note_nlp
Standard Clinical Data Table
Table Columns
| field | type | required |
|---|---|---|
| note_nlp_id | integer | Yes |
| note_id | integer | Yes |
| section_concept_id | integer | No |
| snippet | varchar(250) | No |
| offset | varchar(50) | No |
| lexical_variant | varchar(250) | Yes |
| note_nlp_concept_id | integer | No |
| note_nlp_source_concept_id | integer | No |
| nlp_system | varchar(250) | No |
| nlp_date | date | Yes |
| nlp_datetime | datetime | No |
| term_exists | varchar(1) | No |
| term_temporal | varchar(50) | No |
| term_modifiers | varchar(2000) | No |
Columns Description
note_nlp_id
A unique identifier for the NLP record.
note_id
A foreign key to the Note table note the NLP record is associated to.
section_concept_id
A foreign key to the predefined Concept in the Standardized Vocabularies representing the section of the extracted text.
snippet
A small window of text surrounding the term as it appears in the source document.
offset
Character offset of the extracted term in the source document.
lexical_variant
Raw text extracted from the NLP tool.
note_nlp_concept_id
A foreign key to the predefined Concept in the Standardized Vocabularies reflecting the normalized concept for the extracted term. Maps to the same domain of the extracted term.
note_nlp_source_concept_id
A foreign key to a Concept that refers to the code in the source vocabulary used by the NLP system.
nlp_system
Name and version of the NLP system that extracted the term. Useful for data provenance.
nlp_date
The date of the note processing.
nlp_datetime
The date and time of the note processing.
term_exists
A summary modifier that signifies presence or absence of the term for a given patient. Useful for quick querying. ‘Y’, ‘N’, or NULL.
term_temporal
An optional time modifier associated with the extracted term. (e.g. “history of” = past, “future” = future, null = present).
term_modifiers
A compact description of all the modifiers of the specific term extracted by the NLP system. (e.g. “son has rash” = negated=no,subject=family, certainty=undef,conditional=false,general=false).
Conventions
- Each NLP extraction should be linked to a specific NOTE record
- Multiple NLP records can be associated with a single note
- The lexical_variant contains the actual extracted text as found in the source
- Standardized concepts should be used when possible for note_nlp_concept_id
- Term modifiers capture important contextual information like negation, uncertainty, and temporality