Clinical abnormalities are diseases that affect body parts and can be caused by a variety of causes, such as genetics and lifestyle. Heart disease is one of the leading causes of mortality and a major risk factor due to the rising global frequency of diseases. Clinical data analysis makes the prediction of cardiovascular illness a challenging task. Machine learning (ML) has shown promise for forecasting and decision-making in the healthcare industry. In our proposed model, we have included some different Computational Intelligence Principle (CIP) for coronary artery heart disease forecasting: Gaussian Naive Bayes (GNB) Classifier, K-Nearest Neighbors Classifier (K-NNC), Random Forest Classifier (RFC), AdaBoost Classifier (ABC). These all CIPs are included at level0 of our proposed novel stacking model used for learning at the initial stage. Then all the outcomes of these initial stages are supplied to the level1 of our proposed model where we have included another CIP i.e., Logistic Regression (LR) which complete the stack for final prediction. All these models are combined in ensemble model with stacking strategy to improve the prediction accuracy. Dataset of heart disease which was used in this study was taken from the UCI machine learning repository’s Cleveland Clinic. The experiment concluded with a better accuracy of 86.957%. After integrating the power of all the models, we have achieved a great precision and recall of 83.333% and 90.909% respectively. This also emphasizes the usefulness of the hybrid classifier.