Entity Document Span

DescriptionA set of data that records sections of text within an unformatted text document. This data is created and used by during document analysis by a National Language Processing (NLP) engine for the purpose of identifying certain types of data, for example, a patient problem or a procedure. This analysis involves identifying the beginning and end of a text string that describes a data type, for example, a patient problem. This text string is known as a 'span'. The beginning of the string is identified by the character count within the document where the span begins and the end is the character count where the span ends.

Attributes
Annotator CodeAnnotator Code
Annotator Version NumAnnotator Version Num
Confidence FactorConfidence Factor
Confidence Factor ValueConfidence Factor Value
Document SectionDocument Section
Span Begin CntSpan Begin Cnt
Span Cover TextSpan Cover Text
Span End CntSpan End Cnt

Relationship
Document Span_Document_FKDocument Span_Document_FK

Dependencies
 NONE

Reverse Dependencies
 

Attribute Details

 Annotator Code
DescriptionIdentifies the annotator or Natural Language Processing engine used to extract the code.
Data TypeStandards - Data Domains.ddm/Data Domains/Enumeration [VARCHAR(20)]
Is Part Of PrimaryKeyfalse
Is Requiredfalse
Is Derivedfalse
Is Surrogate Keyfalse



 Annotator Version Num
DescriptionIndicates the version number for the Annotator or Natural Language Processing engine used to extract the code.
Data TypeStandards - Data Domains.ddm/Data Domains/Alphanumeric [VARCHAR(80)]
Is Part Of PrimaryKeyfalse
Is Requiredfalse
Is Derivedfalse
Is Surrogate Keyfalse



 Confidence Factor
DescriptionIndicates the nature of patient problem identification.

For example:
possible
rule_out
almost
at_risk
likely
negative
positive
Data TypeStandards - Data Domains.ddm/Data Domains/Enumeration [VARCHAR(20)]
Is Part Of PrimaryKeyfalse
Is Requiredfalse
Is Derivedfalse
Is Surrogate Keyfalse



 Confidence Factor Value
DescriptionThe ratio, out of 100, that a problem was correctly discovered in an unstructured document by the Natural Language Processing Engine.
Data TypeStandards - Data Domains.ddm/Data Domains/Rate [FLOAT(5)]
Is Part Of PrimaryKeyfalse
Is Requiredfalse
Is Derivedfalse
Is Surrogate Keyfalse



 Document Section
DescriptionIndicates the section of a document.

For example:
Complaint
Medical History
Family Medical History
Lab Results
Physical Examination etc.
Data TypeStandards - Data Domains.ddm/Data Domains/Enumeration [VARCHAR(20)]
Is Part Of PrimaryKeyfalse
Is Requiredfalse
Is Derivedfalse
Is Surrogate Keyfalse



 Span Begin Cnt
DescriptionThe character count of the text within a document where the span begins.The Span can include procedure,problem,medication, diagnosis codes etc.
Data TypeStandards - Data Domains.ddm/Data Domains/Count [INTEGER]
Is Part Of PrimaryKeyfalse
Is Requiredfalse
Is Derivedfalse
Is Surrogate Keyfalse



 Span Cover Text
DescriptionA string of text within an unformatted text document that has been identified by the Natural Language Processing engine as a Span.
Data TypeStandards - Data Domains.ddm/Data Domains/Description [VARCHAR(250)]
Is Part Of PrimaryKeyfalse
Is Requiredfalse
Is Derivedfalse
Is Surrogate Keyfalse



 Span End Cnt
DescriptionThe character count of the text within a document where the span ends. The Span can include procedure,problem,medication, diagnosis codes etc.
Data TypeStandards - Data Domains.ddm/Data Domains/Count [INTEGER]
Is Part Of PrimaryKeyfalse
Is Requiredfalse
Is Derivedfalse
Is Surrogate Keyfalse

Relationship Details

 Document Span_Document_FK
Is Identifying Relationshiptrue
Child TableDocument Span
Child MultiplicityZERO_TO_MANY
Child Referential Integrity: On DeleteNONE
Child Referential Integrity: On InsertNONE
Child Referential Integrity: On UpdateNONE
Parent TableDocument
Parent MultiplicityONE
Parent Referential Integrity: On DeleteNONE
Parent Referential Integrity: On InsertNONE
Parent Referential Integrity: On UpdateNONE