Department of Medical Imaging, Jinling Hospital, Medical School of Nanjing University, Nanjing, 210002, Jiangsu, China.
Division of Cardiovascular Imaging, Department of Radiology and Radiological Science, Medical University of South Carolina, Ashley River Tower, MSC 226, 25 Courtenay Dr, Charleston, SC, 29425, USA.
Eur Radiol. 2021 Sep;31(9):6592-6604. doi: 10.1007/s00330-021-07922-w. Epub 2021 Apr 17.
To investigate the feasibility and prognostic implications of coronary CT angiography (CCTA) derived fractional flow reserve (FFR) in patients who have undergone stents implantation.
Firstly, the feasibility of FFR in stented vessels was validated. The diagnostic performance of FFR in identifying hemodynamically in-stent restenosis (ISR) in 33 patients with invasive FFR ≤ 0.88 as reference standard, intra-group correlation coefficient (ICC) between FFR and FFR was calculated. Secondly, prognostic value was assessed with 115 patients with serial CCTA scans after PCI. Stent characteristics (location, diameter, length, etc.), CCTA measurements (minimum lumen diameter [MLD], minimum lumen area [MLA], ISR), and FFR measurements (FFR, ΔFFR, ΔFFR/stent length) both at baseline and follow-up were recorded. Longitudinal analysis included changes of MLD, MLA, ISR, and FFR. The primary endpoint was major adverse cardiovascular events (MACE).
Per-patient accuracy of FFR was 0.85 in identifying hemodynamically ISR. FFR had a good correlation with FFR (ICC = 0.84). 15.7% (18/115) developed MACE during 25 months since follow-up CCTA. Lasso regression identified age and follow-up ΔFFR/length as candidate variables. In the Cox proportional hazards model, age (hazard ratio [HR], 1.102 [95% CI, 1.032-1.177]; p = 0.004) and follow-up ΔFFR/length (HR, 1.014 [95% CI, 1.006-1.023]; p = 0.001) were independently associated with MACE (c-index = 0.856). Time-dependent ROC analysis showed AUC was 0.787 (95% CI, 0.594-0.980) at 25 months to predict adverse outcome. After bootstrap validation with 1000 resamplings, the bias-corrected c-index was 0.846.
Noninvasive ML-based FFR is feasible in patients following stents implantation and shows prognostic value in predicting adverse events after stents implantation in low-moderate risk patients.
• Machine-learning-based FFR is feasible to evaluate the functional significance of in-stent restenosis in patients with stent implantation. • Follow-up △FFR along with the stent length might have prognostic implication in patients with stent implantation and low-to-moderate risk after 2 years follow-up. The prognostic role of FFR in patients with moderate-to-high or high risk needs to be further studied. • FFR might refine the clinical pathway of patients with stent implantation to invasive catheterization.
探讨在已植入支架的患者中，冠状动脉 CT 血管造影（CCTA）衍生的血流储备分数（FFR）的可行性及其预后意义。
首先，验证了 FFR 在支架血管中的可行性。以 33 例有创 FFR≤0.88 为参考标准的患者的血流动力学支架内再狭窄（ISR）作为参考标准，计算 FFR 与 FFR 之间的组内相关系数（ICC）。其次，对 115 例接受经皮冠状动脉介入治疗（PCI）后行连续 CCTA 扫描的患者进行预后评估。记录支架特征（位置、直径、长度等）、CCTA 测量值（最小管腔直径[MLD]、最小管腔面积[MLA]、ISR）和 FFR 测量值（FFR、ΔFFR、ΔFFR/支架长度）在基线和随访时的变化。纵向分析包括 MLD、MLA、ISR 和 FFR 的变化。主要终点是主要不良心血管事件（MACE）。
每位患者识别血流动力学 ISR 的 FFR 准确率为 0.85。FFR 与 FFR 相关性良好（ICC=0.84）。在随访 CCTA 后 25 个月，15.7%（18/115）发生 MACE。Lasso 回归确定年龄和随访ΔFFR/长度为候选变量。在 Cox 比例风险模型中，年龄（风险比[HR]，1.102[95%可信区间，1.032-1.177]；p=0.004）和随访ΔFFR/长度（HR，1.014[95%可信区间，1.006-1.023]；p=0.001）与 MACE 独立相关（C 指数=0.856）。时间依赖性 ROC 分析显示，25 个月时预测不良结局的 AUC 为 0.787（95%可信区间，0.594-0.980）。通过 1000 次重采样的 bootstrap 验证，校正后的偏倚 C 指数为 0.846。
基于机器学习的 ML 基础 FFR 可用于评估支架植入后患者支架内再狭窄的功能意义，并可预测支架植入后低-中度风险患者的不良事件。
基于机器学习的 FFR 可用于评估支架植入患者支架内再狭窄的功能意义。
支架植入患者在 2 年随访后，随访 ΔFFR 与支架长度可能具有预后意义，中-高危或高危患者的 FFR 预后作用需要进一步研究。
FFR 可能使支架植入患者的临床路径更倾向于有创导管检查。
