Back

FairPRS: a fairness framework for Polygenic Risk Scores

Machado-Reyes, D.; Bose, A.; Karavani, E.; PARIDA, L.

2022-08-30 genetic and genomic medicine
10.1101/2022.08.28.22279309 medRxiv
Show abstract

Polygenic risk scores (PRS) are increasingly used to estimate the personal risk of a trait based on genetics. However, most genomic cohorts are of European populations, with strong under-representative of multi-ethnic minority groups. Given that PRS poorly transport across racial groups, this has the potential exacerbate health disparities if used in clinical care. Hence there is a need to generate PRS that perform comparably across ethnic groups. Borrowing recent advancements in the domain adaption field of machine learning, we propose FairPRS - an Invariant Risk Minimization (IRM) approach for estimating fair PRS or debiasing pre-computed ones. We test our method on both a diverse set of synthetic data and real data form the UK Biobank. We show our method can create ancestry-invariant PRS distributions that are both racially unbiased and largely improve phenotype prediction. We hope that fair PRS will contribute to fairer characterization of patients by genetics rather than by race.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.