Ongoing Investigations

ADNI data is made available to researchers around the world. As such, there are many active research projects accessing and applying the shared ADNI data. To further encourage Alzheimer’s disease research collaboration, and to help prevent duplicate efforts, the list below shows the specific research focus of the active ADNI investigations. This information is requested annually as a requirement for data access.

Principal Investigator  
Principal Investigator's Name: Kellie Archer
Institution: The Ohio State University
Department: Division of Biostatistics, College ofPublic Health
Country:
Proposed Analysis: Health status and outcomes, such as quality of life, functional status, and patient satisfaction, are frequently measured on an ordinal scale. For example, participants in the Alzheimer's Disease Neuroimaging Initiative study were classified as cognitive normal control, significant memory concern, early MCI, and late MCI. When a large number of predictors are available, such as in high-throughput genomic datasets, the common approach to analyzing ordinal response data has been to break the problem into one or more dichotomous response analyses. We developed penalized methods for ordinal response modeling in high-dimensional settings. These methods have been demonstrated to have accurate prediction accuracy and includes features monotonically associated with the ordinal response. Our methodology also allows for the inclusion of demographic/clinical characteristics that are already known to be associated with the response into the statistical model with no penalty. Further, it has been adapted to model longitudinally collected ordinal outcomes. We are developing similar penalized methods for discrete response data. Therefore, we plan to (1) apply our penalized ordinal response model to predict participant type (cognitive normal control, significant memory concern, early MCI, late MCI) and investigate features included in our model with respect to biological relevance; (2) identify important discrete/count response features and apply our penalized discrete response models and investigate features included in our model with respect to biological relevance.
Additional Investigators