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: | Sukrut Khot |
Institution: | The University of Sheffield |
Department: | Computer Science |
Country: | |
Proposed Analysis: | Multitask learning is an approach to machine learning that leverages the information present in multiple related tasks to improve the prediction accuracy of each task. In the context of predicting Alzheimer's disease, multitask learning can be applied to make use of various biomarkers that are indicative of the disease and to better model the underlying biological processes that lead to the onset of Alzheimer's. We will use the ADNI dataset to train and test the ML model. The Alzheimer’s Disease Neuroimaging Initiative (ADNI) unites researchers with study data as they work to define the progression of Alzheimer’s disease (AD). ADNI researchers collect, validate, and utilize data, including MRI and PET images, genetics, cognitive tests, CSF, and blood biomarkers as predictors of the disease. One specific technique that can be used for multitask learning in this context is temporal group lasso. The temporal aspect of this approach refers to the fact that the biomarkers being used for prediction are measured at multiple time points, and the group lasso component refers to how the biomarkers are grouped into relevant sets and regularized together to improve the prediction accuracy. The use of temporal group lasso in this context can have several benefits. For example, it can help to account for the fact that Alzheimer's disease is slowly progressive, and that biomarkers may change over time in different ways. Additionally, by grouping biomarkers into relevant sets, and regularizing them together, this approach can help to improve the interpretability of the model and to better understand the underlying biological processes that are associated with Alzheimer's disease. |
Additional Investigators |