2021/12/08 - AWS Comprehend Medical - 5 new3 updated api methods
Changes This release adds a new set of APIs (synchronous and batch) to support the SNOMED-CT ontology.
Stops an InferSNOMEDCT inference job in progress.
See also: AWS API Documentation
Request Syntax
client.stop_snomedct_inference_job(
JobId='string'
)
string
[REQUIRED]
The job id of the asynchronous InferSNOMEDCT job to be stopped.
dict
Response Syntax
{
'JobId': 'string'
}
Response Structure
(dict) --
JobId (string) --
The identifier generated for the job. To get the status of job, use this identifier with the DescribeSNOMEDCTInferenceJob operation.
Gets the properties associated with an InferSNOMEDCT job. Use this operation to get the status of an inference job.
See also: AWS API Documentation
Request Syntax
client.describe_snomedct_inference_job(
JobId='string'
)
string
[REQUIRED]
The identifier that Amazon Comprehend Medical generated for the job. The StartSNOMEDCTInferenceJob operation returns this identifier in its response.
dict
Response Syntax
{
'ComprehendMedicalAsyncJobProperties': {
'JobId': 'string',
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'PARTIAL_SUCCESS'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'Message': 'string',
'SubmitTime': datetime(2015, 1, 1),
'EndTime': datetime(2015, 1, 1),
'ExpirationTime': datetime(2015, 1, 1),
'InputDataConfig': {
'S3Bucket': 'string',
'S3Key': 'string'
},
'OutputDataConfig': {
'S3Bucket': 'string',
'S3Key': 'string'
},
'LanguageCode': 'en',
'DataAccessRoleArn': 'string',
'ManifestFilePath': 'string',
'KMSKey': 'string',
'ModelVersion': 'string'
}
}
Response Structure
(dict) --
ComprehendMedicalAsyncJobProperties (dict) --
Provides information about a detection job.
JobId (string) --
The identifier assigned to the detection job.
JobName (string) --
The name that you assigned to the detection job.
JobStatus (string) --
The current status of the detection job. If the status is FAILED, the Message field shows the reason for the failure.
Message (string) --
A description of the status of a job.
SubmitTime (datetime) --
The time that the detection job was submitted for processing.
EndTime (datetime) --
The time that the detection job completed.
ExpirationTime (datetime) --
The date and time that job metadata is deleted from the server. Output files in your S3 bucket will not be deleted. After the metadata is deleted, the job will no longer appear in the results of the ListEntitiesDetectionV2Job or the ListPHIDetectionJobs operation.
InputDataConfig (dict) --
The input data configuration that you supplied when you created the detection job.
S3Bucket (string) --
The URI of the S3 bucket that contains the input data. The bucket must be in the same region as the API endpoint that you are calling.
Each file in the document collection must be less than 40 KB. You can store a maximum of 30 GB in the bucket.
S3Key (string) --
The path to the input data files in the S3 bucket.
OutputDataConfig (dict) --
The output data configuration that you supplied when you created the detection job.
S3Bucket (string) --
When you use the OutputDataConfig object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data. The URI must be in the same region as the API endpoint that you are calling. The location is used as the prefix for the actual location of the output.
S3Key (string) --
The path to the output data files in the S3 bucket. Comprehend Medical; creates an output directory using the job ID so that the output from one job does not overwrite the output of another.
LanguageCode (string) --
The language code of the input documents.
DataAccessRoleArn (string) --
The Amazon Resource Name (ARN) that gives Comprehend Medical; read access to your input data.
ManifestFilePath (string) --
The path to the file that describes the results of a batch job.
KMSKey (string) --
The AWS Key Management Service key, if any, used to encrypt the output files.
ModelVersion (string) --
The version of the model used to analyze the documents. The version number looks like X.X.X. You can use this information to track the model used for a particular batch of documents.
Starts an asynchronous job to detect medical concepts and link them to the SNOMED-CT ontology. Use the DescribeSNOMEDCTInferenceJob operation to track the status of a job.
