Lossnitzer Dirk, Chandra Leonard, Rutsch Marlon, Becher Tobias, Overhoff Daniel, Janssen Sonja, Weiss Christel, Borggrefe Martin, Akin Ibrahim, Pfleger Stefan, Baumann Stefan
First Department of Medicine-Cardiology, University Medical Centre Mannheim, Mannheim, Germany, DZHK (German Centre for Cardiovascular Research), partner site Heidelberg/Mannheim, Mannheim, Germany and ECAS (European Center for Angioscience), Faculty of Medicine Mannheim, Heidelberg University, 68167 Mannheim, Germany.
Institute of Clinical Radiology and Nuclear Medicine, University Medical Center Mannheim, Faculty of Medicine Mannheim, Heidelberg University, 68167 Mannheim, Germany.
J Clin Med. 2020 Mar 3;9(3):676. doi: 10.3390/jcm9030676.
Machine-learning-based computed-tomography-derived fractional flow reserve (CT-FFR) obtains a hemodynamic index in coronary arteries. We examined whether it could reduce the number of invasive coronary angiographies (ICA) showing no obstructive lesions. We further compared CT-FFR-derived measurements to clinical and CT-derived scores. We retrospectively selected 88 patients (63 ± 11years, 74% male) with chronic coronary syndrome (CCS) who underwent clinically indicated coronary computed tomography angiography (cCTA) and ICA. cCTA image data were processed with an on-site prototype CT-FFR software. CT-FFR revealed an index of >0.80 in coronary vessels of 48 (55%) patients. This finding was corroborated in 45 (94%) patients by ICA, yet three (6%) received revascularization. In patients with an index ≤ 0.80, three (8%) of 40 were identified as false positive. A total of 48 (55%) patients could have been retained from ICA. CT-FFR (AUC = 0.96, ≤ 0.0001) demonstrated a higher diagnostic accuracy compared to the pretest probability or CT-derived scores and showed an excellent sensitivity (93%), specificity (94%), positive predictive value (PPV; 93%) and negative predictive value (NPV; 94%). CT-FFR could be beneficial for clinical practice, as it may identify patients with CAD without hemodynamical significant stenosis, and may thus reduce the rate of ICA without necessity for coronary intervention.
基于机器学习的计算机断层扫描衍生的血流储备分数（CT-FFR）可获取冠状动脉的血流动力学指标。我们研究了它是否能减少显示无阻塞性病变的有创冠状动脉造影（ICA）的数量。我们还将CT-FFR衍生的测量结果与临床和CT衍生的评分进行了比较。我们回顾性选择了88例患有慢性冠状动脉综合征（CCS）的患者（63±11岁，74%为男性），这些患者接受了临床指征下的冠状动脉计算机断层扫描血管造影（cCTA）和ICA。cCTA图像数据使用现场原型CT-FFR软件进行处理。CT-FFR显示48例（55%）患者的冠状动脉血管指数>0.80。ICA在45例（94%）患者中证实了这一发现，但有3例（6%）接受了血运重建。在指数≤0.80的患者中，40例中有3例（8%）被确定为假阳性。共有48例（55%）患者本可避免接受ICA。与预检概率或CT衍生评分相比，CT-FFR（AUC = 0.96，P≤0.0001）显示出更高的诊断准确性，并且具有出色的敏感性（93%）、特异性（94%）、阳性预测值（PPV；93%）和阴性预测值（NPV；94%）。CT-FFR可能对临床实践有益，因为它可以识别没有血流动力学显著狭窄的冠心病患者，从而可能降低不必要进行冠状动脉干预的ICA发生率。
