计算机辅助设计
机器学习
人工智能
决策树
支持向量机
梯度升压
算法
计算机科学
朴素贝叶斯分类器
随机森林
冠状动脉疾病
Boosting(机器学习)
逻辑回归
统计分类
接收机工作特性
分类器(UML)
内科学
医学
工程类
工程制图
作者
Geetha Pratyusha Miriyala,Arun Kumar Sinha,Dushantha Nalin K. Jayakody,Abhishek Sharma
标识
DOI:10.1109/iciafs52090.2021.9605854
摘要
Coronary Artery Disease (CAD) is a cardiovascular disease that has the highest mortality rate. The non-invasive method for diagnosing CAD is coronary angiography which is expensive and exposes the patient to radiation. The present scenario for diagnosing CAD has motivated researchers to analyze and diagnose the disease using Machine Learning (ML) algorithms. In this work, the efficacy of various ML algorithms used to diagnose CAD disease is presented and compared. The proposed methodology aims to train the dataset using algorithms namely: K-Nearest Neighbor, Support Vector Machine, Logistic Regression, Naïve Bayes, Decision Tree, Extreme Gradient Boosting, Random Forest, Extra Tree Classifier, and Light Gradient Boosting machine, to achieve accuracy for diagnosing the CAD. The experimental results are validated in the simulation environment, and the conclusions were drawn from the performance indices, i.e., Accuracy, Sensitivity, Specificity, Precision, F1-Score, and Binary cross-entropy cost function. The meta-analysis shows that Light Gradient Machine achieves an accuracy of 93.36%, which is the highest among other ML algorithms.
科研通智能强力驱动
Strongly Powered by AbleSci AI