relative_effects: Relative treatment effects

Description

Generate (population-average) relative treatment effects. If a ML-NMR or meta-regression model was fitted, these are specific to each study population.

Usage

relative_effects(
  x,
  newdata = NULL,
  study = NULL,
  all_contrasts = FALSE,
  trt_ref = NULL,
  probs = c(0.025, 0.25, 0.5, 0.75, 0.975),
  summary = TRUE
)

Arguments

A stan_nma object created by nma()

newdata

Only used if a regression model is fitted. A data frame of study details, one row per study, giving the covariate values at which to produce relative effects. Column names must match variables in the regression model. If NULL, relative effects are produced for all studies in the network.

study

Column of newdata which specifies study names, otherwise studies will be labelled by row number.

all_contrasts

Logical, generate estimates for all contrasts (TRUE), or just the "basic" contrasts against the network reference treatment (FALSE)? Default FALSE.

trt_ref

Reference treatment to construct relative effects against, if all_contrasts = FALSE. By default, relative effects will be against the network reference treatment. Coerced to character string.

probs

Numeric vector of quantiles of interest to present in computed summary, default c(0.025, 0.25, 0.5, 0.75, 0.975)

summary

Logical, calculate posterior summaries? Default TRUE.

Value

A nma_summary object if summary = TRUE, otherwise a list containing a 3D MCMC array of samples and (for regression models) a data frame of study information.

Examples

Run this code

# NOT RUN {
## Smoking cessation
# Set up network of smoking cessation data
head(smoking)

smk_net <- set_agd_arm(smoking,
                       study = studyn,
                       trt = trtc,
                       r = r,
                       n = n,
                       trt_ref = "No intervention")

# Print details
smk_net

# }
# NOT RUN {
# Fitting a random effects model
smk_fit_RE <- nma(smk_net,
                  trt_effects = "random",
                  prior_intercept = normal(scale = 100),
                  prior_trt = normal(scale = 100),
                  prior_het = normal(scale = 5))

smk_fit_RE
# }
# NOT RUN {
# }
# NOT RUN {
# Produce relative effects
smk_releff_RE <- relative_effects(smk_fit_RE)
smk_releff_RE
plot(smk_releff_RE, ref_line = 0)

# Relative effects for all pairwise comparisons
relative_effects(smk_fit_RE, all_contrasts = TRUE)

# Relative effects against a different reference treatment
relative_effects(smk_fit_RE, trt_ref = "Self-help")

# Transforming to odds ratios
# We work with the array of relative effects samples
LOR_array <- as.array(smk_releff_RE)
OR_array <- exp(LOR_array)

# mcmc_array objects can be summarised to produce a nma_summary object
smk_OR_RE <- summary(OR_array)

# This can then be printed or plotted
smk_OR_RE
plot(smk_OR_RE, ref_line = 1)
# }
# NOT RUN {
## Plaque psoriasis ML-NMR
# Set up plaque psoriasis network combining IPD and AgD
library(dplyr)
pso_ipd <- filter(plaque_psoriasis_ipd,
                  studyc %in% c("UNCOVER-1", "UNCOVER-2", "UNCOVER-3"))

pso_agd <- filter(plaque_psoriasis_agd,
                  studyc == "FIXTURE")

head(pso_ipd)
head(pso_agd)

pso_ipd <- pso_ipd %>%
  mutate(# Variable transformations
    bsa = bsa / 100,
    prevsys = as.numeric(prevsys),
    psa = as.numeric(psa),
    weight = weight / 10,
    durnpso = durnpso / 10,
    # Treatment classes
    trtclass = case_when(trtn == 1 ~ "Placebo",
                         trtn %in% c(2, 3, 5, 6) ~ "IL blocker",
                         trtn == 4 ~ "TNFa blocker"),
    # Check complete cases for covariates of interest
    complete = complete.cases(durnpso, prevsys, bsa, weight, psa)
  )

pso_agd <- pso_agd %>%
  mutate(
    # Variable transformations
    bsa_mean = bsa_mean / 100,
    bsa_sd = bsa_sd / 100,
    prevsys = prevsys / 100,
    psa = psa / 100,
    weight_mean = weight_mean / 10,
    weight_sd = weight_sd / 10,
    durnpso_mean = durnpso_mean / 10,
    durnpso_sd = durnpso_sd / 10,
    # Treatment classes
    trtclass = case_when(trtn == 1 ~ "Placebo",
                         trtn %in% c(2, 3, 5, 6) ~ "IL blocker",
                         trtn == 4 ~ "TNFa blocker")
  )

# Exclude small number of individuals with missing covariates
pso_ipd <- filter(pso_ipd, complete)

pso_net <- combine_network(
  set_ipd(pso_ipd,
          study = studyc,
          trt = trtc,
          r = pasi75,
          trt_class = trtclass),
  set_agd_arm(pso_agd,
              study = studyc,
              trt = trtc,
              r = pasi75_r,
              n = pasi75_n,
              trt_class = trtclass)
)

# Print network details
pso_net

# Add integration points to the network
pso_net <- add_integration(pso_net,
  durnpso = distr(qgamma, mean = durnpso_mean, sd = durnpso_sd),
  prevsys = distr(qbern, prob = prevsys),
  bsa = distr(qlogitnorm, mean = bsa_mean, sd = bsa_sd),
  weight = distr(qgamma, mean = weight_mean, sd = weight_sd),
  psa = distr(qbern, prob = psa),
  n_int = 1000)

# }
# NOT RUN {
# Fitting a ML-NMR model.
# Specify a regression model to include effect modifier interactions for five
# covariates, along with main (prognostic) effects. We use a probit link and
# specify that the two-parameter Binomial approximation for the aggregate-level
# likelihood should be used. We set treatment-covariate interactions to be equal
# within each class. We narrow the possible range for random initial values with
# init_r = 0.1, since probit models in particular are often hard to initialise.
# Using the QR decomposition greatly improves sampling efficiency here, as is
# often the case for regression models.
pso_fit <- nma(pso_net,
               trt_effects = "fixed",
               link = "probit",
               likelihood = "bernoulli2",
               regression = ~(durnpso + prevsys + bsa + weight + psa)*.trt,
               class_interactions = "common",
               prior_intercept = normal(scale = 10),
               prior_trt = normal(scale = 10),
               prior_reg = normal(scale = 10),
               init_r = 0.1,
               QR = TRUE)
# }
# NOT RUN {
# }
# NOT RUN {
# Produce population-adjusted relative effects for all study populations in
# the network
pso_releff <- relative_effects(pso_fit)
pso_releff
plot(pso_releff, ref_line = 0)

# Produce population-adjusted relative effects for a different target
# population
new_agd_means <- data.frame(
  bsa = 0.6,
  prevsys = 0.1,
  psa = 0.2,
  weight = 10,
  durnpso = 3)

relative_effects(pso_fit, newdata = new_agd_means)
# }

Run the code above in your browser using DataLab

Description

Usage

Arguments

Value

See Also

Examples