DTR-package: Estimation and comparison of dynamic treatment regimes (DTRs) from sequentially randomized clinical trials

Description

This is a package for the estimation and comparison of survival distributions of dynamic treatment regimes (DTRs) from sequentially randomized clinical trials. In a sequentially randomized design, patients are initially randomized to one of the first-stage therapies. Based on their responses to the first-stage therapy, they are then randomized to one of the second-stage therapies. The second-stage therapy could be a rescue therapy if the response is not favorable, or maintenance therapy if favorable response is achieved. There are treatment sequences resulted from such designs: first-stage therapy -> response -> second-stage therapy. The treatment sequences are also referred to as dynamic treatment regimes (DTRs) or adaptive treatment strategies or treatment policies in the literature. The estimation functions include LDTestimate, WRSEestimate, and CHRestimate. The comparisons functions include contrast_wald, contrast_chr, PHfit, contrast_ph, and contrast_logrank. The functions for data simulation include simLDTdata, simWRSEdata, simPHdata, simCHRdata, and simLRdata.

Arguments

Details

In sequentially randomized designs, there could be more than two therapies available at each stage. For simplicity, and to maintain similarity to the most common sequentially randomized clinical trials, a simple two-stage randomization design allowing two treatment options at each stage is used in the current version of the package. In detail, patients are initially randomized to either A1 or A2 at the first stage. Based on their response status, they are then randomized to either B1 or B2 at the second stage. Therefore, there are a total of four DTRs: A1B1, A1B2, A2B1, and A2B2.

The function simLDTdata generates data sets from sequentially randomized clinical trials as described in the simulation study of Lunceford, Davidian and Tsiatis (2002). The function LDTestimate computes the estimates of the survival function and their estimated standard errors for DTRs at observed event times as proposed in Lunceford, Davidian and Tsiatis (2002) Equation (3) and Equation (10).

The function simWRSEdata generates data sets from sequentially randomized clinical trials as described in the simulation study of Guo and Tsiatis (2005). The function WRSEestimate computes the weighted risk set estimator (WRSE) of the survival function and their estimated standard errors for DTRs at observed event times as proposed in Guo and Tsiatis (2002) Equation (3) and Equation (16).

The function contrast_wald compares the survival distributions of dynamic treatment regimes (DTRs) from sequentially randomized clinical trials based on the LDT estimator proposed in Lunceford, Davidian and Tsiatis (2002) or the WRSE estimator proposed in Guo and Tsiatis (2005) using the Wald-type tests.

The function simPHdata generates a data set from sequentially randomized clinical trials as described in the simulation study of Tang and Wahed (2011). The function PHfit fits a generalized Cox model as proposed in Tang and Wahed (2011). The function contrast_ph compares the survival distributions (i.e. hazard functions) of dynamic treatment regimes (DTRs) from sequentially randomized clinical trials after adjustment for covariates as proposed in Tang and Wahed (2011).

The function simCHRdata generates a data set from sequentially randomized clinical trials as described in the simulation study of Tang and Wahed (2013) [Epub ahead of print]. The function CHRestimate computes the estimates for the cumulative hazard ratios (CHRs) between two different dynamic treatment regimes (DTRs) and their variance estimates at given time points as proposed in Tang and Wahed (2013) [Epub ahead of print]. The function contrast_chr compares the cumulative hazard functions of dynamic treatment regimes (DTRs) from sequentially randomized clinical trials by calculating the natural logarithms of cumulative hazard ratios (CHRs) and performing the Wald-type tests based on natural logarithms of CHRs as proposed in Tang and Wahed (2013) [Epub ahead of print].

The function simLRdata generates a data set from sequentially randomized clinical trials as described in the simulation study of Kidwell and Wahed (2013). The function contrast_logrank compares the survival distributions of dynamic treatment regimes (DTRs) from sequentially randomized clinical trials using the weighted logrank tests as proposed in Kidwell and Wahed (2013).

Package:

DTR

Type:

Package

Version:

1.7

Date:

2015-12-25

License:

GPL (>=2)

References

Tang X, Melguizo M: DTR: An R Package for Estimation and Comparison of Survival Outcomes of Dynamic Treatment Regimes. Journal of Statistical Software 65(7):1-28 2005 http://www.jstatsoft.org/v65/i07/ Lunceford JK, Davidian M, Tsiatis AA: Estimation of survival distributions of treatment policies in two-stage randomization designs in clinical trials. Biometrics 58:48-57, 2002 Guo X: Statistical analysis in two-stage randomization designs in clinical trials. PhD thesis, Department of Statistics, North Carolina State University, 2005 Guo X, Tsiatis AA: A weighted risk set estimator for survival distributions in two-stage randomization designs with censored survival data. Int. J. Biostatistics 1:1-15, 2005 Feng W, Wahed AS: Supremum weighted log-rank test and sample size for comparing two-stage adaptive treatment strategies. Biometrika 95:695-707, 2008 Tang X, Wahed AS: Comparison of treatment regimes with adjustment for auxiliary variables. Journal of Applied Statistics 38(12):2925-2938, 2011 Kidwell KM, Wahed AS: Weighted log-rank statistic to compare shared-path adaptive treatment strategies. Biostatistics, 14(2):299-312, 2013 Tang X, Wahed AS: Cumulative hazard ratio estimation for treatment regimes in sequentially randomized clinical trials. Statistics in Biosciences, 2013 [Epub ahead of print]

Description

Arguments

Details

References

See Also