Tabulate Binary Response by Subgroup — response

Tabulate statistics such as response rate and odds ratio for population subgroups.

Usage

extract_rsp_subgroups(
  variables,
  data,
  groups_lists = list(),
  conf_level = 0.95,
  method = NULL,
  label_all = "All Patients"
)

a_response_subgroups(
  .formats = list(n = "xx", n_rsp = "xx", prop = "xx.x%", n_tot = "xx", or =
    list(format_extreme_values(2L)), ci = list(format_extreme_values_ci(2L)), pval =
    "x.xxxx | (<0.0001)")
)

tabulate_rsp_subgroups(lyt, df, vars = c("n_tot", "n", "prop", "or", "ci"))

Arguments

variables: (named list of string)
list of additional analysis variables.
data: (data frame)
the dataset containing the variables to summarize.
groups_lists: (named list of list)
optionally contains for each subgroups variable a list, which specifies the new group levels via the names and the levels that belong to it in the character vectors that are elements of the list.
conf_level: (proportion)
confidence level of the interval.
method: (string)
specifies the test used to calculate the p-value for the difference between two proportions. For options, see s_test_proportion_diff(). Default is NULL so no test is performed.
label_all: (string)
label for the total population analysis.
.formats: (named character or list)
formats for the statistics.
lyt: (layout)
input layout where analyses will be added to.
df: (list)
of data frames containing all analysis variables. List should be created using extract_rsp_subgroups().
vars: (character)
the name of statistics to be reported among n (total number of observations per group), n_rsp (number of responders per group), prop (proportion of responders), n_tot (total number of observations), or (odds ratio), ci (confidence interval of odds ratio) and pval (p value of the effect). Note, the statistics n_tot, or and ci are required.

Details

These functions create a layout starting from a data frame which contains the required statistics. Tables typically used as part of forest plot.

Functions

extract_rsp_subgroups(): prepares response rates and odds ratios for population subgroups in data frames. Simple wrapper for h_odds_ratio_subgroups_df() and h_proportion_subgroups_df(). Result is a list of two data frames: prop and or. variables corresponds to the names of variables found in data, passed as a named list and requires elements rsp, arm and optionally subgroups and strat. groups_lists optionally specifies groupings for subgroups variables.
a_response_subgroups(): Formatted Analysis function used to format the results of extract_rsp_subgroups(). Returns is a list of Formatted Analysis functions with one element per statistic.
tabulate_rsp_subgroups(): table creating function.

Examples


# Testing dataset.
library(scda)
library(dplyr)
library(forcats)
library(rtables)

adrs <- synthetic_cdisc_data("latest")$adrs
adrs_labels <- formatters::var_labels(adrs)

adrs_f <- adrs %>%
  filter(PARAMCD == "BESRSPI") %>%
  filter(ARM %in% c("A: Drug X", "B: Placebo")) %>%
  droplevels() %>%
  mutate(
    # Reorder levels of factor to make the placebo group the reference arm.
    ARM = fct_relevel(ARM, "B: Placebo"),
    rsp = AVALC == "CR"
  )
formatters::var_labels(adrs_f) <- c(adrs_labels, "Response")
# Unstratified analysis.
df <- extract_rsp_subgroups(
  variables = list(rsp = "rsp", arm = "ARM", subgroups = c("SEX", "BMRKR2")),
  data = adrs_f
)
df
#> $prop
#>           arm   n n_rsp      prop     subgroup    var
#> 1  B: Placebo 134    97 0.7238806 All Patients    ALL
#> 2   A: Drug X 134   119 0.8880597 All Patients    ALL
#> 3  B: Placebo  82    57 0.6951220            F    SEX
#> 4   A: Drug X  79    73 0.9240506            F    SEX
#> 5  B: Placebo  52    40 0.7692308            M    SEX
#> 6   A: Drug X  55    46 0.8363636            M    SEX
#> 7  B: Placebo  45    38 0.8444444          LOW BMRKR2
#> 8   A: Drug X  50    46 0.9200000          LOW BMRKR2
#> 9  B: Placebo  56    38 0.6785714       MEDIUM BMRKR2
#> 10  A: Drug X  37    31 0.8378378       MEDIUM BMRKR2
#> 11 B: Placebo  33    21 0.6363636         HIGH BMRKR2
#> 12  A: Drug X  47    42 0.8936170         HIGH BMRKR2
#>                        var_label row_type
#> 1                   All Patients  content
#> 2                   All Patients  content
#> 3                            Sex analysis
#> 4                            Sex analysis
#> 5                            Sex analysis
#> 6                            Sex analysis
#> 7  Categorical Level Biomarker 2 analysis
#> 8  Categorical Level Biomarker 2 analysis
#> 9  Categorical Level Biomarker 2 analysis
#> 10 Categorical Level Biomarker 2 analysis
#> 11 Categorical Level Biomarker 2 analysis
#> 12 Categorical Level Biomarker 2 analysis
#> 
#> $or
#>   arm n_tot       or       lcl       ucl conf_level     subgroup    var
#> 1       268 3.026117 1.5685817  5.838002       0.95 All Patients    ALL
#> 2       161 5.336257 2.0514242 13.880913       0.95            F    SEX
#> 3       107 1.533333 0.5856092  4.014813       0.95            M    SEX
#> 4        95 2.118421 0.5765066  7.784313       0.95          LOW BMRKR2
#> 5        93 2.447368 0.8662556  6.914371       0.95       MEDIUM BMRKR2
#> 6        80 4.800000 1.4936979 15.424806       0.95         HIGH BMRKR2
#>                       var_label row_type
#> 1                  All Patients  content
#> 2                           Sex analysis
#> 3                           Sex analysis
#> 4 Categorical Level Biomarker 2 analysis
#> 5 Categorical Level Biomarker 2 analysis
#> 6 Categorical Level Biomarker 2 analysis
#> 

