Longitudinal Neuroimaging Data Classification for Early Detection of Alzheimer’s Disease using Ensemble Learning Models
This paper applies Ensemble Learning models for the early detection of Alzheimer’s disease in elderly adults. The publicly available dataset from the Open Access Series of Imaging Studies (OASIS) Database is used. A novel longitudinal MRI data-based machine learning model is proposed in the paper, which takes account of features like- Mini-Mental State Examination (MMSE) score and years of education to make a generalized classifier. Our proposed model achieved a 5-fold cross-validation area under the curve (AUC) score of 89.93% and accuracy of 94.64%. We show that our results quantitatively outperform the state-of-the-art in Alzheimer’s disease detection. We then compared our results to other previous state-of-the-art research and our model’s metrics surpasses them.
Email Address of Submitting Authorst3263@drexel.edu
Submitting Author's InstitutionCollege of Computing and Informatics, Drexel University
Submitting Author's Country
- United States of America