
Simulation tools for Bayesian optimal interval (BOIN) designs in phase I dose-finding trials. The documentation, with the six vignettes, is also available at https://gosukehommaex.github.io/simFastBOIN/.
simFastBOIN tabulates the BOIN decision boundaries, simulates the design to obtain operating characteristics, and applies the MTD selection rule used at the end of a trial. The simulation engine is written in C++.
The engine draws one uniform variate per patient, in enrollment
order, and applies the decision rules in the same order as
BOIN::get.oc(). With the same seed and matching arguments
the two implementations agree trial by trial, not merely on average. The
test suite checks this directly against the BOIN package rather than
relying on a tolerance, so the claim is verifiable rather than asserted.
A wider comparison ships with the package as
inst/validation/compare-with-BOIN.R, which runs 200
configurations covering every combination of the options the two
packages share, including extrasafe and
titration.
Version 2.1.0 adds the time-to-event BOIN (TITE-BOIN) design, for
toxicity that appears late in the assessment window or accrual that
outpaces it. New patients are treated while earlier ones are still being
followed, with the pending outcomes handled either by the single mean
imputation of Yuan et al. (2018) or by the effective sample size of Lin
and Yuan (2020). The decision table reproduces the published tables of
Yuan et al. (2018) entry by entry, and whenever no patient is pending
the simulated trials are identical to those of sim_boin()
with the same seed.
The same version adds backfilling: patients who arrive while the dose escalation waits are treated at a lower dose that is safe and has shown a response. BF-BOIN (Zhao et al., 2024) backfills around the BOIN design, and BE-BOIN (Chen et al., 2026) around the time-to-event design. The operating characteristics of Table 4 of Zhao et al. (2024) are reproduced within simulation error.
For trials of two drugs given together, the same version adds the
BOIN drug-combination design of Lin and Yin (2017), which looks for an
MTD combination in a matrix of doses. It follows
BOIN::get.oc.comb() trial by trial and reproduces the
example of Yan et al. (2020) to the printed precision.
Version 2.2.0 adds the BOIN-ET design of Takeda et al. (2018), which decides from both the DLT and the response and selects the optimal biological dose (OBD), with its time-to-event (TITE-BOIN-ET) and backfill (BF-BOIN-ET) versions. The boundaries and the decision table of Takeda et al. (2018) are reproduced exactly, and the operating characteristics agree within simulation error with those of the ‘boinet’ and ‘bfboinet’ packages of the authors.
The same version adds the BOIN12 design of Lin et al. (2020), which treats each cohort at the dose with the most desirable balance of response and toxicity, measured by a utility. Its desirability score table reproduces Table 3 of the article in all 166 cells, and its engine agrees trial by trial with a separate Python implementation. The titration of the BOIN design can now stop at a given dose, which with an early stop at six patients gives the accelerated BOIN design of Kojima et al. (2024).
Its time-to-event version, TITE-BOIN12 (Zhou et al., 2022), treats new patients while the DLT or the response of earlier patients is still pending, which shortens the trial; when every decision waits for all the outcomes it gives exactly the trials of BOIN12.
Comb-BOIN12 (Lu et al., 2025) extends BOIN12 to two drugs given together and selects the optimal biological dose combination with a logistic model of the response. With one row of combinations its trials are those of BOIN12. TITE-Comb-BOIN12 applies its rules at the decision times of TITE-BOIN12. BOIN-ETC (Kakizume et al., 2024) divides the dose matrix of two drugs into subtrials along which the toxicity increases, runs BOIN-ET in each of them and selects the optimal dose combination by a utility, in the three versions of the article.