# Stratified analysis.
df_strat <- extract_rsp_subgroups(
  variables = list(rsp = "rsp", arm = "ARM", subgroups = c("SEX", "BMRKR2"), strat = "STRATA1"),
  data = adrs_f
)
df_strat
#> $prop
#>           arm   n n_rsp      prop     subgroup    var
#> 1  B: Placebo 134    97 0.7238806 All Patients    ALL
#> 2   A: Drug X 134   119 0.8880597 All Patients    ALL
#> 3  B: Placebo  82    57 0.6951220            F    SEX
#> 4   A: Drug X  79    73 0.9240506            F    SEX
#> 5  B: Placebo  52    40 0.7692308            M    SEX
#> 6   A: Drug X  55    46 0.8363636            M    SEX
#> 7  B: Placebo  45    38 0.8444444          LOW BMRKR2
#> 8   A: Drug X  50    46 0.9200000          LOW BMRKR2
#> 9  B: Placebo  56    38 0.6785714       MEDIUM BMRKR2
#> 10  A: Drug X  37    31 0.8378378       MEDIUM BMRKR2
#> 11 B: Placebo  33    21 0.6363636         HIGH BMRKR2
#> 12  A: Drug X  47    42 0.8936170         HIGH BMRKR2
#>                        var_label row_type
#> 1                   All Patients  content
#> 2                   All Patients  content
#> 3                            Sex analysis
#> 4                            Sex analysis
#> 5                            Sex analysis
#> 6                            Sex analysis
#> 7  Categorical Level Biomarker 2 analysis
#> 8  Categorical Level Biomarker 2 analysis
#> 9  Categorical Level Biomarker 2 analysis
#> 10 Categorical Level Biomarker 2 analysis
#> 11 Categorical Level Biomarker 2 analysis
#> 12 Categorical Level Biomarker 2 analysis
#> 
#> $or
#>   arm n_tot       or       lcl       ucl conf_level     subgroup    var
#> 1       268 3.036189 1.5749483  5.853173       0.95 All Patients    ALL
#> 2       161 5.211620 2.0113615 13.503781       0.95            F    SEX
#> 3       107 1.628393 0.6196333  4.279406       0.95            M    SEX
#> 4        95 2.045340 0.5597227  7.474085       0.95          LOW BMRKR2
#> 5        93 2.423656 0.8624779  6.810734       0.95       MEDIUM BMRKR2
#> 6        80 4.540487 1.4443496 14.273571       0.95         HIGH BMRKR2
#>                       var_label row_type
#> 1                  All Patients  content
#> 2                           Sex analysis
#> 3                           Sex analysis
#> 4 Categorical Level Biomarker 2 analysis
#> 5 Categorical Level Biomarker 2 analysis
#> 6 Categorical Level Biomarker 2 analysis
#> 

