Prediction of Heart Failure using Support Vector Machine compared with Decision Tree Algorithm for better Accuracy

Heart attacks are frequently caused by partial or full blockages of the heart's arteries or veins, which restrict blood flow to or from the heart. The aim of this study is to develop the best categorization algorithm that will provide us with the most accurate forecasts. The Artificial Intelligence Laboratory of the Saveetha School of Engineering's Department of Computer Science and Engineering conducted this research. The classification algorithms utilised in this study are divided into two groups. The SVM and DT algorithms are in Groups 1 and 2, respectively with a g-power value of 80 percent and the heart images were collected from various web sources with recent study findings and threshold 0.05%, Confidence Interval 95% mean and standard deviation. The proposed system using SVM algorithm has achieved an improved accuracy of 72.54%, compared with DT algorithm with an accuracy of 70.32% with a significant value of two tailed tests is 0.027 (
$p < 0.05$
) with 95% confidence interval. Prediction of heart failure using the SVM algorithm appears to be significantly better than the DT with improved accuracy.