document_processor: Functions to process documents with NLP engine Process a...

In CEDARS: Simple and Efficient Pipeline for Electronic Health Record Annotation

Description

Processes one EHR document with NLP pipeline and applies NegEx.

Usage

document_processor(
  text_df,
  text_format,
  nlp_engine,
  negex_simp,
  negex_depth,
  single_core_model = NA
)

Arguments

text_df	Dataframe of 1 row, containing all text metadata, including: text_id, text_date, text_sequence, doc_section_name, doc_id, text_tag_1, text_tag_2, text_tag_3, text_tag_4, text_tag_5, text_tag_6, text_tag_7, text_tag_8, text_tag_9 and text_tag_10.
text_format	Text format.
nlp_engine	NLP engine, UDPipe only for now.
negex_simp	Simplified negex.
negex_depth	Maximum distance between negation item and token to negate. Shorter distances will result in decreased sensitivity but increased specificity for negation.
single_core_model	NLP model in case parallel processing is not used.

Value

NLP annotations dataframe.

CEDARS documentation built on Feb. 7, 2021, 5:06 p.m.