Alzheimer’s disease (AD) leads to memory loss and cognitive issues, making early detection and treatment essential. This study explores a new approach to identifying AD using medical imaging techniques. It focuses on combining two types of image analysis methods: Convolutional Neural Networks (CNNs) and Vision Transformers (VT). CNNs are well-known for analyzing images by identifying local patterns and details effectively. However, VT models excel at capturing the overall structure and relationships in an image, providing a broader perspective. Inspired by the strengths of both methods, this research introduces a combined approach that integrates CNN and VT to create a more reliable system for detecting Alzheimer’s disease. The hybrid model was tested using data from two well-known Alzheimer’s disease datasets: OASIS and ADNI. Its performance was then compared with leading individual CNN and VT models under various testing conditions. The results showed that this hybrid method outperformed the separate models. It achieved an impressive accuracy rate of 98.5% on one dataset and 99.6% on the other, demonstrating its effectiveness and reliability in diagnosing AD. This study highlights the potential of combining different image analysis techniques to improve medical imaging applications, offering a promising tool for early detection of Alzheimer’s disease.