Bayesian estimation of extent of recovery for aspects of verbal memory in women undergoing adjuvant chemotherapy treatment for breast cancer

Abstract

Decline in cognitive function can be experienced by up to 50% of women while undergoing adjuvant chemotherapy with a subset of patients experiencing long-term effects. Bayesian latent basis longitudinal random-effects and latent class growth models were used to assess the degree of verbal memory recovery for learning, immediate retention and delayed recall in women undergoing chemotherapy for early stage breast cancer and who were assessed before, and at 1, 6 and 18 months post chemotherapy. The latent basis model, with the initial time point fixed to 1 and the second to 0, enabled the estimation of the degree of recovery at times 3 and 4. In the single-class model, three prior distributions for the random effects were used, resulting in minimal differences in parameter estimation. These models resulted in a near complete recovery for learning, and 57-60% for immediate retention and delayed recall at 18 months post chemotherapy. A range of two- to five-class Bayesian mixture models were fitted, with classes differing for baseline and degree of recovery. In the three-class model, the 'Low' class indicated 29.0%, 11.0% and 9.6% recovery at 18 months post treatment for the three outcome measures respectively, indicating an extended time of reduced verbal memory function. © 2011 Royal Statistical Society.