Coronary artery disease, which involves a wide range of conditions, including narrowed or blocked coronary arteries, has remained the leading cause of death in the United States for over 50 years. The majority of cardiovascular disorders are preventable, which are identified through risk factors. Electrocardiogram (ECG), a routinely available test that provides information about one’s electrophysiologic health, may be beneficial in determining cardiovascular risk. Given the automated and highly correlated nature of its measurements, ECG data are suited well for analysis via machine learning. This research compares and demonstrates the improvements over standard methods for the discussed framework. The proposed framework demonstrates a novel approach to determine the severity of heart diseases using a traditional survival analysis and machine learning methods based on the blockages of major blood vessels in the heart. Hence, modern research demands to improve the accuracy of the predictive analysis. This work analyses the widespread predictive determination using various machine learning methods of heart disease and applies a cost-based matrix to enhance detection accuracy. An HD dataset to evaluate the classification performance following the classification algorithms.

冠状动脉疾病涉及多种疾病，包括冠状动脉狭窄或阻塞，50 多年来一直是美国的主要死亡原因。大多数心血管疾病是可以预防的，这是通过风险因素确定的。心电图 (ECG) 是一种常规可用的测试，可提供有关个人电生理健康的信息，可能有助于确定心血管风险。鉴于其测量的自动化和高度相关性，ECG 数据非常适合通过机器学习进行分析。本研究比较并展示了对所讨论框架的标准方法的改进。拟议的框架展示了一种使用传统生存分析和基于心脏主要血管阻塞的机器学习方法来确定心脏病严重程度的新方法。因此，现代研究要求提高预测分析的准确性。这项工作使用心脏病的各种机器学习方法分析了广泛的预测确定，并应用基于成本的矩阵来提高检测精度。根据分类算法评估分类性能的 HD 数据集。这项工作使用心脏病的各种机器学习方法分析了广泛的预测确定，并应用基于成本的矩阵来提高检测精度。根据分类算法评估分类性能的 HD 数据集。这项工作使用心脏病的各种机器学习方法分析了广泛的预测确定，并应用基于成本的矩阵来提高检测精度。根据分类算法评估分类性能的 HD 数据集。