文献速递心力衰竭与心肌病

基于标准12导联心电图测量的可解释机器学习区分HFmr/rEF与HFpEF

Differentiating HFmr/rEF from HFpEF using standard 12-lead ECG measurements: an interpretable machine learning study
RSS 订阅 · Open Heart

本研究为回顾性队列,纳入495例住院心衰患者(HFmr/rEF 254例,HFpEF 241例),利用常规12导联心电图数据开发机器学习模型区分HFmr/rEF与HFpEF。随机森林模型表现最佳,仅用心电图特征时AUC为0.821,采用12个Boruta筛选变量的简约模型AUC为0.832,与综合模型无显著差异,支持心电图作为超声不可及时的分型辅助工具。

要点

  • 随机森林模型仅用12个心电图变量即可区分HFmr/rEF与HFpEF,AUC达0.832。
  • 简约心电图模型与包含临床/实验室/心电图的综合模型性能无显著差异(p=0.288)。
  • 添加X线心脏增大未提升模型性能,提示心电图特征已提供主要信息。

核心结论

  • 基于少量标准心电图测量的简约随机森林模型能较好区分HFmr/rEF与HFpEF,支持心电图作为超声不可及时的分型辅助工具。

研究设计与样本

  • 回顾性队列纳入495例住院心衰患者,HFmrEF与HFrEF合并为左室射血分数<50%组,数据按70/30分为训练集与留出测试集。
  • 训练随机森林、Extreme Gradient Boosting和支持向量机模型,采用五折交叉验证调参,Boruta筛选关键心电图特征,测试集用AUC和准确率评估,DeLong检验比较AUC。

主要发现

  • 随机森林表现最佳:仅用心电图特征时AUC为0.821(95%CI 0.752-0.890),准确率75.7%。
  • 采用12个Boruta筛选心电图变量的简约随机森林模型AUC为0.832(95%CI 0.766-0.899),准确率76.4%。
  • 简约模型与综合模型(临床/实验室/心电图预测因子,AUC 0.804,95%CI 0.734-0.875)的AUC差异无统计学意义(p=0.288)。
  • 简约模型与使用全部心电图特征的模型AUC差异无统计学意义(p=0.092)。
  • 添加X线心脏增大未改善模型性能。

临床怎么用

  • 当超声心动图不可立即获得时,可采用基于标准12导联心电图测量的简约随机森林模型辅助区分HFmr/rEF与HFpEF。
  • 模型使用12个Boruta筛选的心电图变量,便于临床快速应用。

局限性

  • 本研究为单中心回顾性队列,样本量495例,外部泛化性需进一步验证。
  • HFmrEF与HFrEF合并分析,未单独区分HFmrEF与HFrEF。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

Background Differentiating heart failure (HF) with mildly reduced/reduced ejection fraction (HFmr/rEF) from HF with preserved ejection fraction (HFpEF) guides therapy but echocardiography may be delayed or unavailable. We developed and validated machine learning models using routine 12-lead ECG data to classify HF phenotypes. Methods In this retrospective cohort of hospitalised patients with HF, predictors available at or before the index ECG were used. HFmrEF was pooled with HFrEF (left ventricular ejection fraction <50%) for model development. Data were split 70/30 into training and held-out test sets. Random forest (RF), Extreme Gradient Boosting and support vector machine models were trained and tuned using fivefold cross-validation in the training set. Boruta was used to select key ECG features. Test-set performance was evaluated by area under the curve (AUC) and accuracy; AUCs were compared using DeLong’s test. Results Overall, 495 patients were included (254 HFmr/rEF; 241 HFpEF). RF consistently performed best. Using ECG features alone, RF achieved an AUC of 0.821 (95% CI 0.752 to 0.890) and accuracy of 75.7%. A parsimonious RF model using 12 Boruta-selected ECG variables achieved an AUC of 0.832 (95% CI 0.766 to 0.899) and accuracy of 76.4%, with no significant AUC difference versus a comprehensive RF model using clinical/laboratory/ECG predictors (AUC 0.804, 95% CI 0.734 to 0.875; p=0.288) or the model using all ECG features (p=0.092). Adding X-ray cardiomegaly did not improve performance. Conclusion A parsimonious RF model based on a small set of standard ECG measurements differentiates HFmr/rEF from HFpEF with good discrimination, supporting ECG as an adjunct for phenotyping when echocardiography is not immediately available.

来源:Open Heart,查看原文。版权归原作者所有。

引用

  1. Open Heart:Differentiating HFmr/rEF from HFpEF using standard 12-lead ECG measurements: an interpretable machine learning study

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。