文献速递心脏核医学

基于传统危险因素、冠状动脉钙化与心外膜脂肪体积的机器学习预测血流动力学显著冠状动脉疾病

Machine learning to predict hemodynamically significant CAD based on traditional risk factors, coronary artery calcium and epicardial fat volume.
PubMed 文献 · J Nucl Cardiol · 2023-07-11

研究纳入184例接受SPECT/MPI和侵入性冠状动脉造影的症状性住院患者,采集临床特征、冠状动脉钙化(CAC)和心外膜脂肪体积(EFV),构建可解释机器学习模型预测血流动力学显著CAD。XGBoost模型在测试队列中AUC为0.89,敏感度68.0%、特异度96.8%、阳性预测值94.4%、阴性预测值79.0%、准确率83.9%。

要点

  • EFV、CAC、糖尿病、高血压和高脂血症是递归特征消除排名最高的特征。
  • 训练队列中XGBoost的AUC为0.88,优于逻辑回归和SVM的AUC 0.82。
  • 验证队列XGBoost的AUC为0.89,特异度96.8%,阳性预测值94.4%。

核心结论

  • 基于EFV、CAC、高血压、糖尿病和高脂血症构建并验证的XGBoost模型评估血流动力学显著CAD显示出良好的预测价值。
  • 机器学习联合SHAP方法可对个体化风险预测提供透明解释,使医生直观理解模型中关键特征的影响。

研究设计与样本

  • 研究纳入184例接受SPECT/MPI和侵入性冠状动脉造影的症状性住院患者,采集临床和影像特征(CAC和EFV)。
  • 数据随机分为训练队列(70%)和测试队列(30%),训练队列进行五折交叉验证。
  • 采用递归特征消除(RFE)选择特征,使用三种机器学习分类器(LR、SVM和XGBoost)构建并选择最佳预测模型。

主要发现

  • 训练队列中,血流动力学显著CAD患者的年龄、BMI和EFV显著更高,高血压和CAC比例更高(P均<0.05)。
  • 测试队列中,血流动力学显著CAD患者的EFV显著更高,CAC比例更高。
  • 训练队列中XGBoost的AUC为0.88,优于传统LR模型的AUC 0.82和SVM的AUC 0.82。
  • 决策曲线分析显示XGBoost模型具有最高的净获益指数。
  • 验证中XGBoost模型的AUC、敏感度、特异度、阳性预测值、阴性预测值和准确率分别为0.89、68.0%、96.8%、94.4%、79.0%和83.9%。

关键数值与推荐

  • 血流动力学显著CAD定义为冠状动脉狭窄程度≥50%且SPECT/MPI存在匹配的可逆性灌注缺损。
  • RFE排名最高的特征为EFV、CAC、糖尿病、高血压和高脂血症。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文未报告局限性。

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

We sought to establish an explainable machine learning (ML) model to screen for hemodynamically significant coronary artery disease (CAD) based on traditional risk factors, coronary artery calcium (CAC) and epicardial fat volume (EFV) measured from non-contrast CT scans. 184 symptomatic inpatients who underwent Single Photon Emission Computed Tomography/Myocardial Perfusion Imaging (SPECT/MPI) and Invasive Coronary Angiography (ICA) were enrolled. Clinical and imaging features (CAC and EFV) were collected. Hemodynamically significant CAD was defined when coronary stenosis severity ≥ 50% with a matched reversible perfusion defect in SPECT/MPI. Data was randomly split into a training cohort (70%) on which five-fold cross-validation was done and a test cohort (30%). The normalized training phase was preceded by the selection of features using recursive feature elimination (RFE). Three ML classifiers (LR, SVM, and XGBoost) were used to construct and choose the best predictive model for hemodynamically significant CAD. An explainable approach based on ML and the SHapley Additive exPlanations (SHAP) method was deployed to generate individual explanation of the model's decision. In the training cohort, hemodynamically significant CAD patients had significantly higher age, BMI and EFV, higher proportions of hypertension and CAC comparing with controls (P all < .05). In the test cohorts, hemodynamically significant CAD had significantly higher EFV and higher proportion of CAC. EFV, CAC, diabetes mellitus (DM), hypertension, and hyperlipidemia were the highest ranking features by RFE. XGBoost produced better performance (AUC of 0.88) compared with traditional LR model (AUC of 0.82) and SVM (AUC of 0.82) in the training cohort. Decision Curve Analysis (DCA) demonstrated that XGBoost model had the highest Net Benefit index. Validation of the model also yielded a favorable discriminatory ability with the AUC, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and accuracy of 0.89, 68.0%, 96.8%, 94.4%, 79.0% and 83.9% in the XGBoost model. A XGBoost model based on EFV, CAC, hypertension, DM and hyperlipidemia to assess hemodynamically significant CAD was constructed and validated, which showed favorable predictive value. ML combined with SHAP can offer a transparent explanation of personalized risk prediction, enabling physicians to gain an intuitive understanding of the impact of key features in the model.

来源:J Nucl Cardiol,查看原文。版权归原作者所有。

引用

  1. Yu W, Yang L, Zhang F, et al. Machine learning to predict hemodynamically significant CAD based on traditional risk factors, coronary artery calcium and epicardial fat volume. J Nucl Cardiol. 2023. PMID: 37434084. doi:10.1007/s12350-023-03333-0

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。