See also: AWS API Documentation
Request Syntax
client.start_snomedct_inference_job(
InputDataConfig={
'S3Bucket': 'string',
'S3Key': 'string'
},
OutputDataConfig={
'S3Bucket': 'string',
'S3Key': 'string'
},
DataAccessRoleArn='string',
JobName='string',
ClientRequestToken='string',
KMSKey='string',
LanguageCode='en'
)
dict
[REQUIRED]
The input properties for an entities detection job. This includes the name of the S3 bucket and the path to the files to be analyzed.
S3Bucket (string) -- [REQUIRED]
The URI of the S3 bucket that contains the input data. The bucket must be in the same region as the API endpoint that you are calling.
Each file in the document collection must be less than 40 KB. You can store a maximum of 30 GB in the bucket.
S3Key (string) --
The path to the input data files in the S3 bucket.
dict
[REQUIRED]
The output properties for a detection job.
S3Bucket (string) -- [REQUIRED]
When you use the OutputDataConfig object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data. The URI must be in the same region as the API endpoint that you are calling. The location is used as the prefix for the actual location of the output.
S3Key (string) --
The path to the output data files in the S3 bucket. Comprehend Medical; creates an output directory using the job ID so that the output from one job does not overwrite the output of another.
string
[REQUIRED]
The Amazon Resource Name (ARN) of the AWS Identity and Access Management (IAM) role that grants Amazon Comprehend Medical read access to your input data.
string
The user generated name the asynchronous InferSNOMEDCT job.
string
A unique identifier for the request. If you don't set the client request token, Amazon Comprehend Medical generates one.
This field is autopopulated if not provided.
string
An AWS Key Management Service key used to encrypt your output files. If you do not specify a key, the files are written in plain text.
string
[REQUIRED]
The language of the input documents. All documents must be in the same language.
dict
Response Syntax
{
'JobId': 'string'
}
Response Structure
(dict) --
JobId (string) --
The identifier generated for the job. To get the status of a job, use this identifier with the StartSNOMEDCTInferenceJob operation.
InferSNOMEDCT detects possible medical concepts as entities and links them to codes from the Systematized Nomenclature of Medicine, Clinical Terms (SNOMED-CT) ontology
See also: AWS API Documentation
Request Syntax
client.infer_snomedct(
Text='string'
)
string
[REQUIRED]
The input text to be analyzed using InferSNOMEDCT. The text should be a string with 1 to 10000 characters.
dict
Response Syntax
{
'Entities': [
{
'Id': 123,
'Text': 'string',
'Category': 'MEDICAL_CONDITION'|'ANATOMY'|'TEST_TREATMENT_PROCEDURE',
'Type': 'DX_NAME'|'TEST_NAME'|'PROCEDURE_NAME'|'TREATMENT_NAME',
'Score': ...,
'BeginOffset': 123,
'EndOffset': 123,
'Attributes': [
{
'Category': 'MEDICAL_CONDITION'|'ANATOMY'|'TEST_TREATMENT_PROCEDURE',
'Type': 'ACUITY'|'QUALITY'|'DIRECTION'|'SYSTEM_ORGAN_SITE'|'TEST_VALUE'|'TEST_UNIT',
'Score': ...,
'RelationshipScore': ...,
'RelationshipType': 'ACUITY'|'QUALITY'|'TEST_VALUE'|'TEST_UNITS'|'DIRECTION'|'SYSTEM_ORGAN_SITE',
'Id': 123,
'BeginOffset': 123,
'EndOffset': 123,
'Text': 'string',
'Traits': [
{
'Name': 'NEGATION'|'DIAGNOSIS'|'SIGN'|'SYMPTOM',
'Score': ...
},
],
'SNOMEDCTConcepts': [
{
'Description': 'string',
'Code': 'string',
'Score': ...
},
]
},
],
'Traits': [
{
'Name': 'NEGATION'|'DIAGNOSIS'|'SIGN'|'SYMPTOM',
'Score': ...
