×
  • 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: Jacqueline Maasch
Institution: Cornell University
Department: Computer Science
Country:
Proposed Analysis: I am a second-year PhD student researcher in Computer Science at Cornell Tech. My principal investigator, Dr. Fei Wang (https://wcm-wanglab.github.io/), has multiple ongoing research projects on neurodegenerative disorders. This work takes Alzheimer’s Disease (AD) as a case study in causal discovery for complex pathologies in the setting of latent confounding and small sample size. Preliminary results from our group suggest that causal discovery in the presence of latent confounders can infer an imperfect yet clinically insightful causal structure for the AD phenome. Many challenges arise in phenotypic causal discovery for AD, including 1) the diverse and numerous variables hypothesized to impact this complex disease, 2) the heterogeneity of AD phenotypes both across patients and within patients over time, and 3) limited dataset size. Access to rich, longitudinal, and multi-modal AD data can help mitigate these challenges. The goals of the first stage of this work are to 1) infer the presence of latent confounding in this low data regime and 2) propose means of deconfounding the predicted phenotypic causal graph. This will inform longer-term efforts in proposing a theoretically sound causal structure for the AD phenome and in developing new machine learning methods for causal discovery under limited data regimes. By proposing causal relations on which to intervene, a credible causal graph could inform hypotheses to test in controlled experiments. Clinical insights derived from such experiments could ultimately inform disease-modifying drug discovery or improve symptom management.
Additional Investigators