get_oc_gBOIN_TB: Generate operating characteristics for finding the maximum...

In UnifiedDoseFinding: Dose-Finding Methods for Non-Binary Outcomes

Generate operating characteristics for finding the maximum tolerated dose (MTD) defined by Toxicity Burden (TB) Score using gBOIN design

Description

Obtain the operating characteristics of the generalized Bayesian optimal interval (gBOIN) design (Mu et al. 2017) for maximum tolerated dose (MTD) (defined by the toxicity burden (BT) score proposed by Bekele et al. (2004))-based dosing-finding trials using. The algorithm of this function is exactly same to the get_oc_gBOIN_Continuous() just the input parameter is used by the TB score

Usage

get_oc_gBOIN_TB(target, pmat, weight, ncohort, cohortsize,
                n.earlystop = 100, ntrial, mu_1 = 0.6 * target,
                mu_2 = 1.4 * target, startdose = 1, seed = 100)

Arguments

target	the target TB score
pmat	pmat is a list. Each element is a matrix, representing the probability of different toxicity type and scale under different dose levels.
weight	the severity weight
ncohort	the number of cohort
cohortsize	the cohort size
n.earlystop	the early stopping parameter. The default value is n.earlystop = 100
ntrial	the number of simulated trial
mu_1	the lower bound. The default value is p.saf = 0.6 * target
mu_2	the upper bound. The default value is mu_2 = 1.4 * target
startdose	the starting dose level. The default value is startdose = 1
seed	the seed. The default value is seed = 100

Value

get_oc_gBOIN_TB() returns the operating characteristics of generalized Bayesian optimal interval design as a list object, including: (1) selection percentage of each dose, (2) the average number of patients treated at each dose

Author(s)

Chia-Wei Hsu, Haitao Pan, Rongji Mu

References

Bekele, B. Nebiyou, and Peter F. Thall. "Dose-finding based on multiple toxicities in a soft tissue sarcoma trial." Journal of the American Statistical Association 99, no. 465 (2004): 26-35.

Rongji Mu, Ying Yuan, Jin Xu, Sumithra J. Mandrekar, Jun Yin: gBOIN: a unified model-assisted phase I trial design accounting for toxicity grades, and binary or continuous end points. Royal Statistical Society 2019

Examples

target <- 3.344
ncohort <- 10
cohortsize <- 3
ntrial <- 1000
rate <- 1.1
weight <- rate * rbind(c(0,1,1.5,5,6), c(0,2.5,6,rep(0,2)), c(0,2,3,6,0),
                       c(0,1.5,2,0,0), c(0,0.5,1,0,0))
pmat <- list()
pmat[[1]] <- rbind(c(0.5,0.5,rep(0,3)),
                   c(1,rep(0,4)),
                   c(1,rep(0,4)),
                   c(1,rep(0,4)),
                   c(0.5,0,0.5,0,0))
pmat[[2]] <- rbind(c(0.5,0,0.5,0,0),
                   c(1,rep(0,4)),
                   c(0.5,0.5,0,0,0),
                   c(0.5,0.5,rep(0,3)),
                   c(0.46,0,0.54,rep(0,2)))
pmat[[3]] <- rbind(c(0.5,0,0.5,0,0),
                   c(0.4,0.6,0,0,0),
                   c(0.25,0.75,0,0,0),
                   c(0.5,0.5,0,0,0),
                   c(1,0,0,0,0))
pmat[[4]] <- rbind(c(0.5,0,0.5,0,0),
                   c(0.4,0.6,0,0,0),
                   c(0.25,0.75,0,0,0),
                   c(0.5,0.5,0,0,0),
                   c(0.5,0,0.5,0,0))
pmat[[5]] <- rbind(c(0.5,0,0.5,0,0),
                   c(0,1,0,0,0),
                   c(0.25,0.75,0,0,0),
                   c(0.5,0.5,0,0,0),
                   c(0.5,0,0.5,0,0))
pmat[[6]] <- rbind(c(0,0.5,0.5,0,0),
                   c(0,1,0,0,0),
                   c(0,1,0,0,0),
                   c(0.5,0.5,0,0,0),
                   c(0.5,0,0.5,0,0))
pmat[[7]] <- rbind(c(0,0.5,0.5,0,0),
                   c(0,1,0,0,0),
                   c(0,1,0,0,0),
                   c(0,0.5,0.5,0,0),
                   c(0.5,0,0.5,0,0))
pmat[[8]] <- rbind(c(0,0.5,0.5,0,0),
                   c(0,1,0,0,0),
                   c(0,0,1,0,0),
                   c(0,0.5,0.5,0,0),
                   c(0.5,0,0.5,0,0))
pmat[[9]] <- rbind(c(0,0,1,0,0),
                   c(0,1,0,0,0),
                   c(0,0,1,0,0),
                   c(0,0,1,0,0),
                   c(0,0,1,0,0))
pmat[[10]] <- rbind(c(0,0,1,0,0),
                    c(0,1,0,0,0),
                    c(1/3,0,0,2/3,0),
                    c(0,0,1,0,0),
                    c(0,0,1,0,0))
get_oc_gBOIN_TB(target = target, pmat = pmat, weight = weight,
                ncohort = ncohort, cohortsize = cohortsize,
                ntrial = ntrial)

UnifiedDoseFinding documentation built on Oct. 16, 2022, 1:10 a.m.