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: | Matthew Baucum |
Institution: | University of Tennessee Knoxville |
Department: | Industrial Engineering |
Country: | |
Proposed Analysis: | We hope to use the ADNI data to test the optimal method of predicting Alzheimer's patients cognition scores based on biomarkers and neuroimaging variables. There is little research on how to best predict continuous outcomes (such as cognition scores) over time in disease progression, especially with a time lag. For instance, given a set of patient predictor variables at times n-2, n-1, and n, we seek to identify the best method to predict that patient's cognition score at times n+2, n+3, n+4, etc. The frontrunner methods for such prediction are currently recurrent neural networks and hidden markov models, but each method has drawbacks and it is not known which will allow for optimal prediction of cognition decline. |
Additional Investigators |