Heart Disease Prediction Using Data Analysis and Effective Machine Learning Techniques

Cardiovascular disease stands as a prominent global health concern, claiming a significant number of lives. The accurate prediction of such diseases poses a substantial challenge in the realm of data analysis. The heart, being the second most vital organ in the human body, necessitates dedicated efforts in medical research. Timely identification and diagnosis of heart diseases are pivotal in saving lives, particularly in cases of conditions like coronary heart disease. The utilization of machine learning algorithms, including Gaussian Naive Bayes, Support Vector Machine (SVM), Logistic Regression, K-Nearest Neighbour (K-NN), and Decision Tree classifiers, along with diverse grouping algorithms such as voting, facilitates the creation of a comprehensive model by amalgamating these approaches. The main aims of this research paper strike on using two different approaches of ensemble algorithms the stacking and voting approaches with different unique datasets. The testing phase demonstrates an impressive accuracy rate of approximately 80.4% in the stacking approach and 82.6% for the voting ensemble learning.