Differences

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

--- documentation:cdm:note_nlp [2017/03/06 06:01] – created rimma_belenkaya
+++ documentation:cdm:note_nlp [2017/09/25 15:02] (current) – clairblacketer
@@ Line 1: / Line 1: @@
-===== NOTE table =====
+===== NOTE_NLP table =====
-The NOTE table captures unstructured information that was recorded by a provider about a patient in free text notes on a given date.
+**THIS IS OUTDATED.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.
 ^Field^Required^Type^Description^
-|note_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.|
-|person_id|Yes|integer|A foreign key identifier to the Person about whom the Note was recorded. The demographic details of that Person are stored in the PERSON table.|
+|note_id|Yes|integer|A foreign key to the Note table note the term was extracted from.|
-|note_date |Yes|date|The date the note was recorded.|
+|section_concept_id|No|integer|A foreign key to the predefined Concept in the Standardized Vocabularies representing the section of the extracted term.|
-|note_datetime|No|datetime|The date and time the note was recorded.|
+|snippet|No|string(250)|A small window of text surrounding the term.|
-|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.|
+|offset|No|string(50)|Character offset of the extracted term in the input note.|
-|note_class_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.|
+|lexical_variant|Yes|string(250)|Raw text extracted by the NLP tool.|
-|note_title|No|varchar(250)|The title of the Note as it appears in the source.|
+|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.|
-|note_text|Yes|RBDMS dependent text|The content of the Note.|
+|note_nlp_source_concept_id|No|integer|A foreign key to a Concept that refers to the code in the source vocabulary used by the NLP system.|
-|encoding_concept_id|Yes|integer|A foreign key to the predefined Concept in the Standardized Vocabularies reflecting the note character encoding type.|
+|nlp_system|No|string(250)|Name and version of the NLP system that extracted the term.|
-|language_concept_id|Yes|integer|A foreign key to the predefined Concept in the Standardized Vocabularies reflecting the language of the note.|
+|nlp_date|Yes|date|The date of the note processing.|
-|provider_id|No|integer|A foreign key to the Provider in the PROVIDER table who took the Note.|
+|nlp_date_time|No|datetime|The date and time of the note processing.|
-|visit_occurrence_id|No|integer|Foreign key to the Visit in the VISIT_OCCURRENCE table when the Note was taken.|
+|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).|
-==== Conventions ====
+|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.|
-  * The NOTE table contains free text (in ASCII, or preferably in UTF8 format) taken by a healthcare Provider.
+|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.|
-  * The Visit during which the note was written is recorded through a reference to the VISIT_OCCURRENCE table. This 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(MAX) depending on RDBMS