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: | Jillian Ross |
| Institution: | Massachusetts Institute of Technology (MIT) |
| Department: | Electrical Engineering and Computer Science (EECS) |
| Country: | |
| Proposed Analysis: | We seek to analyze multimodal Alzheimer's detection models through a robustness framework to determine which modalities are least fragile to use in a clinical deployment setting. Building upon results from El-Sappagh et al. and others, we will build and train a random forest ensemble model that detects Alzheimer's. Then, we will apply recent work from robustness verification on tree-based models to assess how the random forest ensembles perform when they are trained with different combinations of modalities. |
| Additional Investigators | |
| Investigator's Name: | Alexandra Berg |
| Proposed Analysis: | We seek to analyze multimodal Alzheimer's detection models through a robustness framework to determine which modalities are least fragile to use in a clinical deployment setting. Building upon results from El-Sappagh et al. and others, we will build and train a random forest ensemble model that detects Alzheimer's. Then, we will apply recent work from robustness verification on tree-based models to assess how the random forest ensembles perform when they are trained with different combinations of modalities. |
| Investigator's Name: | Diego Raygoza-Castanos |
| Proposed Analysis: | We seek to analyze multimodal Alzheimer's detection models through a robustness framework to determine which modalities are least fragile to use in a clinical deployment setting. Building upon results from El-Sappagh et al. and others, we will build and train a random forest ensemble model that detects Alzheimer's. Then, we will apply recent work from robustness verification on tree-based models to assess how the random forest ensembles perform when they are trained with different combinations of modalities. |
