Advancing Precision Medicine through Bayesian Methods: Opportunities and Challenges

A Bayesian method will be presented for personalized treatment selection in settings where data are available from a randomized trial with multiple outcomes. The motivating application is a trial that compared the combination letrozole plus bevacizimab (L+B) to letrozole alone (L) as first-line therapy for hormone receptor positive advanced breast cancer. The trial's data showed that L+B was associated with longer progression-free survival (PFS) time, but also a much higher rate of severe toxicities. To address the problem of selecting a future patient's treatment based on the trial's data and the future patient's covariates, collaborating physicians who treat advanced breast cancer patients constructed a joint utility function of PFS time, total toxicity burden (TTB), and patient prognostic covariates. The construction was guided by their clinical experiences. To estimate joint effects of treatment and covariates on PFS time and TTB, a multivariate Bayesian nonparametric regression model was fit to the data. Using the fitted model, a future patient's treatment may be selected by maximizing the posterior predictive mean utility, computed using the patient's covariates. Posterior inferences showed that, based on this utility function, the optimal treatment for a given patient depends on their age. 

Assessing the long-term benefits of new treatments can be expensive and time-consuming, particularly in disease areas with unmet medical needs. While platform trials enable the evaluation of multiple interventions simultaneously, they currently cannot assess studies involving multiple agents and doses or utilize longitudinal biomarkers in decision-making. We propose a Bayesian biomarker-assisted platform design that offers a unified framework for evaluating multiple investigational agents and their doses in a multi-stage, randomized controlled trial. The design streamlines the drug evaluation process and decreases development costs by including proof-of-concept, futility and superiority monitoring, and dose optimization in a single trial, while avoiding over-allocating patients to a shared placebo or active control arm. To facilitate making real-time interim group sequential decisions, temporarily unobserved long-term responses are estimated from longitudinal biomarker measurements. Design parameters and the maximum sample size are fine-tuned to achieve good frequentist properties. The proposed design is illustrated by a trial of three targeted agents for systemic lupus erythematosus, evaluated by their 24-week response rates. Extensive simulations show that the proposed design compares favorably to several conventional platform designs.