Alzheimer’s disease (AD) is a progressive neurological condition that impacts elderly people leading to memory loss, cognitive decline, and eventually loss of independence. It is vital for diagnosing AD early to manage the disease and halt its progression. Automating the identification and diagnosis of AD utilizing neuroimaging data from MRI, CT, and PET scans has shown promise owing to recent developments in deep learning. However, the majority of current models focus on either recurrent neural networks (RNN) or convolutional neural networks (CNN), each of which has drawbacks of its own. The hybrid deep learning (DL) model proposed in current investigation combines CNN and RNN architectures to improve the precision and resilience of AD diagnosis.