Index
NlpService(interface)AnalyzeEntitiesRequest(message)AnalyzeEntitiesRequest.AlternativeOutputFormat(enum)AnalyzeEntitiesRequest.LicensedVocabulary(enum)AnalyzeEntitiesResponse(message)Entity(message)EntityMention(message)EntityMention.Feature(message)EntityMention.LinkedEntity(message)EntityMentionRelationship(message)TextSpan(message)
NlpService
A service to analyzing healthcare documents.
| AnalyzeEntities |
|---|
|
Analyze heathcare entity in a document. Its response includes the recognized entity mentions and the relationships between them. AnalyzeEntities uses context aware models to detect entities. This method can only analyze documents written in English.
|
AnalyzeEntitiesRequest
The request to analyze healthcare entities in a document.
| Fields | |
|---|---|
nlp_service |
The resource name of the service of the form: "projects/{project_id}/locations/{location_id}/services/nlp". |
document_content |
document_content is a document to be annotated. |
licensed_vocabularies[] |
A list of licensed vocabularies to use in the request, in addition to the default unlicensed vocabularies. |
alternative_output_format |
Optional. Alternative output format to be generated based on the results of analysis. |
AlternativeOutputFormat
Predefined list of available alternative output formats
| Enums | |
|---|---|
ALTERNATIVE_OUTPUT_FORMAT_UNSPECIFIED |
No alternative output format is specified. |
FHIR_BUNDLE |
FHIR bundle output. |
LicensedVocabulary
Predefined list of available licensed vocabularies
| Enums | |
|---|---|
LICENSED_VOCABULARY_UNSPECIFIED |
No licensed vocabulary specified. |
ICD10CM |
ICD-10-CM vocabulary |
SNOMEDCT_US |
SNOMED CT (US version) vocabulary |
AnalyzeEntitiesResponse
Includes recognized entity mentions and relationships between them.
| Fields | |
|---|---|
entity_mentions[] |
The |
entities[] |
The union of all the candidate entities that the entity_mentions in this response could link to. These are UMLS concepts or normalized mention content. |
relationships[] |
relationships contains all the binary relationships that were identified between entity mentions within the provided document. |
Union field alternative_output_format. The alternative supported format if the config was included in the request. alternative_output_format can be only one of the following: |
|
fhir_bundle |
The FHIR bundle ( |
Entity
The candidate entities that an entity mention could link to.
| Fields | |
|---|---|
entity_id |
entity_id is a first class field entity_id uniquely identifies this concept and its meta-vocabulary. For example, "UMLS/C0000970". |
preferred_term |
preferred_term is the preferred term for this concept. For example, "Acetaminophen". For ad hoc entities formed by normalization, this is the most popular unnormalized string. |
vocabulary_codes[] |
Vocabulary codes are first-class fields and differentiated from the concept unique identifier (entity_id). vocabulary_codes contains the representation of this concept in particular vocabularies, such as ICD-10, SNOMED-CT and RxNORM. These are prefixed by the name of the vocabulary, followed by the unique code within that vocabulary. For example, "RXNORM/A10334543". |
EntityMention
An entity mention in the document.
| Fields | |
|---|---|
mention_id |
mention_id uniquely identifies each entity mention in a single response. |
type |
The semantic type of the entity: UNKNOWN_ENTITY_TYPE, ALONE, ANATOMICAL_STRUCTURE, ASSISTED_LIVING, BF_RESULT, BM_RESULT, BM_UNIT, BM_VALUE, BODY_FUNCTION, BODY_MEASUREMENT, COMPLIANT, DOESNOT_FOLLOWUP, FAMILY, FOLLOWSUP, LABORATORY_DATA, LAB_RESULT, LAB_UNIT, LAB_VALUE, MEDICAL_DEVICE, MEDICINE, MED_DOSE, MED_DURATION, MED_FORM, MED_FREQUENCY, MED_ROUTE, MED_STATUS, MED_STRENGTH, MED_TOTALDOSE, MED_UNIT, NON_COMPLIANT, OTHER_LIVINGSTATUS, PROBLEM, PROCEDURE, PROCEDURE_RESULT, PROC_METHOD, REASON_FOR_NONCOMPLIANCE, SEVERITY, SUBSTANCE_ABUSE, UNCLEAR_FOLLOWUP. |
text |
text is the location of the entity mention in the document. |
linked_entities[] |
linked_entities are candidate ontological concepts that this entity mention may refer to. They are sorted by decreasing confidence. |
temporal_assessment |
How this entity mention relates to the subject temporally. Its value is one of: CURRENT, CLINICAL_HISTORY, FAMILY_HISTORY, UPCOMING, ALLERGY |
certainty_assessment |
The certainty assessment of the entity mention. Its value is one of: LIKELY, SOMEWHAT_LIKELY, UNCERTAIN, SOMEWHAT_UNLIKELY, UNLIKELY, CONDITIONAL |
subject |
The subject this entity mention relates to. Its value is one of: PATIENT, FAMILY_MEMBER, OTHER |
confidence |
The model's confidence in this entity mention annotation. A number between 0 and 1. |
additional_info[] |
Additional information about the entity mention. For example, for an entity mention of type |
Feature
A feature of an entity mention.
| Fields | |
|---|---|
value |
The value of this feature annotation. Its range depends on the type of the feature. |
confidence |
The model's confidence in this feature annotation. A number between 0 and 1. |
LinkedEntity
EntityMentions can be linked to multiple entities using a LinkedEntity message lets us add other fields, e.g. confidence.
| Fields | |
|---|---|
entity_id |
entity_id is a concept unique identifier. These are prefixed by a string that identifies the entity coding system, followed by the unique identifier within that system. For example, "UMLS/C0000970". This also supports ad hoc entities, which are formed by normalizing entity mention content. |
EntityMentionRelationship
Defines directed relationship from one entity mention to another.
| Fields | |
|---|---|
subject_id |
subject_id is the id of the subject entity mention. |
object_id |
object_id is the id of the object entity mention. |
confidence |
The model's confidence in this annotation. A number between 0 and 1. |
TextSpan
A span of text in the provided document.
| Fields | |
|---|---|
content |
The original text contained in this span. |
begin_offset |
The unicode codepoint index of the beginning of this span. |