Whatever the design, oc_scenarios(),
oc_results() and oc_compare() set the
operating characteristics of several designs and scenarios side by side
and judge them against the true MTDs and OBDs, with print()
and plot() methods.
install.packages("simFastBOIN")Or the development version:
# install.packages("pak")
pak::pak("gosukehommaEX/simFastBOIN")Since version 2.0.0 the package contains compiled code, so a working C++ toolchain is needed to install from source (Rtools on Windows, Xcode command line tools on macOS).
library(simFastBOIN)
oc <- sim_boin(
target = 0.30,
p_true = c(0.05, 0.15, 0.30, 0.45, 0.60),
n_cohort = 10,
cohort_size = 3,
n_trials = 10000,
seed = 123
)
ocCompare several dose-toxicity scenarios under the same design:
sim_boin_multi(
target = 0.30,
scenarios = list(
"MTD at dose 2" = c(0.15, 0.30, 0.45, 0.60, 0.75),
"MTD at dose 4" = c(0.02, 0.06, 0.15, 0.30, 0.50),
"All doses toxic" = c(0.40, 0.55, 0.65, 0.75, 0.85)
),
n_cohort = 10,
cohort_size = 3,
n_trials = 10000,
seed = 123
)Look at the boundaries the design will actually use:
print(boin_boundary(target = 0.30, max_n = 18, extrasafe = TRUE), cohort_size = 3)Read the dose decisions off a table, or off a figure for a protocol:
decisions <- boin_decision_table(target = 0.30, max_n = 18)
print(decisions, cohort_size = 3)
plot(decisions) # needs ggplot2When toxicity can appear late, or patients arrive faster than they can be assessed, use the time-to-event design. Its decisions also depend on how long the pending patients have been followed:
tite <- tite_boin_decision_table(target = 0.30, max_n = 15)
print(tite, cohort_size = 3)
sim_tite_boin(
target = 0.30,
p_true = c(0.05, 0.15, 0.30, 0.45, 0.60),
n_cohort = 10,
cohort_size = 3,
window = 3, # a three month assessment window
accrual_rate = 2, # two patients a month
n_trials = 10000,
seed = 123
)To backfill patients to lower doses while the escalation waits, give the response probabilities as well:
sim_bf_boin(
target = 0.25,
p_true = c(0.04, 0.12, 0.25, 0.43, 0.63),
p_resp = c(0.10, 0.20, 0.30, 0.45, 0.58),
n_cohort = 10,
cohort_size = 3,
window = 1, # a one month assessment window
accrual_rate = 3, # three patients a month
n_earlystop = 9,
n_trials = 10000,
seed = 123
)For two drugs given together, give the true DLT rates as a matrix, with the levels of drug A in the rows and those of drug B in the columns:
sim_comb_boin(
target = 0.25,
p_true = matrix(c(0.02, 0.04, 0.08, 0.14,
0.08, 0.25, 0.42, 0.48,
0.25, 0.45, 0.50, 0.60), nrow = 3, byrow = TRUE),
n_cohort = 16,
cohort_size = 3,
n_trials = 10000,
seed = 123
)Design
| Function | Purpose |
|---|---|
boin_lambda() |
Escalation and de-escalation interval boundaries |
boin_boundary() |
Integer decision boundaries by sample size |
boin_decision_table() |
Decision table indexed by DLTs and patients |
boin_stopping_table() |
Safety stopping boundary as a two-row table |
Simulation
| Function | Purpose |
|---|---|
sim_boin() |
Operating characteristics for one scenario |
sim_boin_multi() |
Operating characteristics across scenarios |
boin_simulate() |
Raw trial data from the engine |
boin_isotonic() |
Isotonic estimates of the dose-toxicity curve |
boin_select_mtd() |
MTD selection from completed trials |
Time-to-event BOIN (TITE-BOIN)
| Function | Purpose |
|---|---|
tite_boin_decision_table() |
Decision table with pending patients, for either method |
sim_tite_boin() |
Operating characteristics, trial duration and suspensions of accrual |
sim_tite_boin_multi() |
The same across scenarios |
tite_boin_simulate() |
Raw trial data from the time-to-event engine |
Backfilling (BF-BOIN and BE-BOIN)
| Function | Purpose |
|---|---|
sim_bf_boin() |
Operating characteristics of BF-BOIN, with backfilled patients, responses and trial duration |
sim_bf_boin_multi() |
The same across scenarios |
bf_boin_simulate() |
Raw trial data from the BF-BOIN engine |
sim_be_boin() |
Operating characteristics of BE-BOIN, backfilling with the time-to-event design |
sim_be_boin_multi() |
The same across scenarios |
be_boin_simulate() |
Raw trial data from the BE-BOIN engine |
Drug combinations
| Function | Purpose |
|---|---|
sim_comb_boin() |
Operating characteristics of the BOIN drug-combination design for one matrix of DLT rates |
