University of Florida
Complex diseases such as cancer have often heterogeneous responses to treatment, and this has attracted much interest in developing individualized treatment rules to tailor therapies to an individual patient according to the patient-specific characteristics. In this talk, we discuss how to use Bayesian neural networks to achieve this goal, including how to select disease related features. The theoretical properties of Bayesian neural networks is studied under the small-n-large-P framework, and simulation is done using the parallel stochastic approximation Monte Carlo algorithm on a multicore computer. The performance of the proposed approach is illustrated via simulation studies and a real data example.