Title:	Drug Ontology Parsing Engine
Version:	2.1.0
Description:	Provides information on drug names (brand, generic and street) for drugs tracked by the DEA. There are functions that will search synonyms and return the drug names and types. The vignettes have extensive information on the work done to create the data for the package.
License:	MIT + file LICENSE
URL:	https://ctn-0094.github.io/DOPE/, https://github.com/CTN-0094/DOPE
BugReports:	https://github.com/CTN-0094/DOPE/issues
Encoding:	UTF-8
LazyData:	true
RoxygenNote:	7.1.1
Depends:	R (≥ 2.10)
Imports:	dplyr, magrittr, stats, stringr, tibble, tidytext, utils
Suggests:	purrr, knitr, rmarkdown, conflicted, readr, rvest, sqldf, tidyr, testthat, usethis, xml2
VignetteBuilder:	knitr
NeedsCompilation:	no
Packaged:	2021-06-18 18:09:49 UTC; godom
Author:	Raymond Balise [aut, cre], Layla Bouzoubaa [aut], Gabriel Odom [aut], Nathaniel Castor [aut]
Maintainer:	Raymond Balise <balise@miami.edu>
Repository:	CRAN
Date/Publication:	2021-06-18 18:40:02 UTC

Collapse Redundant Rows of a Lookup Table

Description

Given a Drug Lookup table as returned by the function lookup, collapse rows from unwanted columns

Usage

compress_lookup(
  lookupTable,
  compressOriginalWord = FALSE,
  compressClass = FALSE,
  compressCategory = FALSE,
  compressSynonym = TRUE
)

Arguments

Value

A compressed lookup table, with unwanted columns removed.

Examples

  longExampleTable <- lookup("dope", "methamphetamine")
  compress_lookup(longExampleTable)
  compress_lookup(longExampleTable, compressCategory = TRUE)

Drug brand info

Description

A dataset containing a unique record for each the drug categories and their respective brand names.

Usage

data(dea_brands)

Format

A tibble with 28 rows and 2 variables:

category

the drug category

brands

Drug brand name

Drug controlled substance synonyms

Description

A dataset containing

Usage

data(dea_controlled)

Format

A tibble with 29 rows and 3 variables:

substance

formal drug name

number

DEA number

schedule

drug schedule number

narcotic

Yes No indicator if the drug is a narcotic

synonym

synonym name

Drug ontology information from https://www.dea.gov/factsheets

Description

A dataset containing a record for each drug category listed on https://www.dea.gov/factsheets, the class in which that drug belongs in and path to the factsheet.

Usage

data(dea_factsheets)

Format

A tibble with 29 rows and 3 variables:

class

the drug class

category

the drug category

fact_path

the unique path to the drug's factsheet

Source

https://www.dea.gov/factsheets

Drug slang from DEA's DIR-020-17 Drug Slang Code Words.pdf

Description

A dataset containing slag provided by the DEA

Usage

data(dea_street_names)

Format

A tibble with 1734 rows and 3 variables:

category

DEA drug category

brand

Brand name of drug

slang

slang name

Simulated drug data

Description

A dataset containing a record of drugs used by a patient. The textdrug field is unstructured.

Usage

data(drug_df)

Format

A tibble with 500 rows and 3 variables:

textdrug

A free-text field of drug names

sex

Patient sex

race

Patient race

A vector with drug-specific stop words in English

Description

These are extraneous words or characters found in several clinical data that have been accumulated to form a vector that can be used to parse out drug names from corpus of text.

Usage

data(drug_stop_words)

Format

A vector with 47 words:

Data sent from IQVIA

Description

A dataset containing a unique record for each the drug names and their classes and categories.

Usage

data(iqvia)

Format

A tibble with 125 rows and 3 variables:

caegory

drug category

class

the drug class

synonym

drug name

Make a table with the class and category for a drug name

Description

This function provides a table with drug class and category information all of the known drugs.

Usage

lookup(
  drug_vec = NULL,
  ...,
  searchClass = TRUE,
  searchCategory = TRUE,
  searchSynonym = TRUE
)

Arguments

Value

A lookup table with category data.frame having four columns: original search term, drug class, drug category, and drug street name.

Examples

  lookup("zip", "shrooms")

A lookup table with drug class, category, and synonyms

Description

A dataset containing a record for each drug synonym

Usage

data(lookup_df)

Format

A tibble with 4,296 rows and 3 variables:

class

the drug class

category

the drug category

synonym

drug synonym

Make a table with the class and category for a drug name

Description

This function provides a table with drug synonyms that have the same class and category as the search term.

Usage

lookup_syn(drug_name)

Arguments

Value

A lookup table with category data.frame having three columns: drug class, drug category match, and synonym name.

Examples

  lookup_syn("zip")

Drug terms from https://www.noslang.com/drugs/dictionary

Description

A dataset containing a record for a drug rleated term and it's description. This contains both drug names and other things like drug amounts.

Usage

data(noslang_raw)

Format

A tibble with 3172 rows and 2 variables:

street_name

Slang term

description

Text description of drug term

Source

www.noslang.com

Drug slang from https://www.noslang.com/drugs/dictionary

Description

A dataset containing a record for a drug slang term and it's description.

Usage

data(noslang_street_names)

Format

A tibble with 3172 rows and 2 variables:

street_name

Slang term

description

Text description of drug term

Source

www.noslang.com

Parse a vector of free text containing drug information

Description

This function provides a dataframe of parsed out strings from a free text field, input as a vector, specified by the user.

Usage

parse(drug_vec)

Arguments

Value

A n x 1 vector of class character.

Examples

  parse("Lortab and Percocet")