Heart Plaque Detection with Improved Accuracy using Decision tree in comparison with Least Squares Support Vector Machine

Abstract

Aim: The main aim of this research is to detect heart plaque using the Decision Tree algorithm with improved accuracy and comparing it with Least Squares Support Vector Machine. Materials and Methods: Decision tree and Least squares Support Vector Machine algorithms are two groups compared in this study. Each group has 20 samples and calculations utilized pretest power of 0.08 with 95% confidence interval. The G power is estimated for samples using clincalc, which has two groups: alpha, power, and enrollment ratio. These samples are split into two groups: training dataset (n = 489 [70%]) and test dataset (n = 277 [30%]). Results: The accuracy obtained for Decision Tree was 68.13 % and 67.3 % for the Least Squares Support Vector Machine technique. Since p (2-tailed) < 0.05, in SPSS statistical analysis, a significant difference exists between the two groups. Conclusion: It is found that the Decision Tree algorithm is significantly better than the Least Squares Support Vector Machine algorithm in Heart plaque disease detection for the dataset considered.