Alzheimer’s Disease (AD) is an immedicable neurodegenerative disease that collective deteriorate the cognitive functions of humankind, predominantly among the elderly persons, ultimately resulting to be fatal. Early diagnosis of AD plays a significant role to make a timely decision on the therapeutic choices. This article reports on artificial intelligence-based ensemble classifier model for the diagnosis of AD. In this research, a new composite and comprehensive classification schemes for MRI termed as Progressive Ensemble Machine Learning Models for Alzheimer Disease Prediction using (PEM- ADP) stacked ensemble classifier combines five different machine learning algorithms: Extreme Gradient Boosting (XGB), K-Nearest Neighbours (KNN), Support Vector Machine (SVM), Extra Trees Classifier (ETC), and Gradient Boosting Machine (GBM). The Open Access Series of Imaging Studies (OASIS) for T1-Weighted MRI images are used; each of these models was assessed separately and in four distinct ensemble combinations. The performance of these models was ascertained using the metrics viz., Accuracy, Precision, Recall, and F1-Score. The outcomes show that the stacked ensemble models have performed consistently better than the individual classifiers and their combinations. The increased classification accuracy demonstrates the merit of ensemble methods to improve the precision of MRI-based Alzheimer's disease (AD) diagnosis.