Get an object to fit the BOIN model using the BOIN package.
get_boin(
num_doses,
target,
use_stopping_rule = TRUE,
stop_when_deescalation_impossible = FALSE,
...
)Number of doses under investigation.
We seek a dose with this probability of toxicity.
TRUE to use the toxicity stopping rule described in Yan et al. (2019). FALSE to suppress the authors' stopping rule, with the assumption being that you will test the necessity to stop early in some other way.
TRUE to stop a trial and recommend no dose when the advice is to de-escalate but de-escalation is impossible because we are already at the lowest dose. Note that this feature was requested by a user. This param is FALSE by default so that behaviour matches what was described in the publication. The original authors do advocate this behaviour.
Extra args are passed to get.boundary.
an object of type selector_factory that can fit the
BOIN model to outcomes.
Yan, F., Pan, H., Zhang, L., Liu, S., & Yuan, Y. (2019). BOIN: An R Package for Designing Single-Agent and Drug-Combination Dose-Finding Trials Using Bayesian Optimal Interval Designs. Journal of Statistical Software, 27(November 2017), 0–35. https://doi.org/10.18637/jss.v000.i00
Liu, S., & Yuan, Y. (2015). Bayesian optimal designs for Phase I clinical trials. J. R. Stat. Soc. C, 64, 507–523. https://doi.org/10.1111/rssc.12089
target <- 0.25
model1 <- get_boin(num_doses = 5, target = target)
outcomes <- '1NNN 2NTN'
model1 %>% fit(outcomes) %>% recommended_dose()
#> [1] 1