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: | Fredrik Johansson |
| Institution: | Chalmers University of Technology |
| Department: | Computer Science & Engineering |
| Country: | |
| Proposed Analysis: | A big question in Alzheimer's disease (AD) research is to what extent AD should be classified in terms of multiple disease types and if so, based on what symptoms or biomarkers. An observation which supports the existence of multiple types of AD is that patients with similar levels of beta-amyloid plaques in the brain still progress in substantially different ways in terms of their symptoms. This begs the question: can we identify prototypical progression trajectories? In this analysis, we will identify such prototype sequences using machine learning methods. These methods will learn representations of patient histories based on what sets the end point of the trajectory apart. For example: what types of trajectories lead up to a rapid decline in cognitive function? Which lead up to a change in diagnosis? We aim for the result of this analysis to be sufficiently interpretable to give new insights into what biomarkers are indicative of the rate of progression of AD. To accomplish this, we will focus on machine learning methods designed to output results which are interpretable by a domain expert in AD. |
| Additional Investigators |
