What is it about?
A novel machine learning method for detecting association patterns between the human brain and genome, and their interaction with the Alzheimer's disease status. The approach integrates the innate metabolic and functional structures of the brain and hierarchical structures of the genome, therefore is more powerful in novel association signal discovery and disease pattern prediction.
Featured Image
Photo by David Clode on Unsplash
Why is it important?
This paper is among the pioneer work in machine learning methods implemented to be able to handle both ultrahigh-dimensional response features and ultrahigh-dimensional predictors. It is also the first work that integrates brain anatomical, functional and genome hierarchical structures into disease association pattern detection. By integrating the biological and molecular structures, we were able to detect novel association signals between the brain, the genome, and Alzheimer's disease status.
Perspectives
I hope this method could help with a more precision diagnostics for Alzheimer's progression and transition, by utilizing the high-throughput and high-resolution genomic and neuroimaging data, and by integrating the innate human brain and genome biological structures.
Yanming Li
University of Kansas Medical Center Area Health Education Center
Read the Original
This page is a summary of: A structured brain‐wide and genome‐wide association study using ADNI PET images, Canadian Journal of Statistics, February 2021, Wiley,
DOI: 10.1002/cjs.11605.
You can read the full text:
Contributors
The following have contributed to this page
