Alzheimer’s Disease (AD) is a fast-progressing neurodegenerative condition with limited treatment options, making early and accurate diagnosis incredibly important for managing the disease and exploring potential therapies. This research project focuses on using machine learning which may help to detect Alzheimer’s at its early stages, with a special emphasis on identifying Mild Cognitive Impairment (MCI), which is often the first sign of the disease. We developed a machine learning model that combines Convolutional Neural Networks (CNN) with Support Vector Machines (SVM) to analyze MRI scans for signs of AD. Using data from the ADNI database, we evaluated the performance of our model and compared it with existing approaches—highlighting limitations in current methods related to accuracy and real-world applicability. Our model achieved an accuracy of 93.59%. While some other models may report slightly higher accuracy, ours stands out due to its robustness and practical effectiveness. By training on a large dataset, we successfully reduced the risk of underfitting and overfitting, making our model more reliable in real-world diagnostic scenarios. Ultimately, this model could significantly enhance the early detection of Alzheimer’s Disease, enabling quicker intervention and paving the way for more personalized treatment strategy.