A Novel Logistic Regression in Coronary Artery Disease Prediction and Comparison of XGBoost Classifier for Improved Accuracy

the objective is to increase the precision of heart disease prediction by utilizing novel Logistic Regression and contrasting it with the XGBoost Classifier. There are 20 examples in each of the two groups representing the innovative Logistic Regression and XGBoost Classifier. The study's sample size is assessed using the G-power pre-test score of 80% and CI-95%, which accounts for the fact that each group has 20 samples. With a trained dataset of 303 samples, the accuracy of heart disease prediction by Logistic Regression is 93.8830% and XGBoost Classifier is 91.0480% respectively and it is significantly higher than the accuracy of the comparison model, with a statistical difference 0.001 (p<0.05) in SPSS statistical analysis. There is a statistical significance between the two groups. In light of the acquired outcomes the Logistic Regression gives a better accuracy rate of 93.8830% when contrasted with XGBoost Classifier which provides accuracy rate of 91.0480%.