sim_comb_boin_multi() |
The same across scenarios |
comb_boin_simulate() |
Raw trial data from the drug-combination engine |
comb_boin_select_mtd() |
MTD combination selection from completed trials |
comb_boin_next() |
Combination for the next cohort of a trial in progress, with
print() and plot() methods |
Optimal biological dose (BOIN-ET)
| Function | Purpose |
|---|---|
boin_et_boundary() |
Boundaries of the BOIN-ET design for the DLT and the response |
boin_et_decision_table() |
Decision table indexed by DLTs and responses |
sim_boin_et() |
Operating characteristics with the selection of the optimal biological dose (OBD) |
sim_boin_et_multi() |
The same across scenarios |
boin_et_simulate() |
Raw trial data from the BOIN-ET engine |
boin_et_select_obd() |
OBD selection from completed trials |
sim_tite_boin_et() |
Operating characteristics of the time-to-event TITE-BOIN-ET design |
sim_tite_boin_et_multi() |
The same across scenarios |
tite_boin_et_simulate() |
Raw trial data from the TITE-BOIN-ET engine |
sim_bf_boin_et() |
Operating characteristics of the backfill BF-BOIN-ET design |
sim_bf_boin_et_multi() |
The same across scenarios |
Optimal biological dose (BOIN12 and TITE-BOIN12)
| Function | Purpose |
|---|---|
boin12_decision_table() |
Desirability score table indexed by patients, DLTs and responses |
sim_boin12() |
Operating characteristics with the selection of the OBD |
sim_boin12_multi() |
The same across scenarios |
boin12_simulate() |
Raw trial data from the BOIN12 engine |
boin12_select_obd() |
OBD selection from completed trials |
sim_tite_boin12() |
Operating characteristics of the time-to-event TITE-BOIN12 design |
sim_tite_boin12_multi() |
The same across scenarios |
tite_boin12_simulate() |
Raw trial data from the TITE-BOIN12 engine |
Optimal biological dose combinations (Comb-BOIN12 and TITE-Comb-BOIN12)
| Function | Purpose |
|---|---|
sim_comb_boin12() |
Operating characteristics with the selection of the OBD combination |
sim_comb_boin12_multi() |
The same across scenarios |
comb_boin12_simulate() |
Raw trial data from the Comb-BOIN12 engine |
comb_boin12_select_obd() |
OBD combination selection from completed trials |
sim_tite_comb_boin12() |
Operating characteristics of the time-to-event TITE-Comb-BOIN12 design |
sim_tite_comb_boin12_multi() |
The same across scenarios |
tite_comb_boin12_simulate() |
Raw trial data from the TITE-Comb-BOIN12 engine |
Optimal dose combinations (BOIN-ETC)
| Function | Purpose |
|---|---|
sim_boin_etc() |
Operating characteristics of BOIN-ETC1, 2 or 3 with the selection of the optimal dose combination |
sim_boin_etc_multi() |
The same across scenarios |
boin_etc_simulate() |
Raw trial data from the BOIN-ETC engine |
boin_etc_select_obd() |
Optimal dose combination selection from completed trials |
3+3 design
| Function | Purpose |
|---|---|
oc_3p3() |
Operating characteristics in closed form |
sim_3p3() |
The same by simulation, as a check on the closed form |
decision_table_3p3() |
Decision table of the design |
Tables and figures
| Function | Purpose |
|---|---|
oc_scenarios() |
True scenarios with the utilities and the true MTDs and OBDs |
oc_results() |
Results of several designs and scenarios in one long table |
oc_compare() |
Several designs judged against the true doses: correct selection, overdosing, sample size |
| Argument | Effect |
|---|---|
titration |
Treat one patient per dose until the first DLT, then switch to full cohorts |
titration_doses |
Stop the titration at this dose; with n_earlystop = 6,
the accelerated BOIN design of Kojima et al. (2024) |
extrasafe |
Add a stopping rule at the lowest dose that triggers before elimination |
bound_mtd |
Refuse to select a dose whose estimate exceeds the de-escalation boundary |
n_earlystop |
Stop once the current dose has accrued this many patients and the design would stay |
start_dose |
Dose level for the first cohort, ignored under
titration |
stay_on_1_of_3 |
Make one DLT out of three a stay rather than a de-escalation |
min_mtd_sample |
Smallest number of patients for a dose to be eligible as the MTD |
Note that n_earlystop defaults to 18 here, whereas
BOIN::get.oc() defaults to 100, which in practice switches
the rule off. Set it explicitly when comparing the two.
