Skip to contents

Count the Number of Patients with a Particular Event

Source: R/count_patients_with_event.R
count_patients_with_event.Rd

[Stable]

Usage

s_count_patients_with_event(
  df,
  .var,
  filters,
  .N_col,
  .N_row,
  denom = c("n", "N_row", "N_col")
)

a_count_patients_with_event(
  df,
  .var,
  filters,
  .N_col,
  .N_row,
  denom = c("n", "N_row", "N_col")
)

count_patients_with_event(
  lyt,
  vars,
  ...,
  table_names = vars,
  .stats = "count_fraction",
  .formats = NULL,
  .labels = NULL,
  .indent_mods = NULL
)

s_count_patients_with_flags(
  df,
  .var,
  flag_variables,
  .N_col,
  .N_row,
  denom = c("n", "N_row", "N_col")
)

a_count_patients_with_flags(
  df,
  .var,
  flag_variables,
  .N_col,
  .N_row,
  denom = c("n", "N_row", "N_col")
)

count_patients_with_flags(
  lyt,
  var,
  var_labels = var,
  show_labels = "hidden",
  ...,
  table_names = paste0("tbl_flags_", var),
  .stats = "count_fraction",
  .formats = NULL,
  .indent_mods = NULL
)

Arguments

df

(data frame)
data set containing all analysis variables.

.var

(character)
name of the column that contains the unique identifier.

filters

(character)
a character vector specifying the column names and flag variables to be used for counting the number of unique identifiers satisfying such conditions. Multiple column names and flags are accepted in this format c("column_name1" = "flag1", "column_name2" = "flag2"). Note that only equality is being accepted as condition.

.N_col

(count)
row-wise N (row group count) for the group of observations being analyzed (i.e. with no column-based subsetting) that is passed by rtables.

.N_row

(count)
column-wise N (column count) for the full column that is passed by rtables.

denom

(string)
choice of denominator for proportion:
can be n (number of values in this row and column intersection), N_row (total number of values in this row across columns), or N_col (total number of values in this column across rows).

lyt

(layout)
input layout where analyses will be added to.

vars

(character)
variable names for the primary analysis variable to be iterated over.

...

additional arguments for the lower level functions.

table_names

(character)
this can be customized in case that the same vars are analyzed multiple times, to avoid warnings from rtables.

.stats

(character)
statistics to select for the table.

.formats

(named character or list)
formats for the statistics.

.labels

(named character)
labels for the statistics (without indent).

.indent_mods

(named integer)
indent modifiers for the labels.

flag_variables

(character)
a character vector specifying the names of logical variables from analysis dataset used for counting the number of unique identifiers.

var

(string)
single variable name that is passed by rtables when requested by a statistics function.

var_labels

character for label.

show_labels

label visibility: one of "default", "visible" and "hidden".

Value

s_count_patients_with_event() returns the count and fraction of patients with the defined event.

Details

The primary analysis variable .var denotes the unique patient identifier.

Functions

  • s_count_patients_with_event(): Statistics Function that returns the number and the fraction of unique identifiers with a particular type of event, e.g. the number and the fraction of patients who had treatment-emergent adverse events. Note that the user can define a new data column containing the event of interest.

  • a_count_patients_with_event(): Formatted Analysis function which can be further customized by calling rtables::make_afun() on it. It is used as afun in rtables::analyze().

  • count_patients_with_event(): Analyze Function which adds the count statistics to the input layout. Note that additional formatting arguments can be used here.

  • s_count_patients_with_flags(): Statistics function that returns the number and the fraction of unique identifiers with each particular flag. Returns a list of totals, counts, counts and fractions with one element per flag.

  • a_count_patients_with_flags(): Formatted Analysis function which can be further customized by calling rtables::make_afun() on it. It is used as afun in rtables::analyze().

  • count_patients_with_flags(): Analyze Function which is a modified version of count_patients_with_event(). Adds the count statistics to the input layout for multiple flag variables at once.

Examples



library(dplyr)
library(scda)
adae <- synthetic_cdisc_data("latest")$adae
adsl <- synthetic_cdisc_data("latest")$adsl

# `s_count_patients_with_event()`

s_count_patients_with_event(
  adae,
  .var = "SUBJID",
  filters = c("TRTEMFL" = "Y")
)
#> $n
#> [1] 365
#> 
#> $count
#> [1] 365
#> 
#> $count_fraction
#> [1] 365   1
#> 
#> $n_blq
#> [1] 0
#> 
s_count_patients_with_event(
  adae,
  .var = "SUBJID",
  filters = c("TRTEMFL" = "Y", "AEOUT" = "FATAL")
)
#> $n
#> [1] 365
#> 
#> $count
#> [1] 221
#> 
#> $count_fraction
#> [1] 221.0000000   0.6054795
#> 
#> $n_blq
#> [1] 0
#> 
s_count_patients_with_event(
  adae,
  .var = "SUBJID",
  filters = c("TRTEMFL" = "Y", "AEOUT" = "FATAL"),
  denom = "N_col",
  .N_col = 456
)
#> $n
#> [1] 365
#> 
#> $count
#> [1] 221
#> 
#> $count_fraction
#> [1] 221.0000000   0.4846491
#> 
#> $n_blq
#> [1] 0
#> 
# `a_count_patients_with_event()`
a_count_patients_with_event(
  adae,
  .var = "SUBJID",
  filters = c("TRTEMFL" = "Y"),
  .N_col = 100,
  .N_row = 100
)
#> RowsVerticalSection (in_rows) object print method:
#> ----------------------------
#>         row_name formatted_cell indent_mod      row_label
#> 1              n            365          0              n
#> 2          count            365          0          count
#> 3 count_fraction     365 (100%)          0 count_fraction
#> 4          n_blq              0          0          n_blq

