Cumulative impact of common genetic variants and other risk factors on colorectal cancer risk in 42,103 individuals

Abstract

Objective: Colorectal cancer (CRC) has a substantial heritable component. Common genetic variation has been shown to contribute to CRC risk. A study was conducted in a large multi-population study to assess the feasibility of CRC risk prediction using common genetic variant data combined with other risk factors. A risk prediction model was built and applied to the Scottish population using available data.

Design: Nine populations of European descent were studied to develop and validate CRC risk prediction models. Binary logistic regression was used to assess the combined effect of age, gender, family history (FH) and genotypes at 10 susceptibility loci that individually only modestly influence CRC risk. Risk models were generated from case-control data incorporating genotypes alone (n=39,266) and in combination with gender, age and FH (n=11,324). Model discriminatory performance was assessed using 10-fold internal cross-validation and externally using 4187 independent samples. The 10-year absolute risk was estimated by modelling genotype and FH with age- and gender-specific population risks.

Results: The median number of risk alleles was greater in cases than controls (10 vs 9, p<2.2 × 10(-16)), confirmed in external validation sets (Sweden p=1.2 × 10(-6), Finland p=2 × 10(-5)). The mean per-allele increase in risk was 9% (OR 1.09; 95% CI 1.05 to 1.13). Discriminative performance was poor across the risk spectrum (area under curve for genotypes alone 0.57; area under curve for genotype/age/gender/FH 0.59). However, modelling genotype data, FH, age and gender with Scottish population data shows the practicalities of identifying a subgroup with >5% predicted 10-year absolute risk.

Conclusion: Genotype data provide additional information that complements age, gender and FH as risk factors, but individualised genetic risk prediction is not currently feasible. Nonetheless, the modelling exercise suggests public health potential since it is possible to stratify the population into CRC risk categories, thereby informing targeted prevention and surveillance.

Figure 1. Distribution of risk by allele number

Odds ratios (95% CI) for each specific number of risk alleles are shown by diamonds, using 9 alleles as the reference (A). Odds ratios (95% CI) for thresholds of risk alleles are indicated by squares (thus risk associated with carrying 10 alleles and more is compared to 9 alleles and less, and so on). Allele frequency distribution in cases and controls from all populations used in generating the models is shown in columns. Data are shown in tabular form (B) for odds ratios for number of risk alleles and partitioned by various thresholds of risk alleles.

Figure 2. Box plot of risk alleles in case and control subjects by study

Box plot of number of risk alleles in case and control subjects for each study population used in the generation and internal validation of the risk models (A) and in the external validation sets from Sweden and Finland (B). Median number of risk alleles for cases and controls combined is indicated by a heavy black line. Mean number of alleles in cases by fine solid grey line and broken grey line for controls. There was a marginal difference in median number of risk alleles (9 versus 10) in DACHs compared to other populations, but the difference in mean number of alleles between cases and controls was similar to that in all other populations.

Figure 3

Variation in predicted probability of CRC (n=39,266) for a given number of risk alleles in the logistic regression model incorporating genotype data.

Figure 4

ROC curves assessing the discriminative ability of the logistic regression model incorporating only genotype data for the 10 risk SNPs (A) (39,266 subjects) and of a model incorporating genotype data for the 10 SNPs along with age, FH status and gender (B) (11,324 subjects). Mean ROC is plotted and the spread of the estimates shown as a box-plot along the ROC curve is shown for A and B. External validation comprised analysis of genotype data from 3,067 Swedish subjects (C) and 1,120 Finnish subjects (D).

Figure 5. Estimated absolute 10-year CRC risk

10-year absolute risk for cancer-free males (A) and females (B) within the general population carrying >12,>13, >14 risk alleles using 2006 Scottish population estimates (1,310,552 males, 1,441,245 females aged ≥35yrs) using a Bayesian risk modelling approach. The rationale for assessing risk associated with carriage of various numbers of alleles is based on population frequency of that number of alleles and the associated risk (see Figure 1). 10 years is taken as the predicted risk period because it is reasonable to expect colonoscopy to influence CRC stage, mortality and/or incidence over that timescale. Cumulative probability is estimated from 1−exp(−cumulative rate) and the absolute risk in the next 10 years obtained by subtraction of the estimated cumulative risk up to the current age from the estimated cumulative risk for 10 years older than the current age. Risk is shown for males and females in each age group in the average risk population, FH+ subgroups, and by genotype groups (note scale difference in plotting male and female risks).