DTRlearn-package: Dynamic Treatment Regimens Learning

In DTRlearn: Learning Algorithms for Dynamic Treatment Regimes

Description

Dynamic treatment regimens (DTRs) are sequential decision rules tailored at each stage by time-varying subject-specific features and intermediate outcomes observed in previous stages. For many complex chronic disorders, DTRs operationalize the sequential process of medical decision-making. Sequential Multiple Assignment Randomized Trials (SMARTs) are proposed to best construct DTRs which offer a causal interpretation of their comparisons through randomization at each critical decision point. Machine learning methods such as O-learning (Zhao et. al. 2012,2014), Q-learning (Murphy et. al. 2007, Zhao et.al. 2009) and P-learning (Liu et. al. 2014, 2015) have been proposed to estimate the optimal individualized treatment from a SMART.

This package implements these 3 main types of algorithms to estimate the optimal DTR. The algorithms consider a continuous outcome (the larger indicates better clinical results), and allow two treatment choices for each stage coded by 1 and -1.

Details

Package:	DTRlearn
Type:	Package
Version:	1.1
Date:	2015-10-26
License:	GPL-2

Author(s)

Ying Liu
Yuanjia Wang
Donglin Zeng

References

Liu, Y., Zeng, D., Wang, Y. (2014). Use of personalized Dynamic Treatment Regimes (DTRs) and Sequential Multiple Assignment Randomized Trials (SMARTs) in mental health studies. Shanghai archives of psychiatry, 26(6), 376. http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4311115/

Liu et al. (2015). Under double-blinded review.

Zhao, Y., Zeng, D., Rush, A. J., & Kosorok, M. R. (2012). Estimating individualized treatment rules using outcome weighted learning. Journal of the American Statistical Association, 107(499), 1106-1118.

Zhao, Y. Q., Zeng, D., Laber, E. B., & Kosorok, M. R. (2014). New statistical learning methods for estimating optimal dynamic treatment regimes. Journal of the American Statistical Association, (just-accepted), 00-00.
Watkins, C. J. C. H. (1989). Learning from delayed rewards (Doctoral dissertation, University of Cambridge).

Murphy, S. A., Oslin, D. W., Rush, A. J., & Zhu, J. (2007). Methodological challenges in constructing effective treatment sequences for chronic psychiatric disorders. Neuropsychopharmacology, 32(2), 257-262.

Zhao, Y., Kosorok, M. R., & Zeng, D. (2009). Reinforcement learning design for cancer clinical trials. Statistics in medicine, 28(26), 3294.

DTRlearn documentation built on April 6, 2018, 1:04 a.m.