eng Oriental Scientific Publishing Company Biomedical and Pharmacology Journal 0974-6242 2026-10-29 19 4 73859 article Sushreeta Tripathy 1 Usha Manasi Mohapatra 2 Sumant Sekhar Mohanty 3 Sanjivani Bhuyan 4 Binod Kumar Pattanayak 4 Department of CA, S’O’A Deemed to be University, Bhubaneswar, India Department of CS, Gangadhar Meher University, Sambalpur, India School of computer science, Odisha University of Technology and Research, Bhubaneswar, India Department of CSE, S’O’A Deemed to be University, Bhubaneswar, India  Heart-related issues rank among the top causes of global mortality. While health professionals are essential for confirming heart risks, expert systems can aid in the diagnostic process. Aiming to design a system that can identify the risk of heart diseases from the data, this paper examines the binary classification of heart disease data using a mix of ensemble and traditional ML approach. This study tests ensemble learning, including Gradient Boosting Classifier and Random Forest( RF), alongside methods like kNN, SVM and Logistic Regression for classification of data into two classes. The above mentioned algorithms are computed based on various classification performance metrics. Results show that Random Forest achieves 100% accuracy and yields the highest area-under-curve value compared to other predictive technique. RF exhibits better performance compared to other algorithms for the data under study. The performance of Random Forest may be experimented on real-time data in the future study. https://biomedpharmajournal.org/vol19no4/a-comparative-assessment-of-ensemble-classifiers-in-prediction-of-heart-disease/ Classification Coronary Artery Disease Ensemble Learning Heart Disease Machine Learning Random Forest