Helper Function to create a new SMQ variable in ADAE by stacking SMQ and/or CQ records.

Helper Function to create a new SMQ variable in ADAE that consists of all adverse events belonging to selected Standardized/Customized queries. The new dataset will only contain records of the adverse events belonging to any of the selected baskets.

Usage

h_stack_by_baskets(
  df,
  baskets = grep("^(SMQ|CQ).+NAM$", names(df), value = TRUE),
  smq_varlabel = "Standardized MedDRA Query",
  keys = c("STUDYID", "USUBJID", "ASTDTM", "AEDECOD", "AESEQ"),
  aag_summary = NULL,
  na_level = "<Missing>"
)

Arguments

df: (data frame)
data set containing all analysis variables.
baskets: (character)
variable names of the selected Standardized/Customized queries.
smq_varlabel: (string)
a label for the new variable created.
keys: (character)
names of the key variables to be returned along with the new variable created.
aag_summary: (data frame)
containing the SMQ baskets and the levels of interest for the final SMQ variable. This is useful when there are some levels of interest that are not observed in the df dataset. The two columns of this dataset should be named basket and basket_name.
na_level: (string)
used to replace all NA or empty values in factors.

Examples

library(scda)

adae <- synthetic_cdisc_data("latest")$adae[1:20, ] %>% df_explicit_na()
h_stack_by_baskets(df = adae)
#> # A tibble: 4 × 6
#>   STUDYID USUBJID              ASTDTM              AEDECOD       AESEQ SMQ      
#>   <fct>   <fct>                <dttm>              <fct>         <int> <fct>    
#> 1 AB12345 AB12345-BRA-1-id-141 2021-10-23 00:00:00 dcd D.2.1.5.3     2 D.2.1.5.…
#> 2 AB12345 AB12345-BRA-1-id-141 2022-08-03 00:00:00 dcd A.1.1.1.1     3 D.2.1.5.…
#> 3 AB12345 AB12345-BRA-1-id-141 2023-03-04 00:00:00 dcd A.1.1.1.1     5 D.2.1.5.…
#> 4 AB12345 AB12345-BRA-1-id-265 2021-09-12 00:00:00 dcd C.1.1.1.3     4 C.1.1.1.…

aag <- data.frame(
  NAMVAR = c("CQ01NAM", "CQ02NAM", "SMQ01NAM", "SMQ02NAM"),
  REFNAME = c(
    "D.2.1.5.3/A.1.1.1.1 AESI", "X.9.9.9.9/Y.8.8.8.8 AESI",
    "C.1.1.1.3/B.2.2.3.1 AESI", "C.1.1.1.3/B.3.3.3.3 AESI"
  ),
  SCOPE = c("", "", "BROAD", "BROAD"),
  stringsAsFactors = FALSE
)

basket_name <- character(nrow(aag))
cq_pos <- grep("^(CQ).+NAM$", aag$NAMVAR)
smq_pos <- grep("^(SMQ).+NAM$", aag$NAMVAR)
basket_name[cq_pos] <- aag$REFNAME[cq_pos]
basket_name[smq_pos] <- paste0(
  aag$REFNAME[smq_pos], "(", aag$SCOPE[smq_pos], ")"
)

aag_summary <- data.frame(
  basket = aag$NAMVAR,
  basket_name = basket_name,
  stringsAsFactors = TRUE
)

result <- h_stack_by_baskets(df = adae, aag_summary = aag_summary)
all(levels(aag_summary$basket_name) %in% levels(result$SMQ))
#> [1] TRUE

h_stack_by_baskets(
  df = adae,
  aag_summary = NULL,
  keys = c("STUDYID", "USUBJID", "AEDECOD", "ARM"),
  baskets = "SMQ01NAM"
)
#> # A tibble: 1 × 5
#>   STUDYID USUBJID              AEDECOD       ARM            SMQ                 
#>   <fct>   <fct>                <fct>         <fct>          <fct>               
#> 1 AB12345 AB12345-BRA-1-id-265 dcd C.1.1.1.3 C: Combination C.1.1.1.3/B.2.2.3.1…