Impact of a Panel of 88 Single Nucleotide Polymorphisms on the Risk of Breast Cancer in High-Risk Women: Results From Two Randomized Tamoxifen Prevention Trials

Abstract

Purpose At least 94 common single nucleotide polymorphisms (SNPs) are associated with breast cancer. The extent to which an SNP panel can refine risk in women who receive preventive therapy has not been directly assessed previously. Materials and Methods A risk score on the basis of 88 SNPs (SNP88) was investigated in a nested case-control study of women enrolled in the International Breast Intervention Study (IBIS-I) or the Royal Marsden study. A total of 359 women who developed cancer were matched to 636 controls by age, trial, follow-up time, and treatment arm. Genotyping was done using the OncoArray. Conditional logistic regression and matched concordance indices (mC) were used to measure the performance of SNP88 alone and with other breast cancer risk factors assessed using the Tyrer-Cuzick (TC) model. Results SNP88 was predictive of breast cancer risk overall (interquartile range odds ratio [IQ-OR], 1.37; 95% CI, 1.14 to 1.66; mC, 0.55), but mainly for estrogen receptor-positive disease (IQ-OR, 1.44; 95% CI, 1.16 to 1.79; P for heterogeneity = .10) versus estrogen receptor-negative disease. However, the observed risk of SNP88 was only 46% (95% CI, 19% to 74%) of expected. No significant interaction was observed with treatment arm (placebo IQ-OR, 1.46; 95% CI, 1.13 to 1.87; tamoxifen IQ-OR, 1.25; 95% CI, 0.96 to 1.64; P for heterogeneity = .5). The predictive power was similar to the TC model (IQ-OR, 1.45; 95% CI, 1.21 to 1.73; mC, 0.55), but SNP88 was independent of TC (Spearman rank-order correlation, 0.012; P = .7), and when combined multiplicatively, a substantial improvement was seen (IQ-OR, 1.64; 95% CI, 1.36 to 1.97; mC, 0.60). Conclusion A polygenic risk score may be used to refine risk from the TC or similar models in women who are at an elevated risk of breast cancer and considering preventive therapy. Recalibration may be necessary for accurate risk assessment.

Fig 1.

CONSORT diagram. IBIS-I, International Breast Intervention Study; Marsden, Royal Marsden study; SNPs, single nucleotide polymorphisms.

Fig 2.

(A) Distribution of 88 single nucleotide polymorphisms risk score (SNP88) in cases and controls. (B) SNP88 and Tyrer-Cuzick odds ratios (ORs) for cases and controls; Spearman coefficient 0.012, P = .7, where each interquartile range in controls is represented by the dashed lines. (C) logistic regression fit (gold line) of observed versus predicted ORs from the SNP score in both arms, blue points are estimates from each decile of SNP88 in controls, and the rug plot at the top and bottom gives the observed SNP88 in cases and controls, respectively.