Analysis and Comparison for Innovative Prediction Technique of Breast Cancer Tumor by Naive Bayes Algorithm over Support Vector Machine Algorithm with Improved Accuracy

Abstract

Aim: This research aims to determine the presence of breast cancer using Machine learning techniques and improving the accuracy of breast cancer prediction. Materials and Methods: This study is done on the data obtained from the UCI Machine Learning Repository and is used to acquire the data sets for the research of Innovative breast cancer prediction using machine learning algorithms. Naive Bayes (N=20) and Support vector machine (N=20) with sample size in accordance to total sample size calculated using clincalc.com by keeping alpha error-threshold at 0.05, confidence interval at 95%, enrollment ratio as 0:1, and power at 80%. Results: The Naive Bayes algorithm results in an accuracy of 92.25% with P=0.001,p<0.05 a sensitivity of 95.53% with P=0.001,p<0.05 and a precision of 90.87% with P=0.001,p<0.05. Support vector machine algorithm results in mean accuracy of 97.50%, sensitivity of 95.83%, and precision of 100%. Conclusion: Support vector machine (SVM) algorithm performed significantly better than Naive Bayes (NB) algorithm with improved accuracy of 97.50% for Innovative breast cancer prediction.