目的:心脏瓣膜反流患者正在增加;早期筛查潜在的心力衰竭(HF)患者是至关重要的。
方法:选取2019年11月1日至2023年10月31日在广州中医药大学第一附属医院心血管病科住院的509例心脏瓣膜反流患者。选择了三百五十六个案例作为建模的训练集,并选取153个案例作为模型内部验证的验证集。
结果:建立了具有以下9个危险因素的心力衰竭预测模型:房颤(AF),肺部感染(PI),冠状动脉疾病(CAD),肌酐(CREA),低密度脂蛋白胆固醇(LDL-C),d-二聚体(DDi),左心室舒张末期内径(LVEDd),二尖瓣反流(MR)和主动脉瓣反流(AR)。通过C指数[训练集:曲线下面积(AUC)0.937,95%置信区间(CI)0.911-0.963;验证集:AUC0.928,95%CI0.890-0.967]评估模型。Hosmer-Lemeshow检验(训练集:χ210.908,P=0.207;验证集:χ24.896,P=0.769)显示训练集和验证集在模型区分和校准方面均表现良好。决策曲线分析表明,训练集和验证集均具有较高的净收益,表明该模型具有良好的实用性。十倍交叉验证表明,训练集与验证集具有很高的相似性,说明该模型具有良好的稳定性。
结论:瓣膜反流患者心力衰竭的发生与房颤有显著的相关性,PI,CAD,CREA,LDL-C,DDi,LVEDD,MR和AR基于这些风险因素,开发并验证了心力衰竭的预测模型,表现出良好的差异化和实用性,精度高、稳定性好,提供了一种预测心力衰竭的方法。
OBJECTIVE: Patients with heart valvular regurgitation is increasing; early screening of potential patients developing heart failure (HF) is crucial.
METHODS: From 1 November 2019 to 31 October 2023, a total of 509 patients with heart valvular regurgitation hospitalized in the Department of Cardiovascular Disease of the First Affiliated Hospital of Guangzhou University of Traditional Medicine were enrolled. Three hundred fifty-six cases were selected as the training set for modelling, and 153 cases were selected as the validation set for the internal validation of the model.
RESULTS: A predictive model of heart failure with the following nine risk factors was developed: atrial fibrillation (AF), pulmonary infection (PI), coronary artery disease (CAD), creatinine (CREA), low-density lipoprotein cholesterol (LDL-C), d-dimer (DDi), left ventricular end-diastolic diameter (LVEDd), mitral regurgitation (MR) and aortic regurgitation (AR). The model was evaluated by the C-index [the training set: area under curve (AUC) 0.937, 95% confidence interval (CI) 0.911-0.963; the validation set: AUC 0.928, 95% CI 0.890-0.967]. Hosmer-Lemeshow test (the training set: χ2 10.908, P = 0.207; the validation set: χ2 4.896, P = 0.769) revealed that both the training and validation sets performed well in terms of model differentiation and calibration. Decision curve analysis showed that both the training and validation sets have higher net benefits, indicating that the model has good utility. Ten-fold cross-validation showed that the training set has high similarities with the validation set, which means that the model has good stability.
CONCLUSIONS: The occurrence of heart failure in patients with valvular regurgitation has a significant correlation with AF, PI, CAD, CREA, LDL-C, DDi, LVEDd, MR and AR. Based on these risk factors, a prediction model for heart failure was developed and validated, which showed good differentiation and utility, high accuracy and stability, providing a method for predicting heart failure.