# `count_patients_with_event()`

lyt <- basic_table() %>%
  split_cols_by("ARM") %>%
  add_colcounts() %>%
  count_values(
    "STUDYID",
    values = "AB12345",
    .stats = "count",
    .labels = c(count = "Total AEs")
  ) %>%
  count_patients_with_event(
    "SUBJID",
    filters = c("TRTEMFL" = "Y"),
    .labels = c(count_fraction = "Total number of patients with at least one adverse event"),
    table_names = "tbl_all"
  ) %>%
  count_patients_with_event(
    "SUBJID",
    filters = c("TRTEMFL" = "Y", "AEOUT" = "FATAL"),
    .labels = c(count_fraction = "Total number of patients with fatal AEs"),
    table_names = "tbl_fatal"
  ) %>%
  count_patients_with_event(
    "SUBJID",
    filters = c("TRTEMFL" = "Y", "AEOUT" = "FATAL", "AEREL" = "Y"),
    .labels = c(count_fraction = "Total number of patients with related fatal AEs"),
    .indent_mods = c(count_fraction = 2L),
    table_names = "tbl_rel_fatal"
  )
build_table(lyt, adae, alt_counts_df = adsl)
#>                                                            A: Drug X    B: Placebo   C: Combination
#>                                                             (N=134)      (N=134)        (N=132)    
#> ———————————————————————————————————————————————————————————————————————————————————————————————————
#> Total AEs                                                     609          622            703      
#> Total number of patients with at least one adverse event   122 (100%)   123 (100%)     120 (100%)  
#> Total number of patients with fatal AEs                    76 (62.3%)   70 (56.9%)     75 (62.5%)  
#>     Total number of patients with related fatal AEs        76 (62.3%)   70 (56.9%)     75 (62.5%)  

# `s_count_patients_with_flags()`

# Add labelled flag variables to analysis dataset.
adae <- adae %>%
  mutate(
    fl1 = TRUE,
    fl2 = TRTEMFL == "Y",
    fl3 = TRTEMFL == "Y" & AEOUT == "FATAL",
    fl4 = TRTEMFL == "Y" & AEOUT == "FATAL" & AEREL == "Y"
  )
labels <- c(
  "fl1" = "Total AEs",
  "fl2" = "Total number of patients with at least one adverse event",
  "fl3" = "Total number of patients with fatal AEs",
  "fl4" = "Total number of patients with related fatal AEs"
)
formatters::var_labels(adae)[names(labels)] <- labels

s_count_patients_with_flags(
  adae,
  "SUBJID",
  flag_variables = c("fl1", "fl2", "fl3", "fl4"),
  denom = "N_col",
  .N_col = 1000
)
#> $n
#> $n$fl1
#> [1] 365
#> 
#> $n$fl2
#> [1] 365
#> 
#> $n$fl3
#> [1] 365
#> 
#> $n$fl4
#> [1] 365
#> 
#> 
#> $count
#> $count$fl1
#> [1] 365
#> 
#> $count$fl2
#> [1] 365
#> 
#> $count$fl3
#> [1] 221
#> 
#> $count$fl4
#> [1] 221
#> 
#> 
#> $count_fraction
#> $count_fraction$fl1
#> [1] 365.000   0.365
#> 
#> $count_fraction$fl2
#> [1] 365.000   0.365
#> 
#> $count_fraction$fl3
#> [1] 221.000   0.221
#> 
#> $count_fraction$fl4
#> [1] 221.000   0.221
#> 
#> 
#> $n_blq
#> $n_blq$fl1
#> [1] 0
#> 
#> $n_blq$fl2
#> [1] 0
#> 
#> $n_blq$fl3
#> [1] 0
#> 
#> $n_blq$fl4
#> [1] 0
#> 
#> 
#  We need to ungroup `count_fraction` first so that the `rtables` formatting
# function `format_count_fraction()` can be applied correctly.

# `a_count_patients_with_flags()`

afun <- make_afun(a_count_patients_with_flags,
  .stats = "count_fraction",
  .ungroup_stats = "count_fraction"
)
afun(
  adae,
  .N_col = 10L, # nolint
  .N_row = 10L,
  .var = "USUBJID",
  flag_variables = c("fl1", "fl2", "fl3", "fl4")
)
#> RowsVerticalSection (in_rows) object print method:
#> ----------------------------
#>   row_name formatted_cell indent_mod row_label
#> 1      fl1     365 (100%)          0       fl1
#> 2      fl2     365 (100%)          0       fl2
#> 3      fl3    221 (60.5%)          0       fl3
#> 4      fl4    221 (60.5%)          0       fl4

# `count_patients_with_flags()`

lyt2 <- basic_table() %>%
  split_cols_by("ARM") %>%
  add_colcounts() %>%
  count_patients_with_flags(
    "SUBJID",
    flag_variables = formatters::var_labels(adae[, c("fl1", "fl2", "fl3", "fl4")]),
    denom = "N_col"
  )
build_table(lyt2, adae, alt_counts_df = adsl)
#>                                                            A: Drug X    B: Placebo    C: Combination
#>                                                             (N=134)       (N=134)        (N=132)    
#> ————————————————————————————————————————————————————————————————————————————————————————————————————
#> Total AEs                                                  122 (91%)    123 (91.8%)    120 (90.9%)  
#> Total number of patients with at least one adverse event   122 (91%)    123 (91.8%)    120 (90.9%)  
#> Total number of patients with fatal AEs                    76 (56.7%)   70 (52.2%)      75 (56.8%)  
#> Total number of patients with related fatal AEs            76 (56.7%)   70 (52.2%)      75 (56.8%)