derive_var_extreme_dt: Derive First or Last Date from Multiple Sources
In admiral: ADaM in R Asset Library

View source: R/derive_var_extreme_date.R

derive_var_extreme_dt

R Documentation

Derive First or Last Date from Multiple Sources

Description

The derive_var_extreme_dt() function has been superseded in favor of derive_vars_extreme_event().

Add the first or last date from multiple sources to the dataset, e.g., the last known alive date (LSTALVDT).

Note: This is a wrapper function for the function derive_var_extreme_dtm().

Usage

derive_var_extreme_dt(
  dataset,
  new_var,
  ...,
  source_datasets,
  mode,
  subject_keys = get_admiral_option("subject_keys")
)

Arguments

`dataset`	Input dataset The variables specified by the `subject_keys` argument are expected to be in the dataset.
`new_var`	Name of variable to create
`...`	Source(s) of dates. One or more `date_source()` objects are expected.
`source_datasets`	A named `list` containing datasets in which to search for the first or last date
`mode`	Selection mode (first or last) If `"first"` is specified, the first date for each subject is selected. If `"last"` is specified, the last date for each subject is selected. Permitted Values: `"first"`, `"last"`
`subject_keys`	Variables to uniquely identify a subject A list of expressions where the expressions are symbols as returned by `exprs()` is expected.

Details

The following steps are performed to create the output dataset:

For each source dataset the observations as specified by the filter element are selected and observations where date is NA are removed. Then for each patient the first or last observation (with respect to date and mode) is selected.
The new variable is set to the variable or expression specified by the date element.
The variables specified by the set_values_to element are added.
The selected observations of all source datasets are combined into a single dataset.
For each patient the first or last observation (with respect to the new variable and mode) from the single dataset is selected and the new variable is merged to the input dataset.
The time part is removed from the new variable.

Value

The input dataset with the new variable added.

Examples

library(dplyr, warn.conflicts = FALSE)
ae <- tribble(
  ~STUDYID,  ~DOMAIN,  ~USUBJID, ~AESEQ,     ~AESTDTC,     ~AEENDTC,
  "PILOT01",    "AE", "01-1130",      5, "2014-05-09", "2014-05-09",
  "PILOT01",    "AE", "01-1130",      6, "2014-05-22",           NA,
  "PILOT01",    "AE", "01-1130",      4, "2014-05-09", "2014-05-09",
  "PILOT01",    "AE", "01-1130",      8, "2014-05-22",           NA,
  "PILOT01",    "AE", "01-1130",      7, "2014-05-22",           NA,
  "PILOT01",    "AE", "01-1130",      2, "2014-03-09", "2014-03-09",
  "PILOT01",    "AE", "01-1130",      1, "2014-03-09", "2014-03-16",
  "PILOT01",    "AE", "01-1130",      3, "2014-03-09", "2014-03-16",
  "PILOT01",    "AE", "01-1133",      1, "2012-12-27",           NA,
  "PILOT01",    "AE", "01-1133",      3, "2012-12-27",           NA,
  "PILOT01",    "AE", "01-1133",      2, "2012-12-27",           NA,
  "PILOT01",    "AE", "01-1133",      4, "2012-12-27",           NA,
  "PILOT01",    "AE", "01-1211",      5, "2012-11-29",           NA,
  "PILOT01",    "AE", "01-1211",      1, "2012-11-16",           NA,
  "PILOT01",    "AE", "01-1211",      7, "2013-01-11",           NA,
  "PILOT01",    "AE", "01-1211",      8, "2013-01-11",           NA,
  "PILOT01",    "AE", "01-1211",      4, "2012-11-22",           NA,
  "PILOT01",    "AE", "01-1211",      2, "2012-11-21", "2012-11-21",
  "PILOT01",    "AE", "01-1211",      3, "2012-11-21",           NA,
  "PILOT01",    "AE", "01-1211",      6, "2012-12-09",           NA,
  "PILOT01",    "AE", "01-1211",      9, "2013-01-14", "2013-01-14",
  "PILOT01",    "AE", "09-1081",      2, "2014-05-01",           NA,
  "PILOT01",    "AE", "09-1081",      1, "2014-04-07",           NA,
  "PILOT01",    "AE", "09-1088",      1, "2014-05-08",           NA,
  "PILOT01",    "AE", "09-1088",      2, "2014-08-02",           NA
)

adsl <- tribble(
  ~STUDYID,   ~USUBJID,              ~TRTEDTM,      ~TRTEDT,
  "PILOT01", "01-1130", "2014-08-16 23:59:59", "2014-08-16",
  "PILOT01", "01-1133", "2013-04-28 23:59:59", "2013-04-28",
  "PILOT01", "01-1211", "2013-01-12 23:59:59", "2013-01-12",
  "PILOT01", "09-1081", "2014-04-27 23:59:59", "2014-04-27",
  "PILOT01", "09-1088", "2014-10-09 23:59:59", "2014-10-09"
) %>%
  mutate(
    across(TRTEDTM:TRTEDT, as.Date)
  )


