Case-control studies for estimation of the natural history of preclinical disease from screening data

Abstract

The duration of the detectable preclinical phase of disease, which we call the sojourn time, is an important quantity to consider when recommending frequency of screens and investigating the natural history of the disease. In this paper, we propose a matched case-control methodology for screening data for joint estimation of the sojourn time distribution and the false negative rate of the screening test. The approach is based on a conditional likelihood for matched sets that involves a comparison of the screening histories of cases and controls. We illustrate the methodology with the data from the Aberdeen screening programme for cervical cancer by the Pap smear. We consider a number of different parametric forms for the sojourn time distribution.