Genomic Risk Profiling of Ischemic Stroke: Results of an International Genome-Wide Association Meta-Analysis

Introduction: Familial aggregation of ischemic stroke derives from shared genetic and environmental factors. We present a meta-analysis of genome-wide association scans (GWAS) from 3 cohorts to identify the contribution of common variants to ischemic stroke risk. Methods: This study involved 1464 ischemic stroke cases and 1932 controls. Cases were genotyped using the Illumina 610 or 660 genotyping arrays; controls, with Illumina HumanHap 550Kv1 or 550Kv3 genotyping arrays. Imputation was performed with the 1000 Genomes European ancestry haplotypes (August 2010 release) as a reference. A total of 5,156,597 single-nucleotide polymorphisms (SNPs) were incorporated into the fixed effects meta-analysis. All SNPs associated with ischemic stroke (P < 1 x 10(-5)) were incorporated into a multivariate risk profile model. Results: No SNP reached genome-wide significance for ischemic stroke (P < 5 x 10(-8)). Secondary analysis identified a significant cumulative effect for age at onset of stroke (first versus fifth quintile of cumulative profiles based on SNPs associated with late onset, beta = 14.77 [10.85, 18.68], P = 5.5 x 10(-12)), as well as a strong effect showing increased risk across samples with a high propensity for stroke among samples with enriched counts of suggestive risk alleles (P < 5 x 10(-6)). Risk profile scores based only on genomic information offered little incremental prediction. Discussion: There is little evidence of a common genetic variant contributing to moderate risk of ischemic stroke. Quintiles based on genetic loading of alleles associated with a younger age at onset of ischemic stroke revealed a significant difference in age at onset between those in the upper and lower quintiles. Using common variants from GWAS and imputation, genomic profiling remains inferior to family history of stroke for defining risk. Inclusion of genomic (rare variant) information may be required to improve clinical risk profiling.