Deep Learning Approach for Analysis of Audio for the Diagnosis of Alzheimer

Alzheimer's disease (AD) is a weakening neurodegenerative disorder that affects millions of individuals worldwide. This research work aims to redefine Alzheimer's disease (AD) diagnosis by utilizing deep learning models such as Convolutional Neural Networks (CNN) and Long Short-Term Memory networks (LSTM), which analyze the speech patterns. These algorithms detect AD non invasively from audio inputs, focusing on Mel-Frequency Cepstral Coefficients (MFCCs) as indicative speech patterns. With an impressive of 79% accuracy and minimal loss of 2.06, surpassing existing research works, this model exhibit significant innovation in AD detection. i By prioritizing these elements, the initiative not only advances the field but also ensures practical applicability and scalability of the developed models. This research work leads to earlier detection and more effective treatment strategies for individuals affected by this Alzheimer’s Disease.