Department of Internal Medicine, Seoul National University Hospital, Seoul, South Korea.
British Heart Foundation Centre for Cardiovascular Science, University of Edinburgh, Edinburgh, United Kingdom.
J Am Coll Cardiol. 2021 Aug 10;78(6):545-558. doi: 10.1016/j.jacc.2021.05.047.
Cardiovascular magnetic resonance (CMR) is increasingly used for risk stratification in aortic stenosis (AS). However, the relative prognostic power of CMR markers and their respective thresholds remains undefined.
Using machine learning, the study aimed to identify prognostically important CMR markers in AS and their thresholds of mortality.
Patients with severe AS undergoing AVR (n = 440, derivation; n = 359, validation cohort) were prospectively enrolled across 13 international sites (median 3.8 years' follow-up). CMR was performed shortly before surgical or transcatheter AVR. A random survival forest model was built using 29 variables (13 CMR) with post-AVR death as the outcome.
There were 52 deaths in the derivation cohort and 51 deaths in the validation cohort. The 4 most predictive CMR markers were extracellular volume fraction, late gadolinium enhancement, indexed left ventricular end-diastolic volume (LVEDVi), and right ventricular ejection fraction. Across the whole cohort and in asymptomatic patients, risk-adjusted predicted mortality increased strongly once extracellular volume fraction exceeded 27%, while late gadolinium enhancement >2% showed persistent high risk. Increased mortality was also observed with both large (LVEDVi >80 mL/m) and small (LVEDVi ≤55 mL/m) ventricles, and with high (>80%) and low (≤50%) right ventricular ejection fraction. The predictability was improved when these 4 markers were added to clinical factors (3-year C-index: 0.778 vs 0.739). The prognostic thresholds and risk stratification by CMR variables were reproduced in the validation cohort.
Machine learning identified myocardial fibrosis and biventricular remodeling markers as the top predictors of survival in AS and highlighted their nonlinear association with mortality. These markers may have potential in optimizing the decision of AVR.
心血管磁共振（CMR）越来越多地用于主动脉瓣狭窄（AS）的风险分层。然而，CMR 标志物的相对预后能力及其各自的阈值仍未确定。
使用机器学习，本研究旨在确定 AS 中具有预后意义的 CMR 标志物及其死亡率阈值。
前瞻性纳入 13 个国际中心的 440 例（推导队列；n=359 例，验证队列）严重 AS 患者。CMR 在手术或经导管主动脉瓣置换术（AVR）前进行。使用包含 29 个变量（13 个 CMR）的随机生存森林模型，以 AVR 后死亡为结局。
推导队列中有 52 例死亡，验证队列中有 51 例死亡。最具预测性的 4 个 CMR 标志物是细胞外容积分数、晚期钆增强、指数化左心室舒张末期容积（LVEDVi）和右心室射血分数。在整个队列和无症状患者中，一旦细胞外容积分数超过 27%，风险调整后的预测死亡率就会显著增加，而晚期钆增强>2%则持续显示出高风险。LVEDVi 较大（LVEDVi>80 mL/m）和较小（LVEDVi≤55 mL/m）、右心室射血分数较高（>80%）和较低（≤50%）也与死亡率增加相关。当将这 4 个标志物与临床因素结合时，预测能力得到提高（3 年 C 指数：0.778 比 0.739）。在验证队列中重现了 CMR 变量的预后阈值和风险分层。
机器学习确定心肌纤维化和双心室重构标志物是 AS 患者生存的主要预测因子，并强调了它们与死亡率的非线性关系。这些标志物可能在优化 AVR 决策方面具有潜力。
