Heart disease is one of the leading causes of death in the globe at present. WHO reports that heart diseases are the leading cause of death worldwide. In clinical data analysis, heart disease prediction is a significant impediment. Machine learning (ML) is a helpful decision-making and forecasting tool for the healthcare industry's vast amounts of data. This study offersCatLOrf, a new approach based on ensemble learning that combines three distinct classification algorithms: CatBoost, Logistic regression, and an Optimized random forest. The test accuracy of CatLOrf is 93.55%, and the test recall is 95.45%. We utilized the kaggle "Heart Disease Analysis and Prediction" dataset, which includes 14 features and over 303 records. In addition, we conducted a thorough exploratory data analysis to determine the significance of each feature in triggering heart disease

Cardiovascular disease, CatLOrf, Machine learning, Optimization, Ensemble.