Development of Enhanced Deep Learning Ensemble Model for Cardiovascular Disease Prediction

Abstract

The goal of this research study is to better forecast cardiovascular illnesses, a major worldwide health concern, by using an advanced ensemble machine learning model. The ensemble model tries to take advantage of the individual advantages and make up for the disadvantages of the six different algorithms—K Nearest Neighbors, Decision Tree, Support Vector Classifier, AdaBoost, Linear Discriminant Analysis, and Multilayer Perceptron—by combining their capabilities. By boosting the model's capacity to manage the numerous linkages and complex data elements seen in medical datasets, this method improves the accuracy, precision, and dependability of heart disease diagnosis. Our ensemble technique achieves superior performance metrics, such as high accuracy (93.95%), precision (98.00%), and recall (93.00%), as demonstrated by validation against existing models. These findings demonstrate our ensemble model's ability to greatly improve clinical setting patient management and diagnostic procedures, which represents a major advancement in the use of machine learning in healthcare.