This paper introduces an ensemble heuristic–metaheuristic feature fusion learning (EHMFFL) algorithm for heart disease diagnosis using tabular data. The EHMFFL algorithm combines a diverse ensemble learning model with different feature subsets for each base learner, including support vector machine (SVM), K-nearest neighbors (KNN), logistic regression (LR), random forest (RF), naive bayes (NB), decision tree (DT), and XGBoost. The algorithm leverages a combined heuristic–metaheuristic approach that integrates the heuristic knowledge of the Pearson correlation coefficient (PCC) with the metaheuristic-driven grey wolf optimizer (GWO) to identify the most relevant features for each base learner. The second objective is to aggregate the decision outcomes of the various base learners through ensemble learning. The performance of the EHMFFL algorithm is evaluated using the Cleveland and Statlog datasets, yielding remarkable results with an accuracy of 91.8% and 88.9%, respectively, surpassing state-of-the-art techniques in heart disease diagnosis. The algorithm's effectiveness is demonstrated through feature selection using the PCC–GWO algorithm, which selects an optimal feature subset for each machine learning model. The results show that the EHMFFL algorithm outperforms other techniques in terms of accuracy, precision, recall, F1 score, and specificity. The algorithm's performance is also evaluated in terms of running time, with the EHMFFL model showing reduced response times for the base learners compared to the Ensemble model. The correlation heat map (CHM) analysis reveals the relationships between different variables within the cardiovascular data, highlighting the potential of the EHMFFL algorithm in enhancing diagnostic accuracy for heart disease and providing valuable support to clinicians in making more informed decisions regarding patient care.This paper introduces an ensemble heuristic–metaheuristic feature fusion learning (EHMFFL) algorithm for heart disease diagnosis using tabular data. The EHMFFL algorithm combines a diverse ensemble learning model with different feature subsets for each base learner, including support vector machine (SVM), K-nearest neighbors (KNN), logistic regression (LR), random forest (RF), naive bayes (NB), decision tree (DT), and XGBoost. The algorithm leverages a combined heuristic–metaheuristic approach that integrates the heuristic knowledge of the Pearson correlation coefficient (PCC) with the metaheuristic-driven grey wolf optimizer (GWO) to identify the most relevant features for each base learner. The second objective is to aggregate the decision outcomes of the various base learners through ensemble learning. The performance of the EHMFFL algorithm is evaluated using the Cleveland and Statlog datasets, yielding remarkable results with an accuracy of 91.8% and 88.9%, respectively, surpassing state-of-the-art techniques in heart disease diagnosis. The algorithm's effectiveness is demonstrated through feature selection using the PCC–GWO algorithm, which selects an optimal feature subset for each machine learning model. The results show that the EHMFFL algorithm outperforms other techniques in terms of accuracy, precision, recall, F1 score, and specificity. The algorithm's performance is also evaluated in terms of running time, with the EHMFFL model showing reduced response times for the base learners compared to the Ensemble model. The correlation heat map (CHM) analysis reveals the relationships between different variables within the cardiovascular data, highlighting the potential of the EHMFFL algorithm in enhancing diagnostic accuracy for heart disease and providing valuable support to clinicians in making more informed decisions regarding patient care.