The natural history of lung cancer in a periodically screened population

Abstract

A mathematical model of the progression kinetics of lung cancer in a periodically screened population is proposed and data collected by the Memorial Sloan-Kettering Cancer Center in New York are used for parameter estimation. It is assumed that the development of adenocarcinoma of lung is a stochastic process with two stages, early and advanced, characterized by mean times, detection probabilities, and cure probabilities. Confidence regions of these parameters are estimated using a number of novel techniques. It is found, surprisingly, that the mean duration of the early stage is at least 4 years, the detectability less than .2, and the curability less than .5. These estimates imply that annual radiographic screening from age 45 to 80 might decrease mortality from adenocarcinoma of lung by something less than 20%.