AUTHOR=Alarjani Maitha , Almarri Badar 

TITLE=Multivariate pattern analysis of medical imaging-based Alzheimer's disease

JOURNAL=Frontiers in Medicine

VOLUME=Volume 11 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2024.1412592

DOI=10.3389/fmed.2024.1412592

ISSN=2296-858X

ABSTRACT=Alzheimer's disease (AD) is a devastating brain disorder that steadily worsens over time. It is marked by a relentless decline in memory and cognitive abilities. As the disease progresses, it leads to a significant loss of mental function. Early detection of AD is essential to start treatments that can mitigate the progression of this disease and enhance patients' quality of life. This study aims to observe AD's brain functional connectivity pattern to extract essential patterns through multivariate pattern analysis (MVPA) and analyze activity patterns across multiple brain voxels. The optimized feature extraction techniques are applied to identify the important features for performing the training on the models using several hybrid machine learning classifiers for performing binary classification and multi class classification. The proposed approach using hyrbrid machine learning classification has been applied on two public datasets named as Open Access Series of Imaging Studies (OASIS) and AD Neuroimaging Initiative (ADNI). The results are evaluated using performance metrics and comparison has been done to differentiate between different stages of AD using visualization tools.