摘要：Personalized medicine, whereby treatments are tailored to a specific patient rather than a general disease or condition, is an area of growing interest in the fields of biostatistics, epidemiology, and beyond. Dynamic treatment regimens (DTRs) are an integral part of this framework, allowing for personalized treatment of patients with long-term conditions while accounting for both their present circumstances and medical history. The identification of the optimal DTR in any given context, however, is a non-trivial problem, and so specialized methodologies have been developed for that purpose. Here we introduce the R package DTRreg which implements two regression-based approaches: G-estimation and dynamic weighted ordinary least squares regression. We outline the theory underlying these methods, discuss the implementation of DTRreg and demonstrate its use with hypothetical and real-world inspired simulated datasets.
关键词：adaptive treatment strategies;dynamic treatment regimens;dynamic weighted ordinary least squares;G-estimation;personalized medicine