# Grouping of the BMRKR2 levels.
df_grouped <- extract_rsp_subgroups(
  variables = list(rsp = "rsp", arm = "ARM", subgroups = c("SEX", "BMRKR2")),
  data = adrs_f,
  groups_lists = list(
    BMRKR2 = list(
      "low" = "LOW",
      "low/medium" = c("LOW", "MEDIUM"),
      "low/medium/high" = c("LOW", "MEDIUM", "HIGH")
    )
  )
)
df_grouped
#> $prop
#>           arm   n n_rsp      prop        subgroup    var
#> 1  B: Placebo 134    97 0.7238806    All Patients    ALL
#> 2   A: Drug X 134   119 0.8880597    All Patients    ALL
#> 3  B: Placebo  82    57 0.6951220               F    SEX
#> 4   A: Drug X  79    73 0.9240506               F    SEX
#> 5  B: Placebo  52    40 0.7692308               M    SEX
#> 6   A: Drug X  55    46 0.8363636               M    SEX
#> 7  B: Placebo  45    38 0.8444444             low BMRKR2
#> 8   A: Drug X  50    46 0.9200000             low BMRKR2
#> 9  B: Placebo 101    76 0.7524752      low/medium BMRKR2
#> 10  A: Drug X  87    77 0.8850575      low/medium BMRKR2
#> 11 B: Placebo 134    97 0.7238806 low/medium/high BMRKR2
#> 12  A: Drug X 134   119 0.8880597 low/medium/high BMRKR2
#>                        var_label row_type
#> 1                   All Patients  content
#> 2                   All Patients  content
#> 3                            Sex analysis
#> 4                            Sex analysis
#> 5                            Sex analysis
#> 6                            Sex analysis
#> 7  Categorical Level Biomarker 2 analysis
#> 8  Categorical Level Biomarker 2 analysis
#> 9  Categorical Level Biomarker 2 analysis
#> 10 Categorical Level Biomarker 2 analysis
#> 11 Categorical Level Biomarker 2 analysis
#> 12 Categorical Level Biomarker 2 analysis
#> 
#> $or
#>   arm n_tot       or       lcl       ucl conf_level        subgroup    var
#> 1       268 3.026117 1.5685817  5.838002       0.95    All Patients    ALL
#> 2       161 5.336257 2.0514242 13.880913       0.95               F    SEX
#> 3       107 1.533333 0.5856092  4.014813       0.95               M    SEX
#> 4        95 2.118421 0.5765066  7.784313       0.95             low BMRKR2
#> 5       188 2.532895 1.1393669  5.630807       0.95      low/medium BMRKR2
#> 6       268 3.026117 1.5685817  5.838002       0.95 low/medium/high BMRKR2
#>                       var_label row_type
#> 1                  All Patients  content
#> 2                           Sex analysis
#> 3                           Sex analysis
#> 4 Categorical Level Biomarker 2 analysis
#> 5 Categorical Level Biomarker 2 analysis
#> 6 Categorical Level Biomarker 2 analysis
#> 
# Internal function - a_response_subgroups
if (FALSE) {
a_response_subgroups(.formats = list("n" = "xx", "prop" = "xx.xx%"))
}


## Table with default columns.
basic_table() %>%
  tabulate_rsp_subgroups(df)
#> Baseline Risk Factors                         B: Placebo           A: Drug X                                  
#>                                 Total n    n    Response (%)    n    Response (%)   Odds Ratio      95% CI    
#> ——————————————————————————————————————————————————————————————————————————————————————————————————————————————
#> All Patients                      268     134      72.4%       134      88.8%          3.03      (1.57, 5.84) 
#> Sex                                                                                                           
#>   F                               161     82       69.5%       79       92.4%          5.34      (2.05, 13.88)
#>   M                               107     52       76.9%       55       83.6%          1.53      (0.59, 4.01) 
#> Categorical Level Biomarker 2                                                                                 
#>   LOW                             95      45       84.4%       50       92.0%          2.12      (0.58, 7.78) 
#>   MEDIUM                          93      56       67.9%       37       83.8%          2.45      (0.87, 6.91) 
#>   HIGH                            80      33       63.6%       47       89.4%          4.80      (1.49, 15.42)

## Table with selected columns.
basic_table() %>%
  tabulate_rsp_subgroups(
    df = df,
    vars = c("n_tot", "n", "n_rsp", "prop", "or", "ci")
  )
#> Baseline Risk Factors                               B: Placebo                         A: Drug X                                        
#>                                 Total n    n    Responders   Response (%)    n    Responders   Response (%)   Odds Ratio      95% CI    
#> ————————————————————————————————————————————————————————————————————————————————————————————————————————————————————————————————————————
#> All Patients                      268     134       97          72.4%       134      119          88.8%          3.03      (1.57, 5.84) 
#> Sex                                                                                                                                     
#>   F                               161     82        57          69.5%       79        73          92.4%          5.34      (2.05, 13.88)
#>   M                               107     52        40          76.9%       55        46          83.6%          1.53      (0.59, 4.01) 
#> Categorical Level Biomarker 2                                                                                                           
#>   LOW                             95      45        38          84.4%       50        46          92.0%          2.12      (0.58, 7.78) 
#>   MEDIUM                          93      56        38          67.9%       37        31          83.8%          2.45      (0.87, 6.91) 
#>   HIGH                            80      33        21          63.6%       47        42          89.4%          4.80      (1.49, 15.42)