method |
Pending outcomes handled by | Boundaries refer to | Default suspension rule |
|---|---|---|---|
"imputation" |
Single mean imputation (Yuan et al., 2018) | STFT | Suspend accrual when more than half of the patients at the dose are pending |
"ess" |
Effective sample size (Lin and Yuan, 2020) | ESS | Escalate only once two patients at the dose have completed the assessment |
STFT is the total follow-up time of the pending patients divided by
the length of the assessment window, and ESS adds to it the number of
patients who have completed the assessment. Neither table depends on the
length of the window. Both suspension rules can be set for either method
with max_pending_ratio and min_completed.
A simulation needs the length of the window and the accrual rate in
the same unit of time. Arrivals can be exponential (the default),
uniform or fixed, and the time to DLT Weibull, with a share
late_fraction of the DLTs in the second half of the window,
or uniform. The follow-up of the pending patients can be weighted by a
piecewise uniform prior for the time to DLT through
prior_weights; both articles evaluate their designs with
equal weights, the default.
How the implementation is checked:
tite_boin_decision_table() reproduces all 640 entries
of Table 1 (target 0.2) of Yuan et al. (2018) and of Table S1 (target
0.3) of its supplementary appendix, and the dose decisions of the trial
example in Figure 1 of that article. The published tables allow
de-escalation when the observed DLT rate equals the target, which
equation (5) of the appendix, read literally, does not; the package
follows the tables.tite_boin_simulate() and the summaries of
sim_tite_boin() are identical to those of
boin_simulate() and sim_boin() under the same
seed.Neither article reports operating characteristics that can be reproduced number for number: Yuan et al. (2018) give them as figures relative to the 3+3 design and as averages over randomly generated scenarios, and the tables of Lin and Yuan (2020) are for the keyboard and mTPI designs.
In BF-BOIN the dose escalation proceeds in fully staggered cohorts
with the BOIN decision table. A patient who arrives while it waits is
backfilled to the highest lower dose that has not been eliminated, has
fewer than n_cap patients and has a response observed at or
below it. Backfilled doses whose DLT rate becomes too high are closed,
and when their data conflict with those of the current dose the
escalation decides from the pooled data. BE-BOIN applies the same rules
around the time-to-event design, with the suspension rules of Chen et
al. (2025), and imputes the pending patients in every estimate. The MTD
is selected from all patients, backfilled ones included.
Where the articles leave a detail of the simulation open, the package
offers an argument: no_slot (a patient with nowhere to go
waits or is turned away), conflict_dose (which conflicting
dose anchors the pooled estimate) and resp_window,
resp_late_fraction and resp_cor (the timing of
responses and their correlation with DLTs).
How the implementation is checked:
stay_on_1_of_3 = TRUE, n_earlystop = 9,
accrual = "uniform" and no_slot = "leave". The
script inst/validation/compare-with-Zhao2024.R repeats the
comparison.boin_simulate() and
tite_boin_simulate() under the same seed.See vignette("simFastBOIN-backfill") for the rules, the
choices made where the articles are silent, and the comparison with
Table 4.
sim_comb_boin() implements the design of Lin and Yin
(2017) as the BOIN package does in BOIN::get.oc.comb() with
mtd.contour = FALSE, including the details that the package
adds to the article: a candidate’s posterior probability is increased by
0.0005 per patient treated there, the trial can stop at
n_earlystop, and the MTD is selected from
(y + 0.05) / (n + 0.1) smoothed by
Iso::biviso(). Note that n_earlystop defaults
to 18 here, whereas BOIN::get.oc.comb() defaults to
100.
