Admiral Adtte

library(admiral)
library(dplyr)
library(lubridate)
library(pharmaversesdtm)
library(pharmaverseadam)

# Load event source domain(s) — substitute with the domain(s) relevant to the endpoint
ae   <- pharmaversesdtm::ae
adsl <- pharmaverseadam::adsl  # assumed derived upstream

stopifnot(nrow(ae) > 0)

ae <- ae |> select(-DOMAIN)
# Repeat for every source domain used in event_source() or censor_source() calls

# REVIEW: Confirm which ADSL variables are required per the ADTTE spec.
#   TRTSDT is the conventional STARTDT for most TTE parameters. If the endpoint
#   uses randomization date instead, use RANDDT. Add population flags as needed.
adtte <- ae |>
  derive_vars_merged(
    dataset_add = adsl,
    by_vars     = exprs(STUDYID, USUBJID),
    new_vars    = exprs(TRTSDT, TRTEDT, TRT01P, TRT01PN, TRT01A, TRT01AN,
                        SAFFL, ITTFL)
  )

adtte <- adtte |>
  derive_vars_dt(
    dtc             = AESTDTC,
    new_vars_prefix = "AST",
    date_imputation = "first",
    flag_imputation = "auto"
  )

# REVIEW: The event filter below (AESER == "Y") is the most common definition
#   for a time-to-first-serious-AE endpoint. Confirm the exact event definition
#   from the ADaM ADTTE spec and SAP:
#   - Which AE terms or flags qualify? (AESER, AETOXGR >= 3, specific AEDECOD terms)
#   - Does the event require onset during treatment only, or ever?
#   - What is the event date — onset (ASTDT) or report date?
ttae_event <- event_source(
  dataset_name  = "ae",
  filter        = AESER == "Y",          # PLACEHOLDER — confirm from SAP
  date          = ASTDT,
  set_values_to = exprs(
    EVNTDESC = "Serious adverse event",
    SRCDOM   = "AE",
    SRCVAR   = "AESTDTC",
    SRCSEQ   = AESEQ
  )
)

# REVIEW: The censoring date below (TRTEDT + 30) is a common proxy for
#   "30 days post last dose" TTE endpoints. Confirm the censoring hierarchy
#   from the ADaM ADTTE spec and SAP:
#   - What is the primary censoring date? (last contact, last dose + window, LSDT)
#   - Is the post-treatment window 30, 28, or another number of days?
#   - What is CNSDTDSC for each censoring type? Confirm against define.xml CT.
ttae_censor <- censor_source(
  dataset_name  = "adsl",
  date          = TRTEDT + 30,           # PLACEHOLDER — confirm from SAP
  set_values_to = exprs(
    EVNTDESC = NA_character_,
    # REVIEW: CNSDTDSC must match define.xml controlled terminology exactly.
    #   Common values: "Last dose date + 30 days", "Last known alive date",
    #   "End of study". Confirm the full list and exact strings from the spec.
    CNSDTDSC = "Last dose date + 30 days",   # PLACEHOLDER — confirm CT from spec
    SRCDOM   = "ADSL",
    SRCVAR   = "TRTEDT"
  )
)

# REVIEW: PARAMCD and PARAM must match the ADaM ADTTE spec exactly.
adtte <- derive_param_tte(
  dataset_adsl      = adsl,
  source_datasets   = list(adsl = adsl, ae = ae),
  start_date        = TRTSDT,
  event_conditions  = list(ttae_event),
  censor_conditions = list(ttae_censor),
  set_values_to     = exprs(
    PARAMCD = "TTAE",
    PARAM   = "Time to First Serious Adverse Event"
  )
)

adtte <- adtte |>
  derive_vars_duration(
    new_var      = AVAL,
    start_date   = STARTDT,
    end_date     = ADT,
    out_unit     = "days",
    add_one      = TRUE,    # CDISC: AVAL = 1 when event/censoring on start date
    trunc_out    = FALSE
  )

# Print event/censor summary — inspect for implausible counts before proceeding
event_summary <- adtte |>
  count(PARAMCD, CNSR)
print(event_summary)

# CNSR must be integer 0 (event) or 1 (censored) — never logical or character
stopifnot(all(adtte$CNSR %in% c(0L, 1L)))

# AVAL must be strictly positive — CDISC requires >= 1 day
stopifnot(all(adtte$AVAL >= 1, na.rm = TRUE))

# CNSDTDSC must be non-missing for every censored subject
stopifnot(!any(adtte$CNSR == 1L & is.na(adtte$CNSDTDSC)))

# EVNTDESC must be non-missing for every subject with an event
stopifnot(!any(adtte$CNSR == 0L & is.na(adtte$EVNTDESC)))

# Uniqueness: one record per subject per PARAMCD
dup_check <- adtte |>
  count(STUDYID, USUBJID, PARAMCD) |>
  filter(n > 1)
if (nrow(dup_check) > 0) {
  stop("Duplicate subject-PARAMCD records found:\n",
       paste(paste(dup_check$USUBJID, dup_check$PARAMCD), collapse = "\n"))
}

# Required variable presence check
required_vars <- c(
  "STUDYID", "USUBJID", "PARAMCD", "PARAM",
  "AVAL", "CNSR", "CNSDTDSC", "EVNTDESC",
  "ADT", "STARTDT"
)
missing_vars <- setdiff(required_vars, names(adtte))
if (length(missing_vars) > 0) {
  stop("Missing required ADTTE variables: ", paste(missing_vars, collapse = ", "))
}

# Example: adding a second parameter (time to any AE, grade ≥ 3)
ttae3_event <- event_source(
  dataset_name  = "ae",
  filter        = AETOXGR >= 3,         # REVIEW — confirm grading threshold from SAP
  date          = ASTDT,
  set_values_to = exprs(
    EVNTDESC = "Grade 3+ adverse event",
    SRCDOM = "AE", SRCVAR = "AESTDTC", SRCSEQ = AESEQ
  )
)

adtte <- adtte |>
  derive_param_tte(
    dataset_adsl      = adsl,
    source_datasets   = list(adsl = adsl, ae = ae),
    start_date        = TRTSDT,
    event_conditions  = list(ttae3_event),
    censor_conditions = list(ttae_censor),   # reuse common censoring rule
    set_values_to     = exprs(
      PARAMCD = "TTAE3",
      PARAM   = "Time to First Grade 3+ Adverse Event"
    )
  )