预测缺血性冠状动脉狭窄的最佳指标:供血心肌体积、机器学习FFRCT还是高危斑块特征?
本回顾性研究纳入180例患者208处病变,比较基于机器学习的FFRCT、供血心肌体积及高危斑块特征对冠状动脉狭窄血流动力学意义的预测效能,以FFRICA≤0.8为参考标准。FFRCT+Vratio/MLD的AUC显著优于单独FFRCT(0.935对0.873,p<0.001);高危斑块特征在功能显著与不显著组间无差异;对于FFRCT值0.7-0.8的灰区病变,Vratio/MLD联合FFRCT诊断准确率最佳(86.5%,180/208)。
要点
- FFRCT联合Vratio/MLD的AUC为0.935,显著优于单独FFRCT的0.873(p<0.001)。
- 高危斑块特征在功能显著与不显著组间无差异,不能正确识别血流动力学显著狭窄。
- 对FFRCT值0.7-0.8的灰区病变,Vratio/MLD联合FFRCT诊断准确率最佳(86.5%,180/208)。
核心结论
- 基于机器学习的FFRCT模拟和Vratio/MLD均较CCTA直径狭窄及高危斑块特征提供增量价值;对于模拟FFRCT值0.7-0.8的病变,Vratio/MLD比机器学习FFRCT更准确。
研究设计与样本
- 回顾性纳入2周内同时接受CCTA和FFRICA测量的患者180例、208处病变;记录机器学习FFRCT、供血心肌体积(Vsub)、供血心肌体积占总心肌体积百分比(Vratio)、高危斑块特征、最小管腔直径(MLD)、最小管腔面积(MLA)等参数;以FFRICA≤0.8为功能显著参考标准。
诊断标准与关键数值
- 以FFRICA≤0.8判定病变为功能显著;FFRCT+Vratio/MLD的AUC为0.935,单独FFRCT的AUC为0.873(p<0.001);Vratio/MLD联合FFRCT对FFRCT值0.7-0.8灰区病变的诊断准确率为86.5%(180/208)。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
OBJECTIVES: The present study aimed to compare the diagnostic performance of a machine learning (ML)-based FFRCT algorithm, quantified subtended myocardial volume, and high-risk plaque features for predicting if a coronary stenosis is hemodynamically significant, with reference to FFRICA.
METHODS: Patients who underwent both CCTA and FFRICA measurement within 2 weeks were retrospectively included. ML-based FFRCT, volume of subtended myocardium (Vsub), percentage of subtended myocardium volume versus total myocardium volume (Vratio), high-risk plaque features, minimal lumen diameter (MLD), and minimal lumen area (MLA) along with other parameters were recorded. Lesions with FFRICA ≤ 0.8 were considered to be functionally significant.
RESULTS: One hundred eighty patients with 208 lesions were included. The lesion length (LL), diameter stenosis, area stenosis, plaque burden, Vsub, Vratio, Vratio/MLD, Vratio/MLA, and LL/MLD4 were all significantly longer or larger in the group of FFRICA ≤ 0.8 while smaller minimal lumen area, MLD, and FFRCT value were noted. The AUC of FFRCT + Vratio/MLD was significantly better than that of FFRCT alone (0.935 versus 0.873, p < 0.001). High-risk plaque features failed to show difference between functionally significant and insignificant groups. Vratio/MLD-complemented ML-based FFRCT for "gray zone" lesions with FFRCT value ranged from 0.7 to 0.8 and the combined use of these two parameters yielded the best diagnostic performance (86.5%, 180/208).
CONCLUSIONS: ML-based FFRCT simulation and Vratio/MLD both provide incremental value over CCTA-derived diameter stenosis and high-risk plaque features for predicting hemodynamically significant lesions. Vratio/MLD is more accurate than ML-based FFRCT for lesions with simulated FFRCT value from 0.7 to 0.8.
KEY POINTS: • Machine learning-based FFR CT and subtended myocardium volume both performed well for predicting hemodynamically significant coronary stenosis. • Subtended myocardium volume was more accurate than machine learning-based FFR CT for "gray zone" lesions with simulated FFR value from 0.7 to 0.8. • CT-derived high-risk plaque features failed to correctly identify hemodynamically significant stenosis.
引用
- Yu M, Lu Z, Shen C, et al. The best predictor of ischemic coronary stenosis: subtended myocardial volume, machine learning-based FFRCT, or high-risk plaque features? Eur Radiol. 2019. PMID: 30903334. doi:10.1007/s00330-019-06139-2
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。