Skip to contents

Codelists

codelists.Rmd

This package uses specific codelists developed by GSK.
These codelists are documented and can be accessed within the package.

Below is a list of all the codelists included in the package:

If you want to modify these codelists, please note that the package uses a compressed version of them for internal purposes. To facilitate your development process, we provide a script that allows you to load your codelists from an Excel format and ensure their compatibility with the package.

# Change these --------------
# Paths to codelists
icd9_cm_codelist_path <- "icd9_cm_codes.xlsx"
icd10_cm_codelist_path <- "icd10_cm_codes.xlsx"
icd9_proc_codelist_path <- "icd9_proc_codes.xlsx"
icd10_proc_codelist_path <- "icd10_proc_codes.xlsx"
cpt_codelist_path <- "cpt_pregnancy_codes.xlsx"
l_d_codelist_path <- "labour_and_delivery_list.xlsx"

# No need to change anything else ------------
# Loading packages
library(readxl)
library(dplyr)
library(stringr)
library(tidyr)
library(logr)
library(assertr)

# Defining helper functions
validation_error <- function(list_of_errors, data = NULL, ...) {
  # we are checking to see if there are any errors that
  # are still attached to the data.frame
  if (!is.null(data) && !is.null(attr(data, "assertr_errors"))) {
    errors <- append(attr(data, "assertr_errors"), errors)
  }

  num.of.errors <- length(list_of_errors)

  preface <- sprintf(
    "There %s %d error%s:\n",
    ifelse(num.of.errors == 1, "is", "are"),
    num.of.errors,
    ifelse(num.of.errors == 1, "", "s")
  )
  error_string <- lapply(list_of_errors, function(x) paste(x[["message"]], collapse = "\n"))
  error_string <- c(preface, error_string)
  error_string <- paste(error_string, collapse = "\n")
  put(error_string)
}

success_confirmation <- function(data = NULL) {
  put("Step completed successfully.")
}

# Starting log -------------
log_file <- log_open(show_notes = FALSE)

# Importing pregnancy codes (ICD-CM-9, ICD-CM-10, and CPT) relevant to pregnancy and delivery ---------
## ICD-CM-9: International Classification of Diseases, Ninth Revision, Clinical Modification
## ICD-CM-10: International Classification of Diseases, Tenth Revision, Clinical Modification
## CPT: Current Procedural Terminology, maintained by the American Medical Association (AMA)

##  Import Pregnancy Code Lists

icd9_diagnosis_pregnancy_codes <- read_excel(icd9_cm_codelist_path, trim_ws = TRUE, .name_repair = str_to_lower) %>%
  mutate(secondary_outcome = replace_na(secondary_outcome, " ")) %>%
  mutate(
    outcome = str_to_sentence(outcome),
    secondary_outcome = str_to_sentence(secondary_outcome)
  )

icd10_diagnosis_pregnancy_codes <- read_excel(icd10_cm_codelist_path, trim_ws = TRUE, .name_repair = str_to_lower) %>%
  mutate(secondary_outcome = replace_na(secondary_outcome, " ")) %>%
  mutate(
    outcome = str_to_sentence(outcome),
    secondary_outcome = str_to_sentence(secondary_outcome)
  )

icd9_procedure_pregnancy_codes <- read_excel(icd9_proc_codelist_path, trim_ws = TRUE, .name_repair = str_to_lower) %>%
  mutate(outcome = str_to_sentence(outcome))

icd10_procedure_pregnancy_codes <- read_excel(icd10_proc_codelist_path, trim_ws = TRUE, .name_repair = str_to_lower) %>%
  mutate(outcome = str_to_sentence(outcome))

cpt_pregnancy_codes <- read_excel(cpt_codelist_path, trim_ws = TRUE, .name_repair = str_to_lower) %>%
  mutate(
    outcome = replace_na(outcome, " "),
    secondary_outcome = replace_na(secondary_outcome, " ")
  ) %>%
  mutate(
    outcome = str_to_sentence(outcome),
    secondary_outcome = str_to_sentence(secondary_outcome)
  )

