Efficient Way of Heart Disease Prediction and Analysis using different Ensemble Algorithm: A Comparative Study

This work presents a variety of voting ensemble models to measure human heart disease. This work aims to give confidence to doctors to diagnose heart disease accurately. S o that they can begin treatment in an earlier and more effective manner, thereby saving a valuable human life. The dataset can be trained by different models like Voting Ensemble, Light GBM, Stack Ensemble, XG Boost Classifier, Random Forest, and Logistic Regression. The work considered the 12 attributes and trained the model with different algorithms. Finally, the result shows that the systolic blood pressure parameter is the primary reason for heart disease compared to any other parameter in the data set. Considering all the different algorithms, the voting ensemble method produced more than 80 % accuracy.