Type: | Package |
Title: | Using Multiple Continuous Biomarkers for Patient Enrichment in Two-Stage Clinical Designs |
Version: | 1.0.1 |
Description: | Enrichment strategies play a critical role in modern clinical trial design, especially as precision medicine advances the focus on patient-specific efficacy. Recent developments in enrichment design have introduced biomarker randomness and accounted for the correlation structure between treatment effect and biomarker, resulting in a two-stage threshold enrichment design. We propose novel two-stage enrichment designs capable of handling two or more continuous biomarkers. See Zhang, F. and Gou, J. (2025). Using multiple biomarkers for patient enrichment in two-stage clinical designs. Technical Report. |
License: | GPL-3 |
Encoding: | UTF-8 |
Depends: | R (≥ 4.2.0) |
Imports: | tmvtnorm (≥ 1.2), stats (≥ 4.0.0) |
RoxygenNote: | 7.3.2 |
NeedsCompilation: | no |
Packaged: | 2025-04-10 15:25:34 UTC; psystat |
Author: | Jiangtao Gou [aut, cre], Fengqing (Zoe) Zhang [aut] |
Maintainer: | Jiangtao Gou <gouRpackage@gmail.com> |
Repository: | CRAN |
Date/Publication: | 2025-04-15 19:30:12 UTC |
Compute the average subpopulation treatment effect and the standardized average subpopulation treatment effect when two biomarkers are involved
Description
Compute the average subpopulation treatment effect and the standardized average subpopulation treatment effect when two biomarkers are involved
Usage
avetrteff2(z1z2, kappa, rhovec, sigma, muminusmu0)
Arguments
z1z2 |
a numeric vector of two numbers that are standardized biomarker values |
kappa |
a number of the correlation coefficient between two biomarkers |
rhovec |
a numeric vector of two correlation coefficients between the output and two biomarkers |
sigma |
a number of the standard deviation of outcome |
muminusmu0 |
a number of the difference between the mean of outcome and the minimal clinically important treatment effect |
Value
a list of three numbers: delta
is the average subpopulation treatment effect, lambda
is the standardized average subpopulation treatment effect, and cVar
is the variance with respect to the truncated distribution with specified cutoff values
Author(s)
Jiangtao Gou
References
Zhang, F. and Gou, J. (2025). Using multiple biomarkers for patient enrichment in two-stage clinical designs. Technical Report.
Examples
x1x2 <- c(2, 1)
nu1nu2 <- c(0,0)
tau1tau2 <- c(1,1)
z1z2 <- (x1x2 - nu1nu2)/tau1tau2
muminusmu0 <- 1.8
kappa <- 0.1
sigma <- 1
rhovec <- c(0.1, 0.2)
avetrteff2(z1z2, kappa, rhovec, sigma, muminusmu0)
Find the cutoff values of biomarkers based on the average subpopulation treatment effect
Description
Find the cutoff values of biomarkers based on the average subpopulation treatment effect
Usage
findATE2(z2interval, kkk, muminusmu0, kappa, rhovec, sigma, cDel)
Arguments
z2interval |
a numeric vector of two values, including the lower and upper limits of the initial interval for z2 |
kkk |
the researchers' weighting preference between the two biomarkers |
muminusmu0 |
a number of the difference between the mean of outcome and the minimal clinically important treatment effect |
kappa |
a number of the correlation coefficient between two biomarkers |
rhovec |
a numeric vector of two correlation coefficients between the output and two biomarkers |
sigma |
a number of the standard deviation of outcome |
cDel |
the desired average subpopulation treatment effect |
Value
a numeric vector of two values which are the cutoff values for z1 and z2
Author(s)
Jiangtao Gou
Fengqing Zhang
References
Zhang, F. and Gou, J. (2025). Using multiple biomarkers for patient enrichment in two-stage clinical designs. Technical Report.
Examples
z2interval <- c(-5, 5)
kkk <- 1
muminusmu0 <- 1.8
kappa <- 0.1
rhovec <- c(0.1, 0.2)
sigma <- 1
cDel <- 2.5
findATE2(z2interval, kkk, muminusmu0, kappa, rhovec, sigma, cDel)
Find the cutoff values of biomarkers based on the standardized average subpopulation treatment effect
Description
Find the cutoff values of biomarkers based on the standardized average subpopulation treatment effect
Usage
findSATE2(z2interval, kkk, muminusmu0, kappa, rhovec, sigma, cLam)
Arguments
z2interval |
a numeric vector of two values, including the lower and upper limits of the initial interval for z2 |
kkk |
the researchers' weighting preference between the two biomarkers |
muminusmu0 |
a number of the difference between the mean of outcome and the minimal clinically important treatment effect |
kappa |
a number of the correlation coefficient between two biomarkers |
rhovec |
a numeric vector of two correlation coefficients between the output and two biomarkers |
sigma |
a number of the standard deviation of outcome |
cLam |
the desired standardized average subpopulation treatment effect |
Value
a numeric vector of two values which are the cutoff values for z1 and z2
Author(s)
Jiangtao Gou
Fengqing Zhang
References
Zhang, F. and Gou, J. (2025). Using multiple biomarkers for patient enrichment in two-stage clinical designs. Technical Report.
Examples
z2interval <- c(-4, 4)
kkk <- 1
muminusmu0 <- 1.8
kappa <- 0.1
rhovec <- c(0.1, 0.2)
sigma <- 1
cLam <- 2.5
findSATE2(z2interval, kkk, muminusmu0, kappa, rhovec, sigma, cLam)
Find the difference between the average subpopulation treatment effect and the desired one
Description
Find the difference between the average subpopulation treatment effect and the desired one
Usage
targetDel(z2, kkk, muminusmu0, kappa, rhovec, sigma, cDel)
Arguments
z2 |
the standardized biomarker value of the second biomarker |
kkk |
the researchers' weighting preference between the two biomarkers |
muminusmu0 |
a number of the difference between the mean of outcome and the minimal clinically important treatment effect |
kappa |
a number of the correlation coefficient between two biomarkers |
rhovec |
a numeric vector of two correlation coefficients between the output and two biomarkers |
sigma |
a number of the standard deviation of outcome |
cDel |
the desired average subpopulation treatment effect |
Value
the difference between the average subpopulation treatment effect and the desired one
Find the difference between the standardized average subpopulation treatment effect and the desired one
Description
Find the difference between the standardized average subpopulation treatment effect and the desired one
Usage
targetLam(z2, kkk, muminusmu0, kappa, rhovec, sigma, cLam)
Arguments
z2 |
the standardized biomarker value of the second biomarker |
kkk |
the researchers' weighting preference between the two biomarkers |
muminusmu0 |
a number of the difference between the mean of outcome and the minimal clinically important treatment effect |
kappa |
a number of the correlation coefficient between two biomarkers |
rhovec |
a numeric vector of two correlation coefficients between the output and two biomarkers |
sigma |
a number of the standard deviation of outcome |
cLam |
the desired standardized average subpopulation treatment effect |
Value
the difference between the standardized average subpopulation treatment effect and the desired one