The Fred Hutch Biostatistics Program hosts seminars featuring presentations by Fred Hutch and outside scientists to share their latest developments and recent research. Each seminar includes an hour-long presentation and discussion during which speakers showcase their work and findings.
This seminar will be in-person.
Please contact email@example.com if this is not practical and you would like a Zoom link.
In this talk, we present recent advances and statistical learning developments for evaluating Dynamic Treatment Regimes (DTR), which allow the treatment to be dynamically tailored according to evolving subject-level data. Identification of an optimal DTR is a key component for precision medicine and personalized health care. We will first present a tree-based doubly robust reinforcement learning (T-RL) method, which builds a decision tree that maintains the nature of batch-mode reinforcement learning, and then a new Stochastic-Tree Search method called ST-RL, which contributes to the existing literature in its non-greedy policy search and demonstrates outstanding performances even with a large number of covariates. In addition, we consider a common challenge with practical “restrictions” on the treatment sequences: (i) one or more treatment sequences that were offered to individuals when data were collected are no longer considered viable in practice; (ii) specific treatment sequences are no longer available; or (iii) the scientific focus of the analysis concerns a specific type of treatment sequences (e.g., “stepped-up” treatments). To address this challenge, we develop a Restricted Tree-based Reinforcement Learning (RT-RL) method. The method is illustrated using an observational dataset to estimate a two-stage stepped-up DTR for guiding the level of care placement for adolescents with substance use disorder.