Improving the efficiency of heart disease prediction using novel random forest classifier over support vector machine algorithm

Abstract

Aim: The Aim of the research study is to see how accurate Novel Random Forest (RF) and Support Vector Machine (SVM) classification algorithms were in predicting heart disease.Materials and Methods: The RF Classifier is used to a 304-Record dataset with heart disease.A paradigm for heart disease prediction in the medical field has been presented and developed, comparing Novel Random Forest with SVM classifiers. The total number of images in the sample was 42, with 21 in each test group. Result:-The classifiers were evaluated, predictions and accuracy were supplied. Based on the information provided, the SVM classifier predicts heart illness 60.0% of the time the accuracy of the SVM is 96.42 %, whereas the Novel The Random Forest classifier predicted 72.35% with no statistically significant difference between the two groups (p = 0.103; p > 0.05) with a 95% confidence interval.Conclusion: Novel Random Forest outperforms SVM in terms of prediction and accuracy when compared to it.

Imprint

P. Prasanna Sai Teja, Veeramani T. Improving the Efficiency of Heart Disease Prediction Using Novel Random Forest Classifier Over Support Vector Machine Algorithm. Cardiometry; Issue 25; December 2022; p.1468-1476; DOI: 10.18137/cardiometry.2022.25.14681476; Available from: https://www.cardiometry.net/issues/no25-december-2022/improving-efficiency-heart-disease