Enhancing Heart Disease Prediction and Analysis: An Efficient Voting Ensemble model

The prediction of heart disease is of significant importance in the domain of healthcare, where accurate diagnosis can save lives. In this paper, we propose a proficient model for prediction of heart disease using a Voting Ensemble technique. We employ a integration of Logistic Regression, Decision Tree classifier, and Random Forest classifiers to create a robust predictive model. This ensemble method has shown encouraging results in terms of accuracy and performance. In our experimental analysis, we demonstrate the advantages of our method and offers a comprehensive assessment of its performance on a real-world heart disease dataset. The results highlight the need of ensemble techniques in improving diagnostic accuracy. Our Voting Ensemble model attained an outstanding accuracy of 98% on the test dataset, outperforming individual classifiers. This paper contributes to the advancement of forecasting models for predicting heart disease and provides insights for future investigations in the field of healthcare analytics.

I. Introduction

Heart diseases remains a global health challenge, standing as a leading cause of mortality worldwide. The sheer magnitude of its impact underscores the critical need for prompt and precise diagnosis. According to the reports of World Health Organization (WHO), cardiovascular diseases make up roughly 17.9 million fatalities annually, establishing it as the leading cause of death globally. The heart diseases are highly widespread in both developed and developing nations, transcending geographical and socio-economic-boundaries.