Brain Functional Connectivity Analysis of fMRI-based Alzheimer's Disease Data

Badar Almarri ^* Maitha Alarjani ^*

• King Faisal University, Al-Ahsa, Saudi Arabia

The rising incidence of Alzheimer's disease (AD) due to an aging population presents a major public health challenge. Accurate differentiation between stages of AD remains difficult, owing to limited variability within each stage and the potential for errors in manual classification. To address this, we propose a precise and systematic framework for classifying AD stages. Utilizing datasets from the OASIS and AD Neuroimaging Initiative, which include meticulously verified fMRI scans, we focus on functional connectivity analysis through regions of interest (ROIs).Multivariate Pattern Analysis (MVPA) is employed to extract features that capture the intricate patterns of functional connectivity within the brain. These features serve as inputs to an Extreme Learning Machine (ELM) model for classification. The model's performance is evaluated using comprehensive assessment metrics to ensure robustness and reliability. This research highlights the effectiveness of the proposed approach in accurately distinguishing between various stages of AD, offering potential improvements in diagnostic precision and disease management.