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: | Sofia Yfantidou |
| Institution: | Aristotle University of Thessaloniki |
| Department: | Informatics |
| Country: | |
| Proposed Analysis: | Prior work has introduced personalized Machine Learning and Statistical models for predicting per-subject ADAS-Cog13 cognitive scores – a significant predictor of Alzheimer’s Disease (AD) in the cognitive domain - in the future. Such models operate on the basis of the IID assumption, i.e., that the data are independent and identically distributed. If a model is trained on data from the general population, such assumption can be presumed to hold. However, when we train personalized models, where emphasis is put on the data of a single individual to build the model, their data might violate the independency part of the IID assumption. Our research focus is to examine the effect of potential IID assumption violations in personalized ML, with the ultimate goal of improving prediction accuracy for models predicting future, per-subject ADAS-Cog13 cognitive scores. |
| Additional Investigators |
