Cen Huan, Chen Sinan, Feng Shen, Chen Xiankun, Zhu Huiying, Jiang Wei, Zhang Han, Liu Hongmei, Liu Bo, Lu Weihui, Sun Pengtao
Department of Ultrasonography, The Second Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, China.
School of Physics and Telecommunication Engineering, South China Normal University, Guangzhou, China.
ESC Heart Fail. 2024 Dec;11(6):4335-4347. doi: 10.1002/ehf2.15038. Epub 2024 Sep 1.
The aim of this study was to develop a simple, fast and efficient clinical diagnostic model, composed of exercise stress echocardiography (ESE) indicators, of the exercise capacity of patients with chronic heart failure (CHF) by comparing the effectiveness of different classifiers.
Eighty patients with CHF (aged 60 ± 11 years; 78% male) were prospectively enrolled in this study. All patients underwent both cardiopulmonary exercise test (CPET) and ESE and were divided into two groups according to the VE/VCO slope: 30 patients with VE/VCO slope ventilation classification (VC)1 (i.e., VE/VCO slope < 30) and 50 patients with VC2 (i.e., VE/VCO slope ≥ 30). The analytical features of all patients in the four phases (rest, warm-up, peak and recovery phases) of ESE included the following parameters: left ventricular (LV) systolic function, LV systolic function reserve, LV diastolic function, LV diastolic function reserve and right ventricular function. Logistic regression (LR), extreme gradient boosting trees (XGBT), classification regression tree (CART) and random forest (RF) classifiers were implemented in a K-fold cross-validation model to distinguish VC1 from VC2 (LVEF in VC1 vs. VC2: 44 ± 8% vs. 43 ± 11%, P = 0.617). Among the four models, the LR model had the largest area under the curve (AUC) (0.82; 95% confidence interval [CI]: 0.73 to 0.92). In the multiple-variable LR model, the differences between the peak-exercise-phase and resting-phase values of E (ΔE), s' and sex were strong independent predictors of a VE/VCO slope ≥ 30 (P value: ΔE = 0.002, s' = 0.005, sex = 0.020). E/e', ΔLVEF, ΔLV global longitudinal strain and Δstroke volume were not predictors of VC in the multivariate LR model (P > 0.05 for the above).
Compared with the LR, XGBT, CART and RF models, the LR model performed best at predicting the VE/VCO slope category of CHF patients. A score chart was created to predict VE/VCO slopes ≥ 30. ΔE, s' and sex are independent predictors of exercise capacity in CHF patients.
本研究旨在通过比较不同分类器的有效性，开发一种由运动负荷超声心动图（ESE）指标组成的简单、快速且高效的临床诊断模型，用于评估慢性心力衰竭（CHF）患者的运动能力。
本研究前瞻性纳入了80例CHF患者（年龄60±11岁；78%为男性）。所有患者均接受了心肺运动试验（CPET）和ESE，并根据VE/VCO斜率分为两组：30例VE/VCO斜率通气分类（VC）1组（即VE/VCO斜率<30）和50例VC2组（即VE/VCO斜率≥30）。ESE四个阶段（静息、热身、峰值和恢复阶段）所有患者的分析特征包括以下参数：左心室（LV）收缩功能、LV收缩功能储备、LV舒张功能、LV舒张功能储备和右心室功能。在K折交叉验证模型中实施逻辑回归（LR）、极端梯度提升树（XGBT）、分类回归树（CART）和随机森林（RF）分类器，以区分VC1和VC2（VC1与VC2的左心室射血分数：44±8%对43±11%，P=0.617）。在这四种模型中，LR模型的曲线下面积（AUC）最大（0.82；95%置信区间[CI]：0.73至0.92）。在多变量LR模型中，E（ΔE）、s'的运动峰值阶段与静息阶段值之间的差异以及性别是VE/VCO斜率≥30的强独立预测因素（P值：ΔE=0.002，s'=0.005，性别=0.020）。在多变量LR模型中，E/e'、Δ左心室射血分数、Δ左心室整体纵向应变和Δ每搏输出量不是VC的预测因素（上述各项P>0.05）。
与LR、XGBT、CART和RF模型相比，LR模型在预测CHF患者的VE/VCO斜率类别方面表现最佳。创建了一个评分图表来预测VE/VCO斜率≥30。ΔE、s'和性别是CHF患者运动能力的独立预测因素。
