The University of Texas MD Anderson Cancer Center
Department of Biostatistics
My research focuses on the development of novel adaptive designs for clinical trials, including phase I and phase I/II trial designs to find the maximum tolerated dose (MTD), dose-finding designs that accommodate late-onset toxicities, biomarker-based adaptive designs for targeted therapy development, and adaptive randomization that simultaneously balances covariates across treatment arms. I have proposed algorithm-based dose-finding designs that make optimal dose assignment to minimize the probability of inappropriate dose assignment for each patient. I have proposed a Bayesian phase I/II dose-finding trial design that simultaneously accounts for toxicity and efficacy. The majority of the existing adaptive trial designs require the toxicity/efficacy outcomes to be observed quickly, such that by the time of the next dose assignment, the outcomes of the previously treated patients have been completely observed. However, late-onset toxicities are common in phase I dose-finding studies, especially in oncology. To accommodate the settings in which toxicity may occur long after the treatment, I proposed the data-augmentation continual reassessment method for single-agent, dose-finding clinical trials. In recent decades, the rapid advancements in biomedicine have promoted the development of many biologically targeted therapies. These targeted agents, however, may work for only a subpopulation of patients characterized by particular biomarker signatures. We proposed a biomarker-based adaptive trial design to efficiently identify the subpopulation who benefit from the targeted agents of interest. Besides these examples, I am continuing working on statistical methodological research that is motivated by real-world applications.
Education & Training
Ph.D. - The University of Texas School of Public Health - 2012