Improving genetic risk prediction across diverse population by disentangling ancestry representations. (arXiv:2205.04673v1 [cs.LG])

Risk prediction models using genetic data have seen increasing traction in
genomics. However, most of the polygenic risk models were developed using data
from participants with similar (mostly European) ancestry. This can lead to
biases in the risk predictors resulting in poor generalization when applied to
minority populations and admixed individuals such as African Americans. To
address this bias, largely due to the prediction models being confounded by the
underlying population structure, we propose a novel deep-learning framework
that leverages …

arxiv population prediction risk