R/ctstm.R
IndivCtstmTrans.RdSimulate health state transitions in an individual-level continuous time state transition model using parameters from a multi-state model.
An R6::R6Class object.
IndivCtstmTrans objects are conveniently created from either
fitted models or parameter objects with create_IndivCtstmTrans().
A complete economic model can be implemented with the IndivCtstm class.
hesim::CtstmTrans -> IndivCtstmTrans
paramsAn object of class params_surv or params_surv_list.
input_dataInput data used to simulate health state transitions
by sample from the probabilistic sensitivity analysis (PSA), treatment strategy and patient.
Must be an object of class input_mats. If params contains parameters from
a list of models (i.e., of class params_surv_list), then input_data
must contain a unique row for each treatment strategy
and patient; if params contains parameters from a joint model
(i.e., of class params_surv), then input_data must contain a unique
row for each treatment strategy, patient, and transition.
trans_matA transition matrix describing the states and transitions
in a multi-state model in the format from the mstate package.
See the documentation for the argument "trans" in mstate::msprep.
start_stateA scalar or vector denoting the starting health state. Default is the first health state. If a vector, must be equal to the number of simulated patients.
start_ageA scalar or vector denoting the starting age of each patient in the simulation. Default is 38. If a vector, must be equal to the number of simulated patients.
death_stateThe death state in trans_mat. Used with max_age
in sim_disease as patients transition to this state upon reaching maximum age.
By default, it is set to the final absorbing state (i.e., a row in trans_mat with all NAs).
clock"reset" for a clock-reset model, "forward" for a clock-forward model,
"mix" for a mixture of clock-reset and clock-forward models by state, and
"mixt" for a mixture of clock-reset and clock-forward models by transition. A clock-reset model
is a semi-Markov model in which transition rates depend on time since entering a state.
A clock-forward model is a Markov model in which transition rates depend on time
since entering the initial state. If "mix" is used, then
reset_states must be specified. If "mixt" is used, then transition_types must
be specified.
reset_statesA vector denoting the states in which time resets.
Hazard functions are always a function of elapsed time since either the
start of the model or from when time was previously reset. Only used if
clock = "mix".
transition_typesA vector denoting the type of transition.
The vector is of the same length as the number of transitions
and takes values "reset", "time" or "age" for hazards that are functions of
reset time, time since study entry or age, respectively. Only used if
clock = "mixt".
Inherited methods
new()Create a new IndivCtstmTrans object.
IndivCtstmTrans$new(
params,
input_data,
trans_mat,
start_state = 1,
start_age = 38,
death_state = NULL,
clock = c("reset", "forward", "mix", "mixt"),
reset_states = NULL,
transition_types = NULL
)paramsThe params field.
input_dataThe input_data field.
trans_matThe trans_mat field.
start_stateThe start_state field.
start_ageThe start_age field.
death_stateThe death_state field.
clockThe clock field.
reset_statesThe reset_states field.
transition_typesThe transition_types field.
sim_disease()Simulate disease progression (i.e., individual trajectories through a multi-state model using an individual patient simulation).
max_tA scalar or vector denoting the length of time to simulate the model. If a vector, must be equal to the number of simulated patients.
max_ageA scalar or vector denoting the maximum age to simulate each patient until. If a vector, must be equal to the number of simulated patients.
progressAn integer, specifying the PSA iteration (i.e., sample) that should be printed every progress PSA iterations. For example, if progress = 2, then every second PSA iteration is printed. Default is NULL, in which case no output is printed.
An object of class disprog.
sim_stateprobs()Simulate health state probabilities from a disprog object.
tA numeric vector of times.
disprogA disprog object. If
NULL, then this will be simulated prior to computing state probabilities
using IndivCtstm$sim_disease().
...Additional arguments to pass to IndivCtstm$sim_disease() if
disprog = NULL.
