×
  • Select the area you would like to search.
  • ACTIVE INVESTIGATIONS Search for current projects using the investigator's name, institution, or keywords.
  • EXPERTS KNOWLEDGE BASE Enter keywords to search a list of questions and answers received and processed by the ADNI team.
  • ADNI PDFS Search any ADNI publication pdf by author, keyword, or PMID. Use an asterisk only to view all pdfs.

Active Investigations

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: Reshawn Ramjattan
Institution: University of the West Indies
Department: Computing and IT
Country:
Proposed Analysis: We plan to explore the application of machine learning, explainable AI and optimization techniques to the classification and genetic association of Alzheimer's disease. More specifically, we plan to explore the following questions in order of priority: 1. Can we use explainable AI techniques (such as those that produce saliency maps of feature importance like DeepExplain) to gain transparency into classification models and potentially discover genetic associations from combinations of low p-value SNPs? 2. Can we formulate SNP association as an optimization problem and utilize GPU-accelerated data science pipelines (such as RAPIDS using our lab's Nvidia sponsored GPU) to discover genetic associations from combinations of low p-value SNPs? 3. How does the use of new deep learning architectures (such as vision transformers, DenseNet, EfficientNet and adversarial autoencoders) for early detection compare to the state of the art? Are there architectural changes specific to this problem that can improve performance? 4. Can we use generative techniques (GANs) and other datasets to produce synthetic data that can help address any (if any) lack of minority representation or demographic diversity? If given the genetic and clinical data of individuals with uncommon and common attributes, can we use the data of individuals with common attributes to produce a synthetic set with uncommon attributes? 5. Using data visualization of patterns extracted from the latent space these ML techniques produce, can we find brain-inspired ideas for loss functions in artificial continual-learning algorithms?
Additional Investigators