Clinical use of current polygenic risk scores may exacerbate health disparities

Abstract

Polygenic risk scores (PRS) are poised to improve biomedical outcomes via precision medicine. However, the major ethical and scientific challenge surrounding clinical implementation of PRS is that those available today are several times more accurate in individuals of European ancestry than other ancestries. This disparity is an inescapable consequence of Eurocentric biases in genome-wide association studies, thus highlighting that-unlike clinical biomarkers and prescription drugs, which may individually work better in some populations but do not ubiquitously perform far better in European populations-clinical uses of PRS today would systematically afford greater improvement for European-descent populations. Early diversifying efforts show promise in leveling this vast imbalance, even when non-European sample sizes are considerably smaller than the largest studies to date. To realize the full and equitable potential of PRS, greater diversity must be prioritized in genetic studies, and summary statistics must be publically disseminated to ensure that health disparities are not increased for those individuals already most underserved.

Figure 1. Ancestry of GWAS participants over time compared to the global population.

Cumulative data as reported by the GWAS catalog. Individuals whose ancestry is “not reported” are not shown.

Figure 2. Demographic relationships, allele frequency differences, and local LD patterns between population pairs.

Data analyzed from 1000 Genomes, in which population labels are: AFR = continental African, EUR = European, and EAS = East Asian. a) Cartoon relationships among AFR, EUR, and EAS populations. b) Allele frequency distributions in AFR, EUR, and EAS populations of variants from the GWAS catalog. c–e) Color axis shows LD scale (r²). LD comparisons between pairs of populations show the same region of the genome for each comparison (representative region is chr1, 51572kb-52857kb) among pairs of SNPs polymorphic in both populations, illustrating that different SNPs are polymorphic across some population pairs, and that these SNPs have variable LD patterns across populations.

Figure 3. Prediction accuracy relative to European ancestry individuals across 17 quantitative traits and 5 continental populations in UKBB.

All phenotypes shown here are quantitative anthropometric and blood panel traits, as described in Supplementary Table 6, which includes discovery cohort sample sizes. Prediction target individuals do not overlap with the discovery cohort and are unrelated, with sample sizes shown in Supplementary Table 7. Violin plots show distributions of relative prediction accuracies, points show mean values, and error bars show standard errors of the means. Prediction R² for each trait and population are shown in Supplementary Figure 12.

Figure 4. Polygenic risk prediction accuracy in Japanese, British, and African descent individuals using independent GWAS of equal sample sizes in the BioBank Japan (BBJ) and UK Biobank (UKBB).

a) Explanatory diagram showing the different discovery and target cohorts/populations, and disease endpoints versus quantitative traits. b–f) Genetic prediction accuracy computed from independent BBJ and UKBB summary statistics with identical sample sizes (Supplementary Tables 6 and 8). Note that y-axes differ, reflecting differences in prediction accuracy. b–c) PRS accuracy for five diseases in: Japanese individuals in the BBJ (b) and British individuals in the UKBB. d–f) PRS accuracy for 17 anthropometric and blood panel traits in: Japanese individuals in the BBJ (d), British individuals in the UKBB (e), and African descent British individuals in the UKBB (f). Trait abbreviations are as in Supplementary Table 6. Each point shows the maximum R² (i.e. best predictor) across five p-value thresholds, and lines correspond to 95% confidence intervals calculated via bootstrap. R² values for all p-value thresholds tested are shown in Supplementary Figures 2–6. Prediction accuracy tends to be higher in the UKBB for quantitative traits than in BBJ and vice versa for disease endpoints, likely because of concomitant phenotype precision and consequently observed heritability for these classes of traits (Supplementary Tables 2–4). Thalassemia and sickle cell disease are unlikely to explain a significant fraction of prediction accuracy differences for blood panels across populations, as few individuals have been diagnosed with these disorders via ICD-10 codes (Supplementary Table 9).