Each week, we will be publishing layman’s abstracts of new articles from our prestigious portfolio of journals in statistics. The aim is to highlight the latest research to a broader audience in an accessible format.

The article featured today is from Statistics in Medicine, with the full article now published in Volume 40, Issue 6 and available to read here.

Baker, SG. Modeling the mean time to interval cancer after negative results of periodic cancer screening. Statistics in Medicine. 2021; 40: 1429–1439. https://doi.org/10.1002/sim.8849

The definitive evaluation of cancer screening requires a randomized trial with follow-up to determine a cancer mortality endpoint.   These trials are expensive and long-term.  This paper describes a method to draw preliminary conclusions about cancer screening from periodic cancer screening with short-term follow-up and no control group.  The key idea is to model the mean time until development of interval cancers, which are cancers detected symptomatically between screens or after the last screen.  The method gives reasonably precise estimates of mean lead time when the true mean lead time is short or when investigators know that screening has a high probability of detecting preclinical cancer. Application of the method to persons receiving annual lung cancer screening in the Prostate, Lung, Colorectal, and Ovarian trial indicated a mean lead time less than 1 year. The results suggest that investigators consider the possibility of more frequent screening for lung cancer.