Department of Cardiology, Angiology and Pneumology, University of Heidelberg, Im Neuenheimer Feld 410, 69120, Heidelberg, Germany.
First Department of Medicine-Cardiology, University Medical Centre Mannheim, Mannheim, Germany.
BMC Cardiovasc Disord. 2022 Feb 5;22(1):34. doi: 10.1186/s12872-022-02467-2.
Machine-Learning Computed Tomography-Based Fractional Flow Reserve (CT-FFR) is a novel tool for the assessment of hemodynamic relevance of coronary artery stenoses. We examined the diagnostic performance of CT-FFR compared to stress perfusion cardiovascular magnetic resonance (CMR) and tested if there is an additional value of CT-FFR over coronary computed tomography angiography (cCTA).
Our retrospective analysis included 269 vessels in 141 patients (mean age 67 ± 9 years, 78% males) who underwent clinically indicated cCTA and subsequent stress perfusion CMR within a period of 2 months. CT-FFR values were calculated from standard cCTA.
CT-FFR revealed no hemodynamic significance in 79% of the patients having ≥ 50% stenosis in cCTA. Chi values for the statistical relationship between CT-FFR and stress perfusion CMR was significant (p < 0.0001). CT-FFR and cCTA (≥ 70% stenosis) provided a per patient sensitivity of 88% (95%CI 64-99%) and 59% (95%CI 33-82%); specificity of 90% (95%CI 84-95%) and 85% (95%CI 78-91%); positive predictive value of 56% (95%CI 42-69%) and 36% (95%CI 24-50%); negative predictive value of 98% (95%CI 94-100%) and 94% (95%CI 90-96%); accuracy of 90% (95%CI 84-94%) and 82% (95%CI 75-88%) when compared to stress perfusion CMR. The accuracy of cCTA (≥ 50% stenosis) was 19% (95%CI 13-27%). The AUCs were 0.89 for CT-FFR and 0.74 for cCTA (≥ 70% stenosis) and therefore significantly different (p < 0.05).
CT-FFR compared to stress perfusion CMR as the reference standard shows high diagnostic power in the identification of patients with hemodynamically significant coronary artery stenosis. This could support the role of cCTA as gatekeeper for further downstream testing and may reduce the number of patients undergoing unnecessary invasive workup.
基于机器学习的计算机断层扫描（CT）血流储备分数（CT-FFR）是一种评估冠状动脉狭窄血流动力学意义的新工具。我们比较了 CT-FFR 与压力灌注心血管磁共振（CMR）的诊断性能，并检验了 CT-FFR 是否比冠状动脉计算机断层扫描血管造影（cCTA）具有额外的价值。
我们的回顾性分析纳入了 269 支血管，涉及 141 例患者（平均年龄 67±9 岁，78%为男性），这些患者在 2 个月的时间内接受了临床指征明确的 cCTA 检查和随后的压力灌注 CMR 检查。CT-FFR 值从标准 cCTA 中计算得出。
在 cCTA 存在≥50%狭窄的患者中，79%的患者 CT-FFR 显示无血流动力学意义。CT-FFR 与压力灌注 CMR 之间的统计学关系的 Chi 值具有显著意义（p<0.0001）。CT-FFR 和 cCTA（≥70%狭窄）在每位患者中的灵敏度分别为 88%（95%CI 64-99%）和 59%（95%CI 33-82%）；特异性分别为 90%（95%CI 84-95%）和 85%（95%CI 78-91%）；阳性预测值分别为 56%（95%CI 42-69%）和 36%（95%CI 24-50%）；阴性预测值分别为 98%（95%CI 94-100%）和 94%（95%CI 90-96%）；与压力灌注 CMR 相比，准确性分别为 90%（95%CI 84-94%）和 82%（95%CI 75-88%）。cCTA（≥50%狭窄）的准确性为 19%（95%CI 13-27%）。CT-FFR 的 AUC 为 0.89，cCTA（≥70%狭窄）为 0.74，因此差异具有统计学意义（p<0.05）。
与压力灌注 CMR 作为参考标准相比，CT-FFR 在识别具有血流动力学意义的冠状动脉狭窄患者方面具有较高的诊断能力。这可以支持 cCTA 作为进一步下游检查的“守门员”的作用，并可能减少不必要的有创检查的患者数量。
