To gain insight into the genetic underpinnings that lead to the initial development of aortic stenosis, a team of researchers from UC San Francisco and the Broad Institute of MIT and Harvard conducted a study analyzing genetic associations with aortic valve measurements in a healthy population. The researchers developed a deep learning-based model to estimate aortic valve measurements from MRI data and used these MRI-derived measurements to reveal the common genetic variation underlying aortic valve function and its potential associations with aortic stenosis.
Using deep learning to measure normal variation in aortic valve function helped us to identify 134 loci associated with aortic stenosis risk and 166 with aortic valve stenosis or function. We observed strong associations between aortic stenosis risk and coronary artery disease, lipoprotein biology, and phosphate handling, suggesting future avenues for research to prevent the development or progression of aortic stenosis.
【MORE】