Department of Diagnostic Radiology, Jinling Hospital, Medical School of Nanjing University, Nanjing, 210002, Jiangsu, China.
Department of Medical Imaging, Affiliated Hospital of Jiangnan University, Wuxi, 214041, Jiangsu, China.
Eur Radiol. 2022 Aug;32(8):5179-5188. doi: 10.1007/s00330-022-08604-x. Epub 2022 Feb 17.
To explore downstream management and outcomes of machine learning (ML)-based CT derived fractional flow reserve (FFR) strategy compared with an anatomical coronary computed tomography angiography (CCTA) alone assessment in participants with intermediate coronary artery stenosis.
In this prospective study conducted from April 2018 to March 2019, participants were assigned to either the CCTA or FFR group. The primary endpoint was the rate of invasive coronary angiography (ICA) that demonstrated non-obstructive disease at 90 days. Secondary endpoints included coronary revascularization and major adverse cardiovascular events (MACE) at 1-year follow-up.
In total, 567 participants were allocated to the CCTA group and 566 to the FFR group. At 90 days, the rate of ICA without obstructive disease was higher in the CCTA group (33.3%, 39/117) than that (19.8%, 19/96) in the FFR group (risk difference [RD] = 13.5%, 95% confidence interval [CI]: 8.4%, 18.6%; p = 0.03). The ICA referral rate was higher in the CCTA group (27.5%, 156/567) than in the FFR group (20.3%, 115/566) (RD = 7.2%, 95% CI: 2.3%, 12.1%; p = 0.003). The revascularization-to-ICA ratio was lower in the CCTA group than that in the FFR group (RD = 19.8%, 95% CI: 14.1%, 25.5%, p = 0.002). MACE was more common in the CCTA group than that in the FFR group at 1 year (HR: 1.73; 95% CI: 1.01, 2.95; p = 0.04).
In patients with intermediate stenosis, the FFR strategy appears to be associated with a lower rate of referral for ICA, ICA without obstructive disease, and 1-year MACE when compared to the anatomical CCTA alone strategy.
• In stable patients with intermediate stenosis, ML-based FFR strategy was associated with a lower referral ICA rate, a lower normalcy rate of ICA, and higher revascularization-to-ICA ratio than the CCTA strategy. • Compared with the CCTA strategy, ML-based FFRshows superior outcome prediction value which appears to be associated with a lower rate of 1-year MACE. • ML-based FFR strategy as a non-invasive "one-stop-shop" modality may be the potential to change diagnostic workflows in patients with suspected coronary artery disease.
探讨机器学习（ML）衍生的 CT 血流储备分数（FFR）策略与单独基于解剖学的冠状动脉计算机断层血管造影（CCTA）评估在中度冠状动脉狭窄患者中的下游管理和结果。
本前瞻性研究于 2018 年 4 月至 2019 年 3 月进行，参与者被分配到 CCTA 组或 FFR 组。主要终点是 90 天时显示无阻塞性疾病的侵入性冠状动脉造影（ICA）的比率。次要终点包括 1 年随访时的冠状动脉血运重建和主要不良心血管事件（MACE）。
共 567 名参与者被分配到 CCTA 组，566 名参与者被分配到 FFR 组。90 天时，CCTA 组无阻塞性疾病的 ICA 率（33.3%，39/117）高于 FFR 组（19.8%，19/96）（风险差异[RD] = 13.5%，95%置信区间[CI]：8.4%，18.6%；p = 0.03）。CCTA 组的 ICA 转诊率（27.5%，156/567）高于 FFR 组（20.3%，115/566）（RD = 7.2%，95%CI：2.3%，12.1%；p = 0.003）。CCTA 组的血运重建至 ICA 比率低于 FFR 组（RD = 19.8%，95%CI：14.1%，25.5%，p = 0.002）。1 年时，CCTA 组的 MACE 发生率高于 FFR 组（HR：1.73；95%CI：1.01，2.95；p = 0.04）。
在中度狭窄的患者中，与单独解剖学 CCTA 策略相比，基于机器学习的 FFR 策略似乎与较低的 ICA 转诊率、ICA 无阻塞性疾病和 1 年 MACE 发生率相关。
• 在有中度狭窄的稳定型患者中，基于 ML 的 FFR 策略与 CCTA 策略相比，其 ICA 转诊率较低，ICA 正常率较低，血运重建至 ICA 的比率较高。• 与 CCTA 策略相比，基于 ML 的 FFR 显示出更好的预后预测价值，这似乎与较低的 1 年 MACE 发生率有关。• 基于 ML 的 FFR 策略作为一种非侵入性的“一站式”方法，有可能改变疑似冠心病患者的诊断工作流程。