How the implementation is checked:
BOIN::get.oc.comb() exactly; the tests check nine settings,
and inst/validation/compare-comb-with-BOIN.R 200
configurations.inst/validation/compare-with-LinYin2017.R sets the
results beside Tables 2 and 3 of Lin and Yin (2017), whose rules differ
in some details.To run a trial, comb_boin_next() gives the combination
for the next cohort from the numbers of patients and DLTs observed so
far. It takes its decision with the same C++ code as the simulations, so
the trial follows the rules whose operating characteristics
sim_comb_boin() reports. BOIN::next.comb()
differs from the simulations of BOIN::get.oc.comb() in a
few rules, which the help page of comb_boin_next()
lists.
nxt <- comb_boin_next(
target = 0.25,
n_pts = matrix(c(6, 6, 0, 0,
3, 3, 0, 0,
0, 0, 0, 0), nrow = 3, byrow = TRUE),
n_tox = matrix(c(0, 1, 0, 0,
1, 2, 0, 0,
0, 0, 0, 0), nrow = 3, byrow = TRUE),
current = c(2, 2)
)
nxt # de-escalate to A1B2
plot(nxt) # the dose matrix with the data and the decisionThe waterfall design of Zhang and Yuan (2016), which looks for the
MTD contour, is not provided. See
vignette("simFastBOIN-combination").
For targeted and immune therapies the aim is often the optimal
biological dose (OBD), which weighs the response against the toxicity,
rather than the MTD. The BOIN-ET design of Takeda, Taguri and Morita
(2018) decides the next dose from both the DLT rate and the response
rate at the current dose, with boundaries lambda1,
lambda2 and eta1 that minimize the probability
of an incorrect decision, and selects the OBD at the end of the
trial.
boin_et_decision_table(target = 0.30, target_resp = 0.60, n = c(3, 6))
oc <- sim_boin_et(
target = 0.30, target_resp = 0.60,
p_true = c(0.05, 0.15, 0.25, 0.30, 0.35, 0.40),
p_resp = c(0.05, 0.35, 0.55, 0.65, 0.75, 0.70),
n_cohort = 12, cohort_size = 3, n_trials = 10000
)
ocThe rules follow the ‘boinet’ package (Yamaguchi, Takeda and Maruo,
2025), the reference implementation of the authors: the boundary search
of boinet::gridoptim(), the admissibility of a dose
re-derived after every cohort, and the estimators and selection rules of
boinet::obd.select() (observed rates, model-averaged
unimodal isotonic regression or fractional polynomial logistic
regression; the highest response up to the estimated MTD or one of three
utilities). The trial runs in C++ and the OBD selection too; the
model-based estimates are computed once for every distinct set of final
data. boin_et_select_obd() selects the OBD from completed
trials.
Two rules differ from ‘boinet’, to keep to Takeda et al. (2018), who
do not allow dose skipping during escalation: a dose excluded by its DLT
data also excludes every higher dose, as in the later BF-BOIN-ET design
of the same group, and an escalation from the highest dose ends the
trial when that dose is excluded. boinet_compatible = TRUE
applies the rules of ‘boinet’ exactly.
The time-to-event version, TITE-BOIN-ET (Takeda, Morita and Taguri, 2020), lets patients arrive while others are still assessed, and the backfill version, BF-BOIN-ET (Takeda, Zhu and Hirakawa, 2025), treats the patients who arrive in the meantime at lower doses with a promising response rate:
oc <- sim_tite_boin_et(
target = 0.30, target_resp = 0.60,
p_true = c(0.05, 0.15, 0.25, 0.30, 0.35, 0.40),
p_resp = c(0.05, 0.35, 0.55, 0.65, 0.75, 0.70),
n_cohort = 12, cohort_size = 3, window = 30, resp_window = 45,
accrual_rate = 1 / 10, n_trials = 10000
)
oc_bf <- sim_bf_boin_et(
target = 0.30, target_resp = 0.25,
p_true = c(0.03, 0.05, 0.20, 0.22, 0.45),
p_resp = c(0.05, 0.10, 0.50, 0.68, 0.70),
n_cohort = 10, cohort_size = 3, window = 1, accrual_rate = 3,
n_trials = 10000
)The rules follow boinet::tite.boinet() and
bfboinet::get.oc.backboinet().
