There are many active research projects accessing and applying shared ADNI data. Use the search above to find specific research focuses on the active ADNI investigations. This information is requested annually as a requirement for data access.
| Principal Investigator | |
| Principal Investigator's Name: | Nikan Amirkhani |
| Institution: | Tehran University of Medical Sciences |
| Department: | Department of Medicine |
| Country: | |
| Proposed Analysis: | Several methods for analyzing tabular data have been used to predict the progression of Alzheimer's dementia. These methods include general additive models (GAMs), decision trees, random forests (RFs), and extreme gradient boosting (XGBoost). TabPFN is a recent transformer-based method for analyzing tabular data that can purportedly perform at the state-of-the-art using less computational power and with no hyperparameter tuning. We propose to test this claim on the classification of cognitively normal, mildly cognitively impaired, and Alzheimer's dementia subjects, as well as identify the most crucial features for said classification. |
| Additional Investigators |
