A predictive analysis framework of heart disease using machine learning approaches

Heart diseaseis among the leading causes for death globally. Thus, early identification and treatment are indispensable to prevent disease. In this work, we propose a framework based on machine learning algorithms tackle such problems through of risk variables associated To ensure success our proposed model, influential data pre-processing transformation strategies used generate accurate training model that utilizes five most popular datasets (Hungarian, Stat log, Switzerland, Long Beach VA, Cleveland) from UCI. The univariate feature selection technique is applied identify essential features during phase, classifiers, namely extreme gradient boosting (XGBoost), support vector (SVM), random forest (RF), (GB), decision tree (DT), deployed. Subsequently, various performance evaluations measured demonstrate predictions using introduced algorithms. inclusion Univariate results indicated DT classifier achieves comparatively higher accuracy around 97.75% than others. approach recognize, can predict heart disease with high accuracy. Furthermore, 10 attributes chosen analyze model's outcomes explainability, indicating which more significant in outcome.