Sample size calculation

The sample size is estimated based on the results of the preliminary study including participants from CRC screening with self-reported acetylsalicylic acid use [7]. Accounting for an expected loss of data of about 20% and with an expected prevalence of advanced neoplasms of 10%, 100 advanced neoplasms are expected in each of the two groups. Assuming a sensitivity of 36% in the placebo group (as in our preliminary study) and applying 2-sided chi-square tests with continuity correction at an alpha level of 0.05, this trial should have a power of 90% to detect an increase in sensitivity by short term use of low-dose acetylsalicylic acid to 60% in the entire trial population, and a power of 90% to detect an increase in sensitivity to 70% in gender-specific analyses (sensitivity was 71% in our preliminary study [7]). Furthermore, specificity will be estimated at high levels of precision in both groups, with an expected confidence interval ranging from 88 to 92% for a specificity of 90%.