An object of class stateprobs.
check()Input validation for class. Checks that fields are the correct type.
library("flexsurv")
# Simulation data
strategies <- data.frame(strategy_id = c(1, 2, 3))
patients <- data.frame(patient_id = seq(1, 3),
age = c(45, 50, 60),
female = c(0, 0, 1))
# Multi-state model with transition specific models
tmat <- rbind(c(NA, 1, 2),
c(NA, NA, 3),
c(NA, NA, NA))
fits <- vector(length = max(tmat, na.rm = TRUE), mode = "list")
for (i in 1:length(fits)){
fits[[i]] <- flexsurvreg(Surv(years, status) ~ 1,
data = bosms3[bosms3$trans == i, ],
dist = "exp")
}
fits <- flexsurvreg_list(fits)
# Simulation model
hesim_dat <- hesim_data(strategies = strategies,
patients = patients)
fits_data <- expand(hesim_dat)
transmod <- create_IndivCtstmTrans(fits, input_data = fits_data,
trans_mat = tmat,
n = 2)
head(transmod$hazard(c(1, 2, 3)))
#> transition_id sample strategy_id patient_id grp_id t hazard
#> <num> <num> <int> <int> <int> <num> <num>
#> 1: 1 1 1 1 1 1 0.19599086
#> 2: 1 1 1 1 1 2 0.19599086
#> 3: 1 1 1 1 1 3 0.19599086
#> 4: 2 1 1 1 1 1 0.04988861
#> 5: 2 1 1 1 1 2 0.04988861
#> 6: 2 1 1 1 1 3 0.04988861
head(transmod$cumhazard(c(1, 2, 3)))
#> transition_id sample strategy_id patient_id grp_id t cumhazard
#> <num> <num> <int> <int> <int> <num> <num>
#> 1: 1 1 1 1 1 1 0.19599086
#> 2: 1 1 1 1 1 2 0.39198173
#> 3: 1 1 1 1 1 3 0.58797259
#> 4: 2 1 1 1 1 1 0.04988861
#> 5: 2 1 1 1 1 2 0.09977722
#> 6: 2 1 1 1 1 3 0.14966583
## Simulate disease progression and state probabilities together
transmod$sim_stateprobs(t = c(0, 5, 10))[t == 5]
#> sample strategy_id grp_id state_id t prob
#> <num> <int> <int> <num> <num> <num>
#> 1: 1 1 1 1 5 0.6666667
#> 2: 1 1 1 2 5 0.0000000
#> 3: 1 1 1 3 5 0.3333333
#> 4: 1 2 1 1 5 0.3333333
#> 5: 1 2 1 2 5 0.0000000
#> 6: 1 2 1 3 5 0.6666667
#> 7: 1 3 1 1 5 0.3333333
#> 8: 1 3 1 2 5 0.3333333
#> 9: 1 3 1 3 5 0.3333333
#> 10: 2 1 1 1 5 1.0000000
#> 11: 2 1 1 2 5 0.0000000
#> 12: 2 1 1 3 5 0.0000000
#> 13: 2 2 1 1 5 0.0000000
#> 14: 2 2 1 2 5 0.3333333
#> 15: 2 2 1 3 5 0.6666667
#> 16: 2 3 1 1 5 0.0000000
#> 17: 2 3 1 2 5 0.3333333
#> 18: 2 3 1 3 5 0.6666667
## Simulate disease progression and state probabilities separately
disprog <- transmod$sim_disease(max_t = 10)
transmod$sim_stateprobs(t = c(0, 5, 10), disprog = disprog)[t == 5]
#> sample strategy_id grp_id state_id t prob
#> <num> <int> <int> <num> <num> <num>
#> 1: 1 1 1 1 5 0.3333333
#> 2: 1 1 1 2 5 0.0000000
#> 3: 1 1 1 3 5 0.6666667
#> 4: 1 2 1 1 5 0.3333333
#> 5: 1 2 1 2 5 0.6666667
#> 6: 1 2 1 3 5 0.0000000
#> 7: 1 3 1 1 5 0.3333333
#> 8: 1 3 1 2 5 0.3333333
#> 9: 1 3 1 3 5 0.3333333
#> 10: 2 1 1 1 5 0.6666667
#> 11: 2 1 1 2 5 0.0000000
#> 12: 2 1 1 3 5 0.3333333
#> 13: 2 2 1 1 5 0.3333333
#> 14: 2 2 1 2 5 0.0000000
#> 15: 2 2 1 3 5 0.6666667
#> 16: 2 3 1 1 5 0.0000000
#> 17: 2 3 1 2 5 0.6666667
#> 18: 2 3 1 3 5 0.3333333