User Tools

Site Tools


documentation:cdm:note_nlp

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
documentation:cdm:note_nlp [2017/03/06 06:08]
rimma_belenkaya
documentation:cdm:note_nlp [2017/09/25 15:02] (current)
clairblacketer
Line 1: Line 1:
 ===== NOTE_NLP table ===== ===== NOTE_NLP table =====
 +**THIS IS OUTDATED. All documentation is now on the [[https://​github.com/​OHDSI/​CommonDataModel/​wiki|github wiki]]. Please refer there or to the [[projects:​workgroups:​cdm-wg|CDM working group]] for more information**
 +
 +This table was added with version 5.2 (1-Feb-2017) of the OMOP CDM.
 +
 +---
 +
 The NOTE table encodes all output of NLP on clinical notes. Each row represents a single extracted term from a note. The NOTE table encodes all output of NLP on clinical notes. Each row represents a single extracted term from a note.
-.+
 ^Field^Required^Type^Description^ ^Field^Required^Type^Description^
-|note_NLP_id|Yes|integer|A unique identifier for each note.| +|note_nlp_id|Yes|Big Integer|A unique identifier for each term extracted from a note.| 
-|note_id|Yes|integer|A ​unique identifier for each note.| +|note_id|Yes|integer|A ​foreign key to the Note table note the term was extracted from.| 
-|section_concept_id|Yes|integer|A ​unique identifier for each note.| +|section_concept_id|No|integer|A ​foreign key to the predefined Concept in the Standardized Vocabularies representing the section of the extracted term.| 
-|snippet +|snippet|No|string(250)|A small window of text surrounding the term.
-|chars +|offset|No|string(50)|Character offset of the extracted term in the input note.| 
-|lexical_variant +|lexical_variant|Yes|string(250)|Raw text extracted by the NLP tool.| 
-|note_NLP_concept_id +|note_nlp_concept_id|No|integer|Foreign ​key to Concept ​table. Represents ​the normalized concept for extracted term. Domain of the term is represented as part of the Concept table.| 
-|nlp_system +|note_nlp_source_concept_id|No|integer|A foreign key to Concept ​that refers to the code in the source vocabulary used by the NLP system.| 
-|nlp_date|Yes|date|The date the note was recorded.| +|nlp_system|No|string(250)|Name and version ​of the NLP system that extracted ​the term.| 
-|term_exists|No|datetime|The date and time the note was recorded.| +|nlp_date|Yes|date|The date of the note processing.| 
-|note_type_concept_id|Yes|integer|A foreign ​key to the predefined ​Concept ​in the Standardized Vocabularies reflecting ​the type, origin or provenance ​of the Note.| +|nlp_date_time|No|datetime|The date and time of the note processing.| 
-|value_as_concept_id|Yes|integer|A foreign key to the predefined ​Concept in the Standardized Vocabularies reflecting ​the HL7 LOINC Document Type Vocabulary classification of the note.| +|term_exists|No|Boolean|Term_exists is defined as a flag that indicates if the patient actually has or had the condition. Any of the following modifiers would make Term_exists false: Negation ​true; Subject ​[anything other than the patient]; Conditional ​true; Rule_out ​true; Uncertain ​very low certainty or any lower certainties. A complete lack of modifiers would make Term_exists true. For the modifiers that are there, they would have to have these values: Negation ​false; Subject ​patient; Conditional ​false; Rule_out = false; Uncertain = true or high or moderate or even low (could argue about low).| 
-|value_as_number|No|varchar(250)|The title of the Note as it appears in the source.| +|term_temporal|No|string(50)|Term_temporal ​is to indicate if a condition is “present” or just in the “past”. The following would be past: History = true; Concept_date = anything before ​the time of the report.| 
-|value _as_string|Yes|RBDMS dependent text|The content ​of the Note.| +|term_modifiers|No|string(2000)|Describes compactly all the modifiers extracted by nlp system. For example, “son has rash” → “negated=no,​subject=family,​certainty=undef,​conditional=false,​general=false”. Value will be saved as one of the modifiers.| 
-|unit_concept_id|Yes|integer|A foreign key to the predefined Concept in the Standardized Vocabularies reflecting ​the note character encoding type.| +
-|term_temporal|Yes|integer|A foreign key to the predefined Concept in the Standardized Vocabularies reflecting the language ​of the note.| +
-|term_modifiers|No|integer|A foreign key to the Provider in the PROVIDER table who took the Note.| +
-==== Conventions ​==== +
-  * The NOTE table contains free text (in ASCII, ​or preferably in UTF8 formattaken by a healthcare Provider+
-  * The Visit during which the note was written ​is recorded through a reference ​to the VISIT_OCCURRENCE tableThis information is not always available. +
-  * The Provider making ​the note is recorded through a reference to the PROVIDER table. This information is not always available+
-  * The type of note_text is CLOB or VARCHAR(MAXdepending on RDBMS+
  
documentation/cdm/note_nlp.1488780486.txt.gz · Last modified: 2017/03/06 06:08 by rimma_belenkaya