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: | Vanda Inacio de Carvalho |
Institution: | University of Edinburgh |
Department: | School of Mathematics, Department of Statistics |
Country: | |
Proposed Analysis: | I am developing a new statistical method to evaluate how well a given biomarker, when taking covariate information into account (such as age and gender), distinguishes between three different disease status (e.g., patients with normal cognition, mild dementia, and severe dementia). Specifically, we are developing a method (based on distributional regression/generalised additive models for location, scale, and shape techniques) for ROC surface regression. ROC surfaces are the extension to the three-class case of the popular ROC curve. Although our target for publication is a statistical journal, we realised that some data available under the ADNI initiative would perfect illustrate our new methods. In particular, our biomarker would be the hippocampal volume, the three disease groups would be formed by patients with normal cognition, mild cognition impairment, and Alzheimer disease, and the covariates would be the age and gender of the patients. We would be interested in evaluating, with our proposed method, how the accuracy of the hippocampal volume to discriminate between the three aforementioned groups changes with age and gender. |
Additional Investigators |