) patients. There are limited studies on estimating the bleeding risk after ESD using an artificial intelligence system.
To derivate and verify the performance of the deep learning model and the clinical model for predicting bleeding risk after ESD in EGC patients.
Patients with EGC who underwent ESD between January 2010 and June 2020 at the Samsung Medical Center were enrolled, and post-ESD bleeding (PEB) was investigated retrospectively. We split the entire cohort into a development set (80%) and a validation set (20%). The deep learning and clinical model were built on the development set and tested in the validation set. The performance of the deep learning model and the clinical model were compared using the area under the curve and the stratification of bleeding risk after ESD.
A total of 5629 patients were included, and PEB occurred in 325 patients. The area under the curve for predicting PEB was 0.71 (95% confidence interval: 0.63-0.78) in the deep learning model and 0.70 (95% confidence interval: 0.62-0.77) in the clinical model, without significant difference ( = 0.730). The patients expected to the low- (< 5%), intermediate- (≥ 5%, < 9%), and high-risk (≥ 9%) categories were observed with actual bleeding rate of 2.2%, 3.9%, and 11.6%, respectively, in the deep learning model; 4.0%, 8.8%, and 18.2%, respectively, in the clinical model.
A deep learning model can predict and stratify the bleeding risk after ESD in patients with EGC.
内镜黏膜下剥离术（ESD）后出血是早期胃癌（EGC）患者的主要并发症之一。目前关于使用人工智能系统评估 ESD 后出血风险的研究有限。
旨在开发和验证深度学习模型和临床模型预测 EGC 患者 ESD 后出血风险的性能。
回顾性分析 2010 年 1 月至 2020 年 6 月在三星医疗中心接受 ESD 的 EGC 患者，研究 ESD 后出血（PEB）。我们将整个队列分为开发集（80%）和验证集（20%）。在开发集上构建深度学习模型和临床模型，并在验证集上进行测试。使用曲线下面积和 ESD 后出血风险分层比较深度学习模型和临床模型的性能。
共纳入 5629 例患者，其中 325 例发生 PEB。深度学习模型预测 PEB 的曲线下面积为 0.71（95%置信区间：0.63-0.78），临床模型为 0.70（95%置信区间：0.62-0.77），差异无统计学意义（=0.730）。在深度学习模型中，预计低（<5%）、中（≥5%，<9%）和高（≥9%）风险的患者实际出血率分别为 2.2%、3.9%和 11.6%；在临床模型中，分别为 4.0%、8.8%和 18.2%。
深度学习模型可预测和分层 EGC 患者 ESD 后出血风险。