},
],
'SNOMEDCTConcepts': [
{
'Description': 'string',
'Code': 'string',
'Score': ...
},
]
},
],
'PaginationToken': 'string',
'ModelVersion': 'string',
'SNOMEDCTDetails': {
'Edition': 'string',
'Language': 'string',
'VersionDate': 'string'
},
'Characters': {
'OriginalTextCharacters': 123
}
}
Response Structure
(dict) --
Entities (list) --
The collection of medical concept entities extracted from the input text and their associated information. For each entity, the response provides the entity text, the entity category, where the entity text begins and ends, and the level of confidence that Comprehend Medical has in the detection and analysis. Attributes and traits of the entity are also returned.
(dict) --
The collection of medical entities extracted from the input text and their associated information. For each entity, the response provides the entity text, the entity category, where the entity text begins and ends, and the level of confidence that Comprehend Medical has in the detection and analysis. Attributes and traits of the entity are also returned.
Id (integer) --
The numeric identifier for the entity. This is a monotonically increasing id unique within this response rather than a global unique identifier.
Text (string) --
The segment of input text extracted as this entity.
Category (string) --
The category of the detected entity. Possible categories are MEDICAL_CONDITION, ANATOMY, or TEST_TREATMENT_PROCEDURE.
Type (string) --
Describes the specific type of entity with category of entities. Possible types include DX_NAME, ACUITY, DIRECTION, SYSTEM_ORGAN_SITE, TEST_NAME, TEST_VALUE, TEST_UNIT, PROCEDURE_NAME, or TREATMENT_NAME.
Score (float) --
The level of confidence that Comprehend Medical has in the accuracy of the detected entity.
BeginOffset (integer) --
The 0-based character offset in the input text that shows where the entity begins. The offset returns the UTF-8 code point in the string.
EndOffset (integer) --
The 0-based character offset in the input text that shows where the entity ends. The offset returns the UTF-8 code point in the string.
Attributes (list) --
An extracted segment of the text that is an attribute of an entity, or otherwise related to an entity, such as the dosage of a medication taken.
(dict) --
The extracted attributes that relate to an entity. An extracted segment of the text that is an attribute of an entity, or otherwise related to an entity, such as the dosage of a medication taken.
Category (string) --
The category of the detected attribute. Possible categories include MEDICAL_CONDITION, ANATOMY, and TEST_TREATMENT_PROCEDURE.
Type (string) --
The type of attribute. Possible types include DX_NAME, ACUITY, DIRECTION, SYSTEM_ORGAN_SITE,TEST_NAME, TEST_VALUE, TEST_UNIT, PROCEDURE_NAME, and TREATMENT_NAME.
Score (float) --
The level of confidence that Comprehend Medical has that the segment of text is correctly recognized as an attribute.
RelationshipScore (float) --
The level of confidence that Comprehend Medical has that this attribute is correctly related to this entity.
RelationshipType (string) --
The type of relationship that exists between the entity and the related attribute.
Id (integer) --
The numeric identifier for this attribute. This is a monotonically increasing id unique within this response rather than a global unique identifier.
BeginOffset (integer) --
The 0-based character offset in the input text that shows where the attribute begins. The offset returns the UTF-8 code point in the string.
EndOffset (integer) --
The 0-based character offset in the input text that shows where the attribute ends. The offset returns the UTF-8 code point in the string.
Text (string) --
The segment of input text extracted as this attribute.
Traits (list) --
Contextual information for an attribute. Examples include signs, symptoms, diagnosis, and negation.
(dict) --
Contextual information for an entity.
Name (string) --
The name or contextual description of a detected trait.
Score (float) --
The level of confidence that Comprehend Medical has in the accuracy of a detected trait.
SNOMEDCTConcepts (list) --
The SNOMED-CT concepts specific to an attribute, along with a score indicating the likelihood of the match.