How the implementation is checked:
inst/reproduce/reproduce_Takeda2018.R sets the simulations
beside Table 3. inst/reproduce/reproduce_Takeda2020.R does
the same for Table 2 of Takeda et al. (2020), whose simulations did not
wait for finished assessments (min_completed_share = 0),
and inst/reproduce/reproduce_Takeda2025.R for Tables 1 and
2 of Takeda et al. (2025).boinet::gridoptim() and the OBD of simulated trials with
boinet::obd.select() exactly.inst/validation/compare-with-boinet.R compares the
operating characteristics with boinet::boinet() and
boinet::tite.boinet(), and
inst/validation/compare-with-bfboinet.R with
bfboinet::get.oc.backboinet(). The packages draw their
random numbers differently, so they agree in distribution, not trial by
trial.For two drugs given together, sim_boin_etc() runs
BOIN-ET in subtrials of the dose matrix, the BOIN-ETC design of Kakizume
et al. (2024). inst/reproduce/reproduce_Kakizume2024.R
compares it with the tables of the article and
inst/validation/compare-with-BOINETC.R with the code of the
authors.
See vignette("simFastBOIN-boin-et") for the decision
rules, the selection of the OBD, the dose moves that differ from
‘boinet’, BOIN-ETC and the results of these checks.
The BOIN12 design of Lin et al. (2020) scores each patient by a utility, 100 for a response without DLT, 0 for a DLT without response and two values in between elicited from the clinicians (40 and 60 by default). The next cohort goes to the dose, among the current one and its neighbors, whose utility is most likely to exceed a benchmark, after the BOIN boundaries have ruled out an escalation from a toxic dose. The desirabilities can be tabulated for the protocol:
boin12_decision_table(target = 0.35, target_resp = 0.25)Here target is the highest acceptable DLT rate and
target_resp the lowest acceptable response rate. The
operating characteristics follow the same pattern as the other
designs:
oc <- sim_boin12(
target = 0.35, target_resp = 0.25,
p_true = c(0.05, 0.12, 0.27, 0.35, 0.50),
p_resp = c(0.20, 0.35, 0.36, 0.37, 0.38),
n_cohort = 12, cohort_size = 3, n_trials = 10000
)
ocThe table reproduces Table 3 of Lin et al. (2020) in all 166 cells
(inst/reproduce/reproduce_Lin2020.R), and
inst/validation/compare-with-escalation.R compares the
operating characteristics with the BOIN12 design of the ‘escalation’
package.
The time-to-event version, TITE-BOIN12 (Zhou et al., 2022), treats new patients while the DLT or the response of earlier patients is still pending, replacing each pending outcome by its expectation given the time followed. The windows and the accrual rate are given in the same unit of time:
oc <- sim_tite_boin12(
target = 0.35, target_resp = 0.25,
p_true = c(0.05, 0.12, 0.27, 0.35, 0.50),
p_resp = c(0.20, 0.35, 0.36, 0.37, 0.38),
n_cohort = 12, cohort_size = 3,
window = 1.5, resp_window = 2, accrual_rate = 3, # months
n_trials = 10000
)
ocinst/reproduce/reproduce_Zhou2022.R compares the
desirabilities of Table S.3 of the Supplement of Zhou et al. (2022) and
the operating characteristics of BOIN12 and TITE-BOIN12 in their Figure
3.
