std_term | R Documentation |
Returns a set of SNOMED concepts (as a SNOMEDconcept vector) which can be used to exclude findings in the MedCAT named entity recognition step, or blacklist (filter out) findings from the final output.
std_term(
x,
stopwords = c("the", "of", "by", "with", "to", "into", "and", "or", "both", "at", "as",
"and/or", "in"),
hyphens_to_space = FALSE,
remove_stopwords = FALSE,
remove_words_in_parentheses = FALSE
)
x |
text to standardise |
stopwords |
character vector of words to ignore or remove |
hyphens_to_space |
whether to convert hyphens to spaces (default is to remove them) |
remove_stopwords |
whether to remove stopwords |
remove_words_in_parentheses |
whether to remove words in parentheses (which are usually an alternative form or explanation for other parts of the phrase) |
exclude_irrelevant_findingssocial history (except housing problems and care needs), administrative statuses (except registered disabled) and for concept detection
blacklist_vague_findingsvague findings and disorders, intended to be used in the blacklist
blacklist_almost_all_except_diseasesalmost all findings and vague disorders, intended to be used in the blacklist
standardised text with space at start and end, lower case (except for capitalised words or words with unusual capitalisation) and other options applied as needed
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.