## Import Labor/Delivery Code List

labor_delivery_codes <- read_excel(l_d_codelist_path, trim_ws = TRUE, .name_repair = str_to_lower)

# Data Validation ----------

sep("Loading ICD-CM-9 diagnosis pregnancy codes")
icd9_diagnosis_pregnancy_codes %>%
  chain_start() %>%
  verify(has_all_names("icd9cm", "description", "outcome", "secondary_outcome")) %>%
  verify(has_class("icd9cm", "description", "outcome", "secondary_outcome", class = "character")) %>%
  verify(has_class("final_trimester_code", class = "numeric")) %>%
  assert(not_na, "icd9cm", "description", "outcome", "secondary_outcome") %>%
  chain_end(
    success_fun = success_confirmation,
    error_fun = validation_error
  )

sep("Loading ICD-CM-10 diagnosis pregnancy codes")
icd10_diagnosis_pregnancy_codes %>%
  chain_start() %>%
  verify(has_all_names("icd10cm", "description", "outcome", "secondary_outcome")) %>%
  verify(has_class("icd10cm", "description", "outcome", "secondary_outcome", class = "character")) %>%
  verify(has_class("final_trimester_code", class = "numeric")) %>%
  assert(not_na, "icd10cm", "description", "outcome", "secondary_outcome") %>%
  chain_end(
    success_fun = success_confirmation,
    error_fun = validation_error
  )

sep("Loading ICD-CM-9 procedure pregnancy codes")
icd9_procedure_pregnancy_codes %>%
  chain_start() %>%
  verify(has_all_names("icd9_proc", "description", "outcome", "final_trimester_code")) %>%
  verify(has_class("icd9_proc", "description", "outcome", class = "character")) %>%
  verify(has_class("final_trimester_code", class = "numeric")) %>%
  assert(not_na, "icd9_proc", "description", "outcome", "final_trimester_code") %>%
  chain_end(
    success_fun = success_confirmation,
    error_fun = validation_error
  )

sep("Loading ICD-CM-10 procedure pregnancy codes")
icd10_procedure_pregnancy_codes %>%
  chain_start() %>%
  verify(has_all_names("icd10_proc", "description", "outcome", "final_trimester_code")) %>%
  verify(has_class("icd10_proc", "description", "outcome", class = "character")) %>%
  verify(has_class("final_trimester_code", class = "numeric")) %>%
  assert(not_na, "icd10_proc", "description", "outcome", "final_trimester_code") %>%
  chain_end(
    success_fun = success_confirmation,
    error_fun = validation_error
  )

sep("Loading CPT pregnancy codes")
cpt_pregnancy_codes %>%
  chain_start() %>%
  verify(has_all_names("cpt", "cpt_desc", "outcome", "secondary_outcome", "final_trimester_code")) %>%
  verify(has_class("cpt", "cpt_desc", "outcome", "secondary_outcome", class = "character")) %>%
  verify(has_class("final_trimester_code", class = "numeric")) %>%
  assert(not_na, "cpt", "cpt_desc", "outcome", "secondary_outcome", "final_trimester_code") %>%
  chain_end(
    success_fun = success_confirmation,
    error_fun = validation_error
  )

sep("Loading labor delivery codes")
labor_delivery_codes %>%
  chain_start() %>%
  verify(has_all_names("code", "description")) %>%
  verify(has_class("code", "description", class = "character")) %>%
  assert(not_na, "code", "description") %>%
  chain_end(
    success_fun = success_confirmation,
    error_fun = validation_error
  )

# Closing log -------------
log_close()

# Storing data for internal purposes -------------
usethis::use_data(icd9_diagnosis_pregnancy_codes,icd10_diagnosis_pregnancy_codes,icd9_procedure_pregnancy_codes,icd10_procedure_pregnancy_codes,cpt_pregnancy_codes,labor_delivery_codes, internal = TRUE)