Estimation of age-specific sensitivity and sojourn time in breast cancer screening studies

This study investigates statistical approaches to quantitatively describing the age effect on screening sensitivity and sojourn time distribution in breast cancer screening studies. Such an investigation is directly motivated by the need to understand the inherent relationships between age and these important quantities. We incorporate the age effect through generalized linear models under a progressive disease modelling framework and obtain the corresponding parameter estimators using the maximum likelihood method. Among a set of potential models, we use Akeike's information criterion and likelihood ratio test in model selection and inferences. Extensive simulation studies show that the estimators have reasonable accuracy and the model selection criterion works well. The proposed methods are illustrated using data from two large breast cancer screening trials. The results show that the screening sensitivity increases with age at screening examinations based on these two trials.