Calculation of sample size in trials of screening for early diagnosis of disease.

The calculation of the sample sizes required for trials of screening for disease with the aim of reducing mortality involves the estimation of both the mortality in the control group at intervals after the start of the trial, and the potential reduction due to screening. Since at the start of a screening trial the population is selected to be free of the disease in question, the mortality rate in the control group will differ from that in the general population. A method of estimating this mortality rate using published incidence and survival data is described. The expected reduction in mortality due to screening depends both on the number of, and intervals between, screens and on parameters concerning the natural history of the disease; the means by which these parameters can be estimated are discussed. A trial of screening for colorectal cancer by a faecal occult blood test is used to illustrate these calculations.