Objective: To investigate the impact of the deep-learning-based CT fractional flow reserve (CT-FFR) on clinical decision-making and long-term prognosis in patients with obstructive coronary heart disease. Methods: In this single-center retrospective cohort study, consecutive patients with obstructive coronary heart disease (with at least one stenosis≥50%) on their first coronary computed tomography angiography (CCTA) in Beijing Anzhen Hospital from February 2017 to July 2018 were included. Baseline clinical and CT characteristics were collected. Deep-learning-based CT-FFR and Leiden CCTA risk score were calculated. All patients enrolled were followed up for at least 5 years. The study endpoint was major adverse cardiovascular events (MACE), defined as the composite of cardiac death, nonfatal myocardial infarction, unstable angina requiring hospitalization, and unplanned revascularization. Receiver operating characteristic (ROC) curves were drawn to define the optimal cut-off point of the Leiden score in predicting the 5-year MACE, and survival analysis and Cox regression were performed to explore the related factors of MACE. Results: A total of 622 patients, aged 61 (54, 66) years, with 407 (65.4%) males were included. Diagnostic coronary angiography was performed in 78 patients after their baseline CCTA, with 34 (43.6%) patients had CT-FFR>0.80. During a follow-up time of 2 181 (2 093, 2 355) days, 155 patients (24.9%) suffered from MACE. ROC derived optimal cut-off point of Leiden score for predicting MACE was 15.48. Survival analysis found that male patients, Leiden risk score>15 and CT-FFR≤0.80 had worse prognosis. Multivariate Cox regression analysis identified CT-FFR≤0.80 as an robust and independent predictor of MACE (HR=4.98, 95%CI 3.15-7.86, P<0.001). Conclusion: Deep-learning-based CT-FFR aids in clinical decision-making and the evaluation of long-term prognosis in patients with obstructive coronary heart disease.
目的： 探讨冠状动脉CT血管成像（CCTA）衍生的血流储备分数（CT-FFR）在梗阻性冠心病患者临床决策和远期预后中的应用价值。 方法： 本研究为单中心回顾性队列研究。连续性入选2017年2月至2018年7月于北京安贞医院首次行CCTA检查且诊断为梗阻性冠心病的患者（至少1支冠状动脉狭窄≥50%）。收集患者的基线临床资料和CCTA影像。采用深度学习算法测算CT-FFR，并计算基于CCTA的Leiden风险评分。随访至少5年，研究终点为主要心血管不良事件（MACE），包括心原性死亡、非致死性心肌梗死、不稳定性心绞痛住院治疗、非计划血运重建。绘制受试者工作特征（ROC）曲线探索Leiden风险评分预测5年MACE发生的最佳截断值，采用Kaplan-Meier法绘制核心观察指标不同水平下的生存曲线，并采用Cox回归分析探讨MACE的独立预测因素。 结果： 共纳入622例患者，年龄61（54，66）岁，男性407例（65.4%）。CCTA检查后有78例患者接受了诊断性冠状动脉造影检查，其中34例（43.6%）CT-FFR阴性。随访时间为2 181（2 093，2 355）d，随访期间155例（24.9%）患者发生了MACE。ROC曲线显示Leiden风险评分的最佳截断值为15.48。Kaplan-Meier生存分析显示，Leiden风险评分>15和CT-FFR≤0.80的无MACE生存率更低（Plog-rank均<0.05）。多因素Cox回归分析显示，CT-FFR≤0.80是MACE的独立预测因素（HR=4.98，95%CI 3.15~7.86，P<0.001）。 结论： 基于深度学习的CT-FFR有助于梗阻性冠心病患者的临床决策和远期预后评判。.