[论文解读] Enhancing the Detection of Coronary Artery Disease Using Machine Learning

Karan Kumar Singh, Nikita Gajbhiye+1 more|arXiv (Cornell University)|Mar 6, 2026

Artificial Intelligence in Healthcare被引用 0

一句话总结

该研究比较 Bi-LSTM、GRU 及 Bi-LSTM+GRU 混合模型在基于 3D CCTA 数据的非侵入性冠状动脉疾病检测中的表现，混合模型达到最高准确率 97.07%。

ABSTRACT

Coronary Artery Disease (CAD) remains a leading cause of morbidity and mortality worldwide. Early detection is critical to recover patient outcomes and decrease healthcare costs. In recent years, machine learning (ML) advancements have shown significant potential in enhancing the accuracy of CAD diagnosis. This study investigates the application of ML algorithms to improve the detection of CAD by analyzing patient data, including clinical features, imaging, and biomarker profiles. Bi-directional Long Short-Term Memory (Bi-LSTM), Gated Recurrent Units (GRU), and a hybrid of Bi-LSTM+GRU were trained on large datasets to predict the presence of CAD. Results demonstrated that these ML models outperformed traditional diagnostic methods in sensitivity and specificity, offering a robust tool for clinicians to make more informed decisions. The experimental results show that the hybrid model achieved an accuracy of 97.07%. By integrating advanced data preprocessing techniques and feature selection, this study ensures optimal learning and model performance, setting a benchmark for the application of ML in CAD diagnosis. The integration of ML into CAD detection presents a promising avenue for personalized healthcare and could play a pivotal role in the future of cardiovascular disease management.

研究动机与目标

• 开发一个使用人口统计、临床和影像数据来预测 CAD 的 ML 模型。
• 比较不同 ML 算法（如 DT、RF、SVM、神经网络）在 CAD 预测中的表现。
• 通过特征选择识别显著预测因子，以提升模型准确性。
• 通过预处理步骤（处理缺失值、归一化、离群值处理）来提升学习效果，从而提升数据质量。

提出的方法

• 汇集来自 Siemens 128 排扫描仪的 1000 张 3D CCTA 图像数据集。
• 应用数据清洗、归一化和标准化（z-score）以准备建模特征。
• 使用皮尔逊相关矩阵进行特征选择以降低维度。
• 实现用于 CAD 预测的 Bi-LSTM、GRU 和 Bi-LSTM+GRU 混合分类器。
• 使用准确率、精确率、召回率、F1-score 以及 ROC 相关指标评估模型。

Figure 1: Block diagram of proposed methodology

实验结果

研究问题

• RQ1 ML 模型能否在结合临床特征的非侵入性影像数据上准确预测 CAD？
• RQ2 哪种 ML 架构（Bi-LSTM、GRU，还是混合结构）在该数据集上实现最佳 CAD 检测性能？
• RQ3 特征提取与预处理如何影响模型性能与泛化能力？
• RQ4 所提出的模型与现有 CAD 检测方法在准确率及其他指标上有何比较？

主要发现

模型	准确率	精确率	召回率	F1-score
Bi-LSTM	92.7	92.9	92.7	92.7
GRU	93.9	94	93.9	93.8
Bi-LSTM+GRU 混合	97.07	94.13	94.07	94

• Bi-LSTM 的准确率为 92.7%，精确率 92.9%，召回率 92.7%，F1-score 92.7%。
• GRU 的准确率为 93.9%，精确率 94%，召回率 93.9%，F1-score 93.8%。
• 混合 Bi-LSTM+GRU 的准确率为 97.07%，精确率 94.13%，召回率 94.07%，F1-score 94%。
• 混合模型优于单独的 Bi-LSTM 与 GRU 模型及文献中既有的方法。
• 该研究强调非侵入性数据整合有助于改进临床决策与 CAD 诊断。

Figure 2: Training and validation loss of the Bi-LSTM model across epochs