lb <- tribble(
  ~STUDYID,  ~DOMAIN,  ~USUBJID, ~LBSEQ,             ~LBDTC,
  "PILOT01",    "LB", "01-1130",    219, "2014-06-07T13:20",
  "PILOT01",    "LB", "01-1130",    322, "2014-08-16T13:10",
  "PILOT01",    "LB", "01-1133",    268, "2013-04-18T15:30",
  "PILOT01",    "LB", "01-1133",    304, "2013-04-29T10:13",
  "PILOT01",    "LB", "01-1211",      8, "2012-10-30T14:26",
  "PILOT01",    "LB", "01-1211",    162, "2013-01-08T12:13",
  "PILOT01",    "LB", "09-1081",     47, "2014-02-01T10:55",
  "PILOT01",    "LB", "09-1081",    219, "2014-05-10T11:15",
  "PILOT01",    "LB", "09-1088",    283, "2014-09-27T12:13",
  "PILOT01",    "LB", "09-1088",    322, "2014-10-09T13:25"
)

dm <- tribble(
  ~STUDYID,  ~DOMAIN,  ~USUBJID, ~AGE,   ~AGEU,
  "PILOT01",    "DM", "01-1130",   84, "YEARS",
  "PILOT01",    "DM", "01-1133",   81, "YEARS",
  "PILOT01",    "DM", "01-1211",   76, "YEARS",
  "PILOT01",    "DM", "09-1081",   86, "YEARS",
  "PILOT01",    "DM", "09-1088",   69, "YEARS"
)

ae_start <- date_source(
  dataset_name = "ae",
  date = convert_dtc_to_dt(AESTDTC, highest_imputation = "M")
)
ae_end <- date_source(
  dataset_name = "ae",
  date = convert_dtc_to_dt(AEENDTC, highest_imputation = "M")
)

ae_ext <- ae %>%
  derive_vars_dt(
    dtc = AESTDTC,
    new_vars_prefix = "AEST",
    highest_imputation = "M"
  ) %>%
  derive_vars_dt(
    dtc = AEENDTC,
    new_vars_prefix = "AEEN",
    highest_imputation = "M"
  )

lb_date <- date_source(
  dataset_name = "lb",
  date = convert_dtc_to_dt(LBDTC)
)

lb_ext <- derive_vars_dt(
  lb,
  dtc = LBDTC,
  new_vars_prefix = "LB"
)

adsl_date <- date_source(dataset_name = "adsl", date = TRTEDT)

dm %>%
  derive_var_extreme_dt(
    new_var = LSTALVDT,
    ae_start, ae_end, lb_date, adsl_date,
    source_datasets = list(
      adsl = adsl,
      ae = ae_ext,
      lb = lb_ext
    ),
    mode = "last"
  ) %>%
  select(USUBJID, LSTALVDT)

# derive last alive date and traceability variables
ae_start <- date_source(
  dataset_name = "ae",
  date = convert_dtc_to_dt(AESTDTC, highest_imputation = "M"),
  set_values_to = exprs(
    LALVDOM = "AE",
    LALVSEQ = AESEQ,
    LALVVAR = "AESTDTC"
  )
)

ae_end <- date_source(
  dataset_name = "ae",
  date = convert_dtc_to_dt(AEENDTC, highest_imputation = "M"),
  set_values_to = exprs(
    LALVDOM = "AE",
    LALVSEQ = AESEQ,
    LALVVAR = "AEENDTC"
  )
)

lb_date <- date_source(
  dataset_name = "lb",
  date = convert_dtc_to_dt(LBDTC),
  set_values_to = exprs(
    LALVDOM = "LB",
    LALVSEQ = LBSEQ,
    LALVVAR = "LBDTC"
  )
)

adsl_date <- date_source(
  dataset_name = "adsl",
  date = TRTEDT,
  set_values_to = exprs(
    LALVDOM = "ADSL",
    LALVSEQ = NA_integer_,
    LALVVAR = "TRTEDT"
  )
)

dm %>%
  derive_var_extreme_dt(
    new_var = LSTALVDT,
    ae_start, ae_end, lb_date, adsl_date,
    source_datasets = list(
      adsl = adsl,
      ae = ae_ext,
      lb = lb_ext
    ),
    mode = "last"
  ) %>%
  select(USUBJID, LSTALVDT, LALVDOM, LALVSEQ, LALVVAR)

admiral documentation built on June 22, 2024, 9:06 a.m.