Research Unit Hypertension and Cardiovascular Epidemiology, KU Leuven Department of Cardiovascular Sciences, University of Leuven, Campus Sint Rafaël, Kapucijnenvoer 33, Block h, Box 7001, B 3000 Leuven, Belgium.
Department of Life Science and Technologies, IMEC, Kapeldreef 75, 3001 Leuven, Belgium.
Eur Heart J Cardiovasc Imaging. 2021 Sep 20;22(10):1208-1217. doi: 10.1093/ehjci/jeaa135.
Both left ventricular (LV) diastolic dysfunction (LVDD) and hypertrophy (LVH) as assessed by echocardiography are independent prognostic markers of future cardiovascular events in the community. However, selective screening strategies to identify individuals at risk who would benefit most from cardiac phenotyping are lacking. We, therefore, assessed the utility of several machine learning (ML) classifiers built on routinely measured clinical, biochemical, and electrocardiographic features for detecting subclinical LV abnormalities.
We included 1407 participants (mean age, 51 years, 51% women) randomly recruited from the general population. We used echocardiographic parameters reflecting LV diastolic function and structure to define LV abnormalities (LVDD, n = 252; LVH, n = 272). Next, four supervised ML algorithms (XGBoost, AdaBoost, Random Forest (RF), Support Vector Machines, and Logistic regression) were used to build classifiers based on clinical data (67 features) to categorize LVDD and LVH. We applied a nested 10-fold cross-validation set-up. XGBoost and RF classifiers exhibited a high area under the receiver operating characteristic curve with values between 86.2% and 88.1% for predicting LVDD and between 77.7% and 78.5% for predicting LVH. Age, body mass index, different components of blood pressure, history of hypertension, antihypertensive treatment, and various electrocardiographic variables were the top selected features for predicting LVDD and LVH.
XGBoost and RF classifiers combining routinely measured clinical, laboratory, and electrocardiographic data predicted LVDD and LVH with high accuracy. These ML classifiers might be useful to pre-select individuals in whom further echocardiographic examination, monitoring, and preventive measures are warranted.
超声心动图评估的左心室（LV）舒张功能障碍（LVDD）和肥厚（LVH）都是社区未来心血管事件的独立预后标志物。然而，缺乏用于识别风险个体并确定最受益于心脏表型的选择性筛查策略。因此，我们评估了几种基于常规测量的临床、生化和心电图特征构建的机器学习（ML）分类器在检测亚临床 LV 异常方面的效用。
我们纳入了 1407 名（平均年龄 51 岁，51%为女性）随机招募的一般人群参与者。我们使用反映 LV 舒张功能和结构的超声心动图参数来定义 LV 异常（LVDD，n=252；LVH，n=272）。接下来，我们使用了 4 种监督 ML 算法（XGBoost、AdaBoost、随机森林（RF）、支持向量机和逻辑回归），基于临床数据（67 个特征）构建分类器，以对 LVDD 和 LVH 进行分类。我们应用了嵌套的 10 折交叉验证设置。XGBoost 和 RF 分类器的受试者工作特征曲线下面积（AUC）值较高，预测 LVDD 的 AUC 值在 86.2%至 88.1%之间，预测 LVH 的 AUC 值在 77.7%至 78.5%之间。年龄、体重指数、血压的不同成分、高血压病史、降压治疗以及各种心电图变量是预测 LVDD 和 LVH 的首选特征。
XGBoost 和 RF 分类器结合常规测量的临床、实验室和心电图数据，对 LVDD 和 LVH 具有较高的预测准确性。这些 ML 分类器可能有助于选择需要进一步进行超声心动图检查、监测和预防措施的个体。