(dict) --
The SNOMED-CT concepts that the entity could refer to, along with a score indicating the likelihood of the match.
Description (string) --
The description of the SNOMED-CT concept.
Code (string) --
The numeric ID for the SNOMED-CT concept.
Score (float) --
The level of confidence Comprehend Medical has that the entity should be linked to the identified SNOMED-CT concept.
Traits (list) --
Contextual information for the entity.
(dict) --
Contextual information for an entity.
Name (string) --
The name or contextual description of a detected trait.
Score (float) --
The level of confidence that Comprehend Medical has in the accuracy of a detected trait.
SNOMEDCTConcepts (list) --
The SNOMED concepts that the entity could refer to, along with a score indicating the likelihood of the match.
(dict) --
The SNOMED-CT concepts that the entity could refer to, along with a score indicating the likelihood of the match.
Description (string) --
The description of the SNOMED-CT concept.
Code (string) --
The numeric ID for the SNOMED-CT concept.
Score (float) --
The level of confidence Comprehend Medical has that the entity should be linked to the identified SNOMED-CT concept.
PaginationToken (string) --
If the result of the request is truncated, the pagination token can be used to fetch the next page of entities.
ModelVersion (string) --
The version of the model used to analyze the documents, in the format n.n.n You can use this information to track the model used for a particular batch of documents.
SNOMEDCTDetails (dict) --
The details of the SNOMED-CT revision, including the edition, language, and version date.
Edition (string) --
The edition of SNOMED-CT used. The edition used for the InferSNOMEDCT editions is the US edition.
Language (string) --
The language used in the SNOMED-CT ontology. All Amazon Comprehend Medical operations are US English (en).
VersionDate (string) --
The version date of the SNOMED-CT ontology used.
Characters (dict) --
The number of characters in the input request documentation.
OriginalTextCharacters (integer) --
The number of characters present in the input text document as processed by Comprehend Medical.
Gets a list of InferSNOMEDCT jobs a user has submitted.
See also: AWS API Documentation
Request Syntax
client.list_snomedct_inference_jobs(
Filter={
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'PARTIAL_SUCCESS'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'SubmitTimeBefore': datetime(2015, 1, 1),
'SubmitTimeAfter': datetime(2015, 1, 1)
},
NextToken='string',
MaxResults=123
)
dict
Provides information for filtering a list of detection jobs.
JobName (string) --
Filters on the name of the job.
JobStatus (string) --
Filters the list of jobs based on job status. Returns only jobs with the specified status.
SubmitTimeBefore (datetime) --
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted before the specified time. Jobs are returned in ascending order, oldest to newest.
SubmitTimeAfter (datetime) --
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted after the specified time. Jobs are returned in descending order, newest to oldest.
string
Identifies the next page of InferSNOMEDCT results to return.
integer
The maximum number of results to return in each page. The default is 100.
dict
Response Syntax
{
'ComprehendMedicalAsyncJobPropertiesList': [
{
'JobId': 'string',
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'PARTIAL_SUCCESS'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'Message': 'string',
'SubmitTime': datetime(2015, 1, 1),
'EndTime': datetime(2015, 1, 1),
'ExpirationTime': datetime(2015, 1, 1),
'InputDataConfig': {
'S3Bucket': 'string',
'S3Key': 'string'
},
'OutputDataConfig': {
'S3Bucket': 'string',
'S3Key': 'string'
},
'LanguageCode': 'en',
'DataAccessRoleArn': 'string',
'ManifestFilePath': 'string',
'KMSKey': 'string',
'ModelVersion': 'string'
},
],
'NextToken': 'string'
}
Response Structure
(dict) --
ComprehendMedicalAsyncJobPropertiesList (list) --
A list containing the properties of each job that is returned.
(dict) --
Provides information about a detection job.
JobId (string) --
The identifier assigned to the detection job.
JobName (string) --
The name that you assigned to the detection job.
