Background: Coronary artery disease (CAD) causes substantial death toll in the United States and worldwide. While traditional methods for CAD mortality prediction are based on established risk factors, they have significant limitations in accuracy, adaptability to diverse populations, performance for individual risk prediction compared to group data, and incorporation of socioeconomic and lifestyle variations. Machine learning (ML) models have demonstrated superior performance in CAD prediction; however, they often struggle with capturing complex data interactions that can impact mortality.

Methods: We proposed lightweight, interpretable graph neural network (GNN) models, utilizing data from a large trial of hypertensive patients with CAD to predict mortality using a concise set of critical features. While this smaller set of features can improve efficiency and implementation in clinical settings, the model's "lightweight" nature facilitates fast real-time applications. We utilized a hybrid approach, which first uses logistic regression (LR) to identify statistically significant features, followed by propensity score matching (PSM) to identify potentially causal features. These causal features, alongside demographic variables, were employed to create a graph of patients, drawing edges between patients with similar causal features. Accordingly, lightweight 5-layer graph convolutional network (GCN) and graph attention network (GAT) were designed for mortality prediction, followed by an interpretable method (i.e., GNNExplainer) to report the feature importance.

Results: The proposed GCN achieved a recall of 93.02 % and a negative predictive value (NPV) of 89.42 %, higher than all other classifiers. Accordingly, a web-based decision support system (DSS), called CAD-SS, was developed, capable of predicting mortality, identifying risk factors, and similar patients, guiding clinicians in reliable and informed decision-making.

Conclusions: Our proposed CAD-SS, which utilizes an interpretable and causality-aware lightweight GCN model, demonstrated reasonably high performance in predicting mortality due to CAD. This unique system can help identify the most vulnerable patients.

Keywords: Causal artificial intelligence (Causal AI); Coronary artery disease (CAD); Deep learning (DL); Graph neural network (GNN); Machine learning (ML); Propensity score matching (PSM).

Copyright © 2025 Elsevier Inc. All rights reserved.

背景： 冠状动脉疾病（CAD）在美国和全世界造成了巨大的死亡率。虽然传统的CAD死亡预测方法基于已知的风险因素，但它们在准确性、适应不同人群的能力、个体风险预测与群体数据相比的性能以及纳入社会经济和生活方式变化方面存在显著局限性。机器学习（ML）模型在CAD预测中表现出色；然而，这些模型往往难以捕捉影响死亡率的复杂数据交互。

方法： 我们提出了一种轻量级且可解释的图神经网络（GNN）模型，利用高血压患者的大规模试验数据来预测使用一组关键特征集的CAD患者的死亡率。虽然较小的特征集合可以提高临床环境中的效率和实施效果，但该模型“轻量级”的特性促进了快速实时应用。我们采用了一种混合方法，首先使用逻辑回归（LR）识别统计上显著的特征，然后通过倾向评分匹配（PSM）识别潜在的因果特征。这些因果特征与人口统计数据一起被用于构建患者的图结构，在具有相似因果特征的患者之间绘制边。因此，设计了轻量级5层图卷积网络（GCN）和图注意力网络（GAT），用于死亡率预测，并采用了一种可解释的方法（即GNNExplainer）来报告特征的重要性。

结果： 提出的GCN实现了93.02%的召回率和89.42%的负预测值（NPV），高于所有其他分类器。因此，开发了一个基于网络的决策支持系统（DSS），名为CAD-SS，能够预测死亡率、识别风险因素以及找到相似患者，指导临床医生做出可靠且有信息依据的决策。

结论： 我们提出的利用可解释和因果性感知轻量级GCN模型的CAD-SS，在预测因CAD导致的死亡率方面表现出相对较高的性能。这种独特的系统可以帮助识别最脆弱的患者。

关键词： 因果人工智能（Causal AI）；冠状动脉疾病（CAD）；深度学习（DL）；图神经网络（GNN）；机器学习（ML）；倾向评分匹配（PSM）。