Pooled analysis of the effect of aspirin (thick line) versus control (thin line) on subsequent incidence and mortality due to colorectal cancer in all randomized patients (A) in three trials of low-dose aspirin versus placebo, in those with scheduled duration of trial treatment ≥ 2.5 years (B), and in those with scheduled duration of trial treatment ≥ 5 years (C). A, aspirin; C, control. Reprinted from The Lancet, 376, Rothwell P, et al. Long-term effect of aspirin on colorectal cancer incidence and mortality: 20-year follow-up of five randomised trials, 1741-50, Copyright 2010, with permission from Elsevier.