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: | Xavier Cadet |
| Institution: | Imperial College London |
| Department: | UKRI CDT |
| Country: | |
| Proposed Analysis: | Multi-modal machine learning of large-scale genomic, proteomic, metabolomic, and neuroimaging data to identify upstream biological mechanisms leading to Alzheimer’s disease and dementia Novel insights into mechanistic pathways leading to Alzheimer’s disease and dementia can be gained by multi-modal analysis of the large-scale population data on genetic composition (genomics), products of biochemical reactions at cellular level (metabolomics and proteomics), and brain imaging features linked with neurodegeneration and dementia. Unlike biostatistical approaches that identify P-value based single-hit linear associations on single genomic and metabolomic platforms, machine learning (ML)/ artificial intelligence (AI) approaches can identify patterns across a multitude of “omics” platforms and provide a comprehensive picture of the molecular mechanisms that can be utilised as therapeutic targets or for risk prediction. The aim of this project is to identify genetic variations linked with cellular biochemical pathways leading to changes in brain structures and neurodegeneration. While several disparate data sources and population-based studies have been available in this space, drawing conclusive inferences across these datasets has been challenging due to the large-scale and heterogeneous nature of these data. To date, AI/ML approaches have been severely underutilised. Biostatistical identification of single genetic hits without simultaneous modelling of the large array of metabolomics data that are markers of the linked biochemical pathways, yields genetic variants that are commonly in non-functional regions of the genome, have weak associations with the disease and do not provide useful insights. Likewise, identification of single metabolomic hits in isolation of the upstream genetic and downstream brain imaging features do not provide meaningful insights into the pathogenesis of dementia. We propose to apply multimodal machine learning/artificial intelligence approaches to identify non-linear patterns across the large array of genomics and metabolomics data with neuroimaging indices to identify biological pathways leading to amyloid deposition, and neurodegeneration (e.g., brain atrophy), associated with cognitive function. |
| Additional Investigators |