JobStatus (string) --
The current status of the detection job. If the status is FAILED, the Message field shows the reason for the failure.
Message (string) --
A description of the status of a job.
SubmitTime (datetime) --
The time that the detection job was submitted for processing.
EndTime (datetime) --
The time that the detection job completed.
ExpirationTime (datetime) --
The date and time that job metadata is deleted from the server. Output files in your S3 bucket will not be deleted. After the metadata is deleted, the job will no longer appear in the results of the ListEntitiesDetectionV2Job or the ListPHIDetectionJobs operation.
InputDataConfig (dict) --
The input data configuration that you supplied when you created the detection job.
S3Bucket (string) --
The URI of the S3 bucket that contains the input data. The bucket must be in the same region as the API endpoint that you are calling.
Each file in the document collection must be less than 40 KB. You can store a maximum of 30 GB in the bucket.
S3Key (string) --
The path to the input data files in the S3 bucket.
OutputDataConfig (dict) --
The output data configuration that you supplied when you created the detection job.
S3Bucket (string) --
When you use the OutputDataConfig object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data. The URI must be in the same region as the API endpoint that you are calling. The location is used as the prefix for the actual location of the output.
S3Key (string) --
The path to the output data files in the S3 bucket. Comprehend Medical; creates an output directory using the job ID so that the output from one job does not overwrite the output of another.
LanguageCode (string) --
The language code of the input documents.
DataAccessRoleArn (string) --
The Amazon Resource Name (ARN) that gives Comprehend Medical; read access to your input data.
ManifestFilePath (string) --
The path to the file that describes the results of a batch job.
KMSKey (string) --
The AWS Key Management Service key, if any, used to encrypt the output files.
ModelVersion (string) --
The version of the model used to analyze the documents. The version number looks like X.X.X. You can use this information to track the model used for a particular batch of documents.
NextToken (string) --
Identifies the next page of results to return.
{'Entities': {'Attributes': {'RelationshipType': {'TEST_UNIT'},
'Type': {'DX_NAME',
'ID',
'PHONE_OR_FAX',
'TEST_UNIT'}},
'Type': {'DX_NAME', 'TEST_UNIT', 'PHONE_OR_FAX', 'ID'}},
'UnmappedAttributes': {'Attribute': {'RelationshipType': {'TEST_UNIT'},
'Type': {'DX_NAME',
'ID',
'PHONE_OR_FAX',
'TEST_UNIT'}}}}
The DetectEntities operation is deprecated. You should use the DetectEntitiesV2 operation instead.
Inspects the clinical text for a variety of medical entities and returns specific information about them such as entity category, location, and confidence score on that information .
See also: AWS API Documentation
Request Syntax
client.detect_entities(
Text='string'
)
string
[REQUIRED]
A UTF-8 text string containing the clinical content being examined for entities. Each string must contain fewer than 20,000 bytes of characters.
dict
Response Syntax
{
'Entities': [
{
'Id': 123,
'BeginOffset': 123,
'EndOffset': 123,
'Score': ...,
'Text': 'string',
'Category': 'MEDICATION'|'MEDICAL_CONDITION'|'PROTECTED_HEALTH_INFORMATION'|'TEST_TREATMENT_PROCEDURE'|'ANATOMY'|'TIME_EXPRESSION',
'Type': 'NAME'|'DX_NAME'|'DOSAGE'|'ROUTE_OR_MODE'|'FORM'|'FREQUENCY'|'DURATION'|'GENERIC_NAME'|'BRAND_NAME'|'STRENGTH'|'RATE'|'ACUITY'|'TEST_NAME'|'TEST_VALUE'|'TEST_UNITS'|'TEST_UNIT'|'PROCEDURE_NAME'|'TREATMENT_NAME'|'DATE'|'AGE'|'CONTACT_POINT'|'PHONE_OR_FAX'|'EMAIL'|'IDENTIFIER'|'ID'|'URL'|'ADDRESS'|'PROFESSION'|'SYSTEM_ORGAN_SITE'|'DIRECTION'|'QUALITY'|'QUANTITY'|'TIME_EXPRESSION'|'TIME_TO_MEDICATION_NAME'|'TIME_TO_DX_NAME'|'TIME_TO_TEST_NAME'|'TIME_TO_PROCEDURE_NAME'|'TIME_TO_TREATMENT_NAME',
'Traits': [
{
'Name': 'SIGN'|'SYMPTOM'|'DIAGNOSIS'|'NEGATION',
'Score': ...