See vignette("simFastBOIN-boin12") for the rules, the
arguments that give the rules of the simulations of the articles,
Comb-BOIN12 and TITE-Comb-BOIN12 for two drugs given together, a
comparison of BOIN, BOIN-ET and BOIN12 on the same scenarios, and the
results of these checks.
boin_simulate() records a reason for every trial, and
sim_boin() reports the distribution in
stop_reason_percent.
| Reason | Meaning |
|---|---|
lowest_dose_eliminated |
The lowest dose was eliminated for toxicity |
lowest_dose_too_toxic |
The extrasafe rule stopped the trial at the lowest
dose |
n_earlystop |
Enough patients had accrued at the current dose |
max_sample_size |
The maximum number of patients was reached |
max_cohorts |
All planned cohorts were completed |
reference <- BOIN::get.oc(
target = 0.30, p.true = c(0.05, 0.15, 0.25, 0.45, 0.60),
ncohort = 20, cohortsize = 3, n.earlystop = 18, ntrial = 10000, seed = 6
)
ours <- sim_boin(
target = 0.30, p_true = c(0.05, 0.15, 0.25, 0.45, 0.60),
n_cohort = 20, cohort_size = 3, n_earlystop = 18, n_trials = 10000, seed = 6
)
all.equal(unname(ours$sel_percent), reference$selpercent)
all.equal(unname(ours$n_pts_dose), reference$npatients)
all.equal(unname(ours$n_tox_dose), reference$ntox)
all.equal(ours$percent_no_mtd, reference$percentstop)Five doses, 20 cohorts of three, n_earlystop = 18 and
10,000 simulated trials, measured on one Windows machine:
| Elapsed | |
|---|---|
BOIN::get.oc() |
9.98 s |
sim_boin() |
0.07 s |
That is about two orders of magnitude for this design. The ratio depends on the design and on the machine, so the code below re-measures it rather than asking you to take the table on trust.
scenario <- c(0.05, 0.15, 0.25, 0.45, 0.60)
system.time(
BOIN::get.oc(target = 0.30, p.true = scenario, ncohort = 20, cohortsize = 3,
n.earlystop = 18, ntrial = 10000, seed = 6)
)
system.time(
sim_boin(target = 0.30, p_true = scenario, n_cohort = 20, cohort_size = 3,
n_earlystop = 18, n_trials = 10000, seed = 6)
)The time-to-event engine was timed on a similar design, five doses
and 20 cohorts of three with the true DLT rates
c(0.05, 0.15, 0.30, 0.45, 0.60), a three month window and
two patients a month, 10,000 trials, all three runs together on one
Windows machine:
| Elapsed | |
|---|---|
sim_boin() |
0.05 s |
sim_tite_boin(),
method = "imputation" |
0.09 s |
sim_tite_boin(), method = "ess" |
0.11 s |
Following patients over time costs about twice as much as the BOIN engine. The BOIN package has no time-to-event design, so there is no reference implementation of TITE-BOIN to time it against.
The traditional 3+3 design is included as a comparator. Its operating characteristics are obtained in closed form rather than by simulation, so they carry no Monte Carlo error.
oc_3p3(p_true = c(0.30, 0.48, 0.67))
# The other definition of the MTD in common use
oc_3p3(p_true = c(0.30, 0.48, 0.67), mtd_rule = "expand")sim_3p3() simulates the same design and exists to
confirm the closed form. The result of either has the same component
names as the result of sim_boin(), so the two designs can
be tabulated side by side.
decision_table_3p3() shows the rule itself, with
print() and plot() methods like those of the
BOIN decision table. oc_compare() judges the 3+3 and BOIN
designs against the true MTDs of oc_scenarios(), as shown
in the section “Tables and figures” of
vignette("simFastBOIN-introduction").
decision_table_3p3(mtd_rule = "expand")Version 2.0.0 renames most functions, changes the argument order of
sim_boin() and corrects several defects that affected
numerical results. Simulations run with the same seed will not reproduce
the version 1.3.2 output. See NEWS.md for the full
list and the mapping of old names to new ones.
Liu, S. and Yuan, Y. (2015). Bayesian Optimal Interval Designs for Phase I Clinical Trials. Journal of the Royal Statistical Society: Series C, 64, 507-523.
