Delivering radiation to eradicate a solid tumor while minimizing damage to nearby critical organs remains a challenge. For esophageal cancer, radiation therapy may damage the heart or lungs, and several qualitatively different, possibly recurrent toxicities associated with chemoradiation or surgery may occur, each at two or more possible grades. In this article, we describe a Bayesian group sequential clinical trial design, based on total toxicity burden (TTB) and progression-free survival duration, for comparing two radiation therapy modalities for esophageal cancer. Each patient's toxicities are modeled as a multivariate doubly stochastic Poisson point process, with marks identifying toxicity grades. Each grade of each type of toxicity is assigned a severity weight, elicited from clinical oncologists familiar with the disease and treatments. TTB is defined as a severity-weighted sum over the different toxicities that may occur up to 12 months from the start of treatment. Latent frailties are used to formulate a multivariate model for all outcomes. Group sequential decision rules are based on posterior mean TTB and progression-free survival time. The proposed design is shown to provide both larger power and smaller mean sample size when compared to a conventional bivariate group sequential design.
Keywords: Bayesian analysis; co-primary endpoints; frailty model; prior elicitation; radiation oncology; sequentially adaptive design; utilities.