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: | Jiayu Huo |
| Institution: | King's College London |
| Department: | School of Biomedical Engineering & Imaging Science |
| Country: | |
| Proposed Analysis: | Title: Simulating Alzheimer's Disease Progression using Generative Models with ADNI Dataset Introduction: Alzheimer's Disease (AD) is a neurodegenerative disorder that affects millions of people worldwide. Although the cause of AD is still not fully understood, early detection and intervention are key to improving patient outcomes. The Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset provides a rich source of longitudinal neuroimaging and clinical data, making it an ideal resource for studying the progression of AD. Objective: The main objective of this research proposal is to use generative models to simulate the progression of AD based on the ADNI dataset. The goal is to develop a tool that can help clinicians and researchers better understand the natural history of AD and evaluate the efficacy of potential treatments. Methodology: The proposed research will use a combination of generative models and longitudinal data from the ADNI dataset to simulate the progression of AD. Specifically, we plan to use deep generative models such as variational autoencoders (VAEs) and generative adversarial networks (GANs) to learn the underlying patterns of disease progression from the ADNI dataset. We will then use these models to simulate the progression of AD in new patients over time. To evaluate the accuracy of our simulations, we will compare the simulated disease progression with actual disease progression in the ADNI dataset. We will use metrics such as the mean absolute error and root mean square error to assess the accuracy of our simulations. Expected Results: The proposed research will provide a better understanding of the natural history of AD and help clinicians and researchers evaluate potential treatments. Our simulations will allow us to test the efficacy of various interventions and identify the optimal time for intervention to occur. Conclusion: The proposed research has the potential to make significant contributions to the field of AD research. By using generative models to simulate the progression of AD, we can gain insights into the underlying mechanisms of the disease and develop more effective interventions. The ADNI dataset provides an ideal resource for this research, and we anticipate that our simulations will provide valuable information for clinicians and researchers alike. |
| Additional Investigators |
