目的:上皮下病变(SEL)与各种内镜切除(ER)结果和诊断挑战有关。我们旨在建立一种预测ER相关结果和诊断SEL的工具,并研究内窥镜超声(EUS)的预测价值。
方法:第1阶段(系统开发)是在一个回顾性队列(n=837)中进行的,该队列在8家医院的SEL的ER之前接受了EUS。使用逻辑回归建立了五个关键结果的预测模型。具有令人满意的内部验证性能的模型包括在移动应用系统-SEL内窥镜切除预测器(SELERP)中。在第2阶段,模型在200名患者的前瞻性队列中进行了外部验证。
结果:SELERP是使用EUS特性开发的,其中包括五个关键结果的10个模型:急诊室后溃疡管理,手术时间短,长期住院,药费高,和SELs的诊断。在阶段1中,得出并验证了10个模型(C-统计,0·67-0·99;大范围校准,-0·14-0·10;校准斜率,0·92-1·08)。在第二阶段,推导出的风险预测模型显示出令人信服的歧视(C-统计,0·64-0·73)和校准(大型校准,-0·02-0·05;校准斜率,1·01-1·09)在前瞻性队列中。5种诊断模型的敏感性和特异性分别为68·3%-95·7%和64·1%-83·3%。
结论:我们开发并前瞻性验证了用于预测ER结果和诊断SELs的应用系统,这可以帮助临床决策并促进患者-医生咨询。EUS特征对预测做出了重要贡献。
OBJECTIVE: Subepithelial lesions (SELs) are associated with various endoscopic resection (ER) outcomes and diagnostic challenges. We aimed to establish a tool for predicting ER-related outcomes and diagnosing SELs and to investigate the predictive value of endoscopic ultrasound (EUS).
METHODS: Phase 1 (system development) was performed in a retrospective cohort (n = 837) who underwent EUS before ER for SELs at eight hospitals. Prediction models for five key outcomes were developed using logistic regression. Models with satisfactory internal validation performance were included in a mobile application system, SEL endoscopic resection predictor (SELERP). In Phase 2, the models were externally validated in a prospective cohort of 200 patients.
RESULTS: An SELERP was developed using EUS characteristics, which included 10 models for five key outcomes: post-ER ulcer management, short procedure time, long hospital stay, high medication costs, and diagnosis of SELs. In Phase 1, 10 models were derived and validated (C-statistics, 0.67-0.99; calibration-in-the-large, -0.14-0.10; calibration slopes, 0.92-1.08). In Phase 2, the derived risk prediction models showed convincing discrimination (C-statistics, 0.64-0.73) and calibration (calibration-in-the-large, -0.02-0.05; calibration slopes, 1.01-1.09) in the prospective cohort. The sensitivities and specificities of the five diagnostic models were 68.3-95.7% and 64.1-83.3%, respectively.
CONCLUSIONS: We developed and prospectively validated an application system for the prediction of ER outcomes and diagnosis of SELs, which could aid clinical decision-making and facilitate patient-physician consultation. EUS features significantly contributed to the prediction.
BACKGROUND: Chinese Clinical
Trial Registry, http://www.chictr.org.cn (ChiCTR2000040118).