Related Experiment Videos
Support vector machines classification for discriminating coronary heart disease patients from non-coronary heart
1Institute for Computational Science and Engineering, Laboratory of New Fibrous Materials and Modern Textile, Growing Base for State Key Laboratory, Qingdao University, Qingdao, Shandong, China.
Insights
Support vector machines (SVM) effectively classify coronary heart disease, achieving high accuracy. This machine learning approach aids in diagnosing heart conditions using patient data.
Area of Science:
- Cardiology
- Machine Learning
- Biomedical Informatics
Background:
- Coronary heart disease (CHD) diagnosis relies on various clinical and biochemical markers.
- Accurate and timely diagnosis is crucial for effective patient management and treatment.
- Machine learning offers potential for improving diagnostic accuracy in complex diseases like CHD.
Purpose of the Study:
- To evaluate the efficacy of Support Vector Machines (SVM) for classifying patients with coronary heart disease (CHD) versus non-coronary heart disease.
- To compare the performance of SVM against Linear Discriminant Analysis (LDA) in CHD classification.
- To assess the utility of SVM as an assistive diagnostic tool for CHD.
Main Methods:
- Experiments were conducted using a dataset of 346 patients.
- Key variables included low-density lipoprotein cholesterol (LDLC), high-density lipoprotein cholesterol (HDLC), total cholesterol (TC), triglycerides (TG), glucose, and age.
- Support Vector Machine (SVM) with a radial basis function (RBF) kernel was compared with Linear Discriminant Analysis (LDA).
Main Results:
- SVM achieved a training set prediction accuracy of 96.86% and a test set accuracy of 78.18%.
- LDA achieved a training set accuracy of 90.57% and a test set accuracy of 72.73%.
- Cross-validated accuracy for SVM was 92.67%, and for LDA was 85.4%.
Conclusions:
- Support Vector Machine (SVM) demonstrates significant potential as a valid tool for assisting in the diagnosis of coronary heart disease.
- SVM exhibits superior performance compared to LDA in the classification of CHD based on the tested variables.
- The findings support the integration of machine learning, specifically SVM, into diagnostic workflows for CHD.
Objective:
The present contribution concentrates on the application of support vector machines (SVM) for coronary heart disease and non-coronary heart disease classification.
Methods:
We conducted many experiments with support vector machine and different variables of low-density lipoprotein cholesterol (LDLC), high-density lipoprotein cholesterol (HDLC), total cholesterol (TC), triglycerides (TG), glucose and age (dataset 346 patients with completed diagnostic procedures). Linear and non-linear classifiers were compared: linear discriminant analysis (LDA) and SVM with a radial basis function (RBF) kernel as a non-linear technique.
Results:
The prediction accuracy of training and test sets of SVM were 96.86% and 78.18% respectively, while the prediction accuracy of training and test sets of LDA were 90.57% and 72.73% respectively. The cross-validated prediction accuracy of SVM and LDA were 92.67% and 85.4%.
Conclusion:
Support vector machine can be used as a valid way for assisting diagnosis of coronary heart disease.
Related Concept Videos
01:26Coronary Artery Disease IV: Preventive Measures
01:18Cardiovascular Drugs: Classification based on Therapeutic Indications
01:30Coronary Artery Disease I: Introduction