Analysis and Comparison for Innovative Prediction Technique of Breast Cancer Tumor using Decision Tree Algorithm over Support Vector Machine Algorithm with Improved Accuracy

Abstract

Aim: The major goal of this research is to improve the accuracy of the Decision Tree (DT) and Support vector machine (SVM) algorithms and compare their efficiency in detecting breast cancer tumors. Materials and Methods: This work depends on the data obtained from the UCI Machine Learning Repository and used to acquire the data sets for the research of Innovative breast cancer prediction using machine learning algorithms. The sample size of breast cancer prediction involves two groups: Decision tree (N=20) and Support vector machine (N=20) according to clincalc.com by keeping 0.05 alpha error-threshold, 95% confidence interval, enrollment ratio as 0:1, and 80% G power. The accuracy, sensitivity, and precision are calculated using MATLAB software. Result: The accuracy of the DT is 83.83% (p<0.001) while the accuracy rate of the Support vector machine is 97.50%. The Decision tree outcomes have a sensitivity and precision rate of 87.46% (p<0.001) and 84.13% (p<0.001) respectively, whereas the Support vector machine sensitivity and the precision rate are 95.83% and 100% respectively. Conclusion: Support vector machine algorithm performed significantly better with improved accuracy of 97.50% for breast cancer prediction.