Alzheimer’s disease is the leading cause of dementia, resulting in severe memory loss and a decline in the ability to perform everyday activities. Effective treatment of Alzheimer’s disease (AD) can be assisted by early detection. This study provided hybrid Deep learning models employing Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM). This model effectively recognizes patterns in the EEG dataset, offering both spatial and temporal data. The Open Nuro EEG dataset, which contains resting-state EEG recordings from persons suffering with AD, frontotemporal dementia, and cognitive normal controls, was employed to train and evaluate the proposed approach. This model provides better performance in differentiating between healthy control and Alzheimer’s patients. According to the proposed strategy, research results shows that the suggested method obtains an accuracy of 92%. Performance measurements such as precision, recall, F1-score, and AUC highlight the quality of the approach. Overall, the integration of CNN and LSTM models offers a excellent tool for robust detection of AD. This methodology has a lot of opportunities for applications in medicine.