Yan, F., Zhang, L., Zhou, Y., Pan, H., Liu, S. and Yuan, Y. (2020). BOIN: An R Package for Designing Single-Agent and Drug-Combination Dose-Finding Trials Using Bayesian Optimal Interval Designs. Journal of Statistical Software, 94(13), 1-32.
Yuan, Y., Lin, R., Li, D., Nie, L. and Warren, K. E. (2018). Time-to-Event Bayesian Optimal Interval Design to Accelerate Phase I Trials. Clinical Cancer Research, 24(20), 4921-4930.
Lin, R. and Yuan, Y. (2020). Time-to-Event Model-Assisted Designs for Dose-Finding Trials with Delayed Toxicity. Biostatistics, 21(4), 807-824.
Zhao, Y., Yuan, Y., Korn, E. L. and Freidlin, B. (2024). Backfilling Patients in Phase I Dose-Escalation Trials Using Bayesian Optimal Interval Design (BOIN). Clinical Cancer Research, 30(4), 673-679.
Chen, K., Chen, T.-Y., Zhang, Y., Lin, R. and Yuan, Y. (2025). Practical Considerations for Using the TITE-BOIN Design to Handle Late-Onset Toxicity or Fast Accrual in Phase I Trials. Clinical Cancer Research, 31(13), 2573-2580.
Chen, K., Zhao, Y., Takeda, K. and Yuan, Y. (2026). BE-BOIN: A Dose Optimization Design Accommodating Backfill and Late-Onset Toxicity. Therapeutic Innovation and Regulatory Science.
Lin, R. and Yin, G. (2017). Bayesian Optimal Interval Design for Dose Finding in Drug-Combination Trials. Statistical Methods in Medical Research, 26(5), 2155-2167.
Zhang, L. and Yuan, Y. (2016). A Practical Bayesian Design to Identify the Maximum Tolerated Dose Contour for Drug Combination Trials. Statistics in Medicine, 35(27), 4924-4936.
Takeda, K., Taguri, M. and Morita, S. (2018). BOIN-ET: Bayesian Optimal Interval Design for Dose Finding Based on Both Efficacy and Toxicity Outcomes. Pharmaceutical Statistics, 17(4), 383-395.
Takeda, K., Morita, S. and Taguri, M. (2020). TITE-BOIN-ET: Time-to-event Bayesian optimal interval design to accelerate dose-finding based on both efficacy and toxicity outcomes. Pharmaceutical Statistics, 19, 335-349.
Takeda, K., Zhu, J. and Hirakawa, A. (2025). BF-BOIN-ET: A Backfill Bayesian Optimal Interval Design Using Efficacy and Toxicity Outcomes for Dose Optimization. Pharmaceutical Statistics, 24, e2470.
Yamaguchi, Y., Takeda, K. and Maruo, K. (2025). boinet: An R Package for Bayesian Optimal Interval Design for Dose Finding Based on Both Efficacy and Toxicity Outcomes. The R Journal, 17(2), 15-34.
Lin, R., Zhou, Y., Yan, F., Li, D. and Yuan, Y. (2020). BOIN12: Bayesian Optimal Interval Phase I/II Trial Design for Utility-Based Dose Finding in Immunotherapy and Targeted Therapies. JCO Precision Oncology, 4, 1393-1402.
Zhou, Y., Lin, R., Lee, J. J., Li, D., Wang, L., Li, R. and Yuan, Y. (2022). TITE-BOIN12: A Bayesian Phase I/II Trial Design to Find the Optimal Biological Dose with Late-Onset Toxicity and Efficacy. Statistics in Medicine, 41(11), 1918-1931.
Lu, M., Zhang, J., Yuan, Y. and Lin, R. (2025). Comb-BOIN12: A Utility-Based Bayesian Optimal Interval Design for Dose Optimization in Cancer Drug-Combination Trials. Statistics in Biopharmaceutical Research, 17(2), 266-276.
Kakizume, T., Takeda, K., Taguri, M. and Morita, S. (2024). BOIN-ETC: A Bayesian Optimal Interval Design Considering Efficacy and Toxicity to Identify the Optimal Dose Combinations. Statistical Methods in Medical Research, 33(4), 716-727.
MIT (c) Gosuke Homma