Coronary Artery Disease Prediction and Analysis using Machine Learning Techniques

Authors

  • Jasmine Jinitha A, Dr. S. Mangayarkarasi

DOI:

https://doi.org/10.17762/msea.v71i3.461

Abstract

Coronary Artery Disease (CAD) contains a huge variety of heart-associated illnesses are one of the leading causes of death globally in recent decades. Cardiovascular diseases account for 31 percent of all fatalities worldwide. The scientific affiliation generates a huge quantity of scientific information associated with cardiovascular disease, which need to be well tested to forecast cardiovascular disease. In current days, Machine learning (ML) has emerge as the number one method for the evolution of predictive models within the health-care industry, and it become determined to check how accurate their prediction scores are based on the data collected.  The contemporary dataset from the UCI heart repository database is utilized in this proposal, which employs machine learning approaches. To look at the coronary illness, these strategies use 13 clinical parameters from the patient. As a result, supporting human beings in identifying whether or not or now no longer they are at threat for coronary heart illness is tremendously desirable. Gradient Boosting, Decision Tree, Random Forest, SVM, KNN, and Logistic Regression are some of the Supervised ML classifiers employed in this study to deploy a model for heart disease prediction. A 10-fold cross-validation testing option became used to assess the algorithms performance. Also researcher used tuning of the hyper parameter, number of nearest neighbors, namely k, the instance-based (KNN) classifier. Result indicates that compared to unique ML strategies, Gradient Boosting Classifier       and Ada Boost Classifier algorithms gives 86.88%, Random Forest Classifier gives 88.15% and K Neighbors Classifier and SVM producing 90% accuracy in lots much less time for the prediction. This model (KNN) or SVM can be useful to the medical practitioners at their medical institution as Decision Making Support System.

Downloads

Published

2022-08-19

How to Cite

Jasmine Jinitha A, Dr. S. Mangayarkarasi. (2022). Coronary Artery Disease Prediction and Analysis using Machine Learning Techniques. Mathematical Statistician and Engineering Applications, 71(3), 1207–1224. https://doi.org/10.17762/msea.v71i3.461

Issue

Section

Articles