ENHANCING HEART DISEASE PREDICTION THROUGH ENSEMBLE LEARNING AND FEATURE SELECTION

Abstract

Machine learning techniques are being used extensively in the healthcare field to assist in the early detection and diagnosis of diseases. Prediction of cardiac disease from clinical data is one of the most significant applications of machine learning in healthcare. To develop such a predictive model, data collection, pre-processing, and transformation methods are used to train the model. Feature selection methods such as filter and wrapper are also used to enhance the predictive performance of the model. Classification techniques such as Decision Tree, Logistic Regression, Random Forest, and Ada Boost are used to evaluate the performance of the model. Performance metrics such as accuracy, F1-score, precision, sensitivity, and specificity are used to evaluate the effectiveness of the predictive model. Improvements in these performance metrics indicate that the predictive model is performing better and can help physicians make more informed decisions regarding patient’s health. This study makes an effort to improve the likelihood of heart disease prediction using ensemble learning approaches. It demonstrates the effectiveness of using machine learning and artificial intelligence in predicting heart disease and highlights the importance of feature selection methods in achieving accurate results.