Université de Rennes, CHU Rennes, Inserm, LTSI - UMR 1099, Rennes, France.
Institute for Surgical Research and Department of Cardiology, Oslo University Hospital and University of Oslo, Oslo, Norway.
J Am Soc Echocardiogr. 2021 May;34(5):494-502. doi: 10.1016/j.echo.2020.12.025. Epub 2021 Jan 7.
Despite all having systolic heart failure and broad QRS intervals, patients screened for cardiac resynchronization therapy (CRT) are highly heterogeneous, and it remains extremely challenging to predict the impact of CRT devices on left ventricular function and outcomes. The aim of this study was to evaluate the relative impact of clinical, electrocardiographic, and echocardiographic data on the left ventricular remodeling and prognosis of CRT candidates by the application of machine learning approaches.
One hundred ninety-three patients with systolic heart failure receiving CRT according to current recommendations were prospectively included in this multicenter study. A combination of the Boruta algorithm and random forest methods was used to identify features predicting both CRT volumetric response and prognosis. Model performance was tested using the area under the receiver operating characteristic curve. The k-medoid method was also applied to identify clusters of phenotypically similar patients.
From 28 clinical, electrocardiographic, and echocardiographic variables, 16 features were predictive of CRT response, and 11 features were predictive of prognosis. Among the predictors of CRT response, eight variables (50%) pertained to right ventricular size or function. Tricuspid annular plane systolic excursion was the main feature associated with prognosis. The selected features were associated with particularly good prediction of both CRT response (area under the curve, 0.81; 95% CI, 0.74-0.87) and outcomes (area under the curve, 0.84; 95% CI, 0.75-0.93). An unsupervised machine learning approach allowed the identification of two phenogroups of patients who differed significantly in clinical variables and parameters of biventricular size and right ventricular function. The two phenogroups had significantly different prognosis (hazard ratio, 4.70; 95% CI, 2.1-10.0; P < .0001; log-rank P < .0001).
Machine learning can reliably identify clinical and echocardiographic features associated with CRT response and prognosis. The evaluation of both right ventricular size and functional parameters has pivotal importance for the risk stratification of CRT candidates and should be systematically performed in patients undergoing CRT.
尽管所有患者均存在收缩性心力衰竭和宽 QRS 波群，但接受心脏再同步治疗（CRT）筛选的患者存在高度异质性，因此仍然极难预测 CRT 设备对左心室功能和结局的影响。本研究旨在通过应用机器学习方法评估临床、心电图和超声心动图数据对 CRT 候选者左心室重构和预后的相对影响。
本前瞻性多中心研究纳入了 193 例根据现有推荐接受 CRT 的收缩性心力衰竭患者。采用 Boruta 算法和随机森林方法相结合，确定预测 CRT 容量反应和预后的特征。使用接受者操作特征曲线下面积检验模型性能。还应用 k-medoid 方法识别表型相似的患者聚类。
从 28 个临床、心电图和超声心动图变量中，有 16 个特征可预测 CRT 反应，11 个特征可预测预后。在 CRT 反应的预测因素中，有 8 个变量（50%）与右心室大小或功能有关。三尖瓣环平面收缩期位移是与预后相关的主要特征。所选特征与 CRT 反应（曲线下面积为 0.81；95%置信区间，0.74-0.87）和结局（曲线下面积为 0.84；95%置信区间，0.75-0.93）的预测均具有特别好的相关性。一种无监督机器学习方法可识别出两组表型不同的患者，这些患者在临床变量和双心室大小及右心室功能参数方面存在显著差异。两组患者的预后差异有统计学意义（风险比，4.70；95%置信区间，2.1-10.0；P<0.0001；对数秩检验 P<0.0001）。
机器学习可以可靠地识别与 CRT 反应和预后相关的临床和超声心动图特征。评估右心室大小和功能参数对于 CRT 候选者的风险分层具有重要意义，应在接受 CRT 的患者中系统进行。