},
],
'Attributes': [
{
'Type': 'NAME'|'DX_NAME'|'DOSAGE'|'ROUTE_OR_MODE'|'FORM'|'FREQUENCY'|'DURATION'|'GENERIC_NAME'|'BRAND_NAME'|'STRENGTH'|'RATE'|'ACUITY'|'TEST_NAME'|'TEST_VALUE'|'TEST_UNITS'|'TEST_UNIT'|'PROCEDURE_NAME'|'TREATMENT_NAME'|'DATE'|'AGE'|'CONTACT_POINT'|'PHONE_OR_FAX'|'EMAIL'|'IDENTIFIER'|'ID'|'URL'|'ADDRESS'|'PROFESSION'|'SYSTEM_ORGAN_SITE'|'DIRECTION'|'QUALITY'|'QUANTITY'|'TIME_EXPRESSION'|'TIME_TO_MEDICATION_NAME'|'TIME_TO_DX_NAME'|'TIME_TO_TEST_NAME'|'TIME_TO_PROCEDURE_NAME'|'TIME_TO_TREATMENT_NAME',
'Score': ...,
'RelationshipScore': ...,
'RelationshipType': 'EVERY'|'WITH_DOSAGE'|'ADMINISTERED_VIA'|'FOR'|'NEGATIVE'|'OVERLAP'|'DOSAGE'|'ROUTE_OR_MODE'|'FORM'|'FREQUENCY'|'DURATION'|'STRENGTH'|'RATE'|'ACUITY'|'TEST_VALUE'|'TEST_UNITS'|'TEST_UNIT'|'DIRECTION'|'SYSTEM_ORGAN_SITE',
'Id': 123,
'BeginOffset': 123,
'EndOffset': 123,
'Text': 'string',
'Category': 'MEDICATION'|'MEDICAL_CONDITION'|'PROTECTED_HEALTH_INFORMATION'|'TEST_TREATMENT_PROCEDURE'|'ANATOMY'|'TIME_EXPRESSION',
'Traits': [
{
'Name': 'SIGN'|'SYMPTOM'|'DIAGNOSIS'|'NEGATION',
'Score': ...
},
]
},
]
},
],
'UnmappedAttributes': [
{
'Type': 'MEDICATION'|'MEDICAL_CONDITION'|'PROTECTED_HEALTH_INFORMATION'|'TEST_TREATMENT_PROCEDURE'|'ANATOMY'|'TIME_EXPRESSION',
'Attribute': {
'Type': 'NAME'|'DX_NAME'|'DOSAGE'|'ROUTE_OR_MODE'|'FORM'|'FREQUENCY'|'DURATION'|'GENERIC_NAME'|'BRAND_NAME'|'STRENGTH'|'RATE'|'ACUITY'|'TEST_NAME'|'TEST_VALUE'|'TEST_UNITS'|'TEST_UNIT'|'PROCEDURE_NAME'|'TREATMENT_NAME'|'DATE'|'AGE'|'CONTACT_POINT'|'PHONE_OR_FAX'|'EMAIL'|'IDENTIFIER'|'ID'|'URL'|'ADDRESS'|'PROFESSION'|'SYSTEM_ORGAN_SITE'|'DIRECTION'|'QUALITY'|'QUANTITY'|'TIME_EXPRESSION'|'TIME_TO_MEDICATION_NAME'|'TIME_TO_DX_NAME'|'TIME_TO_TEST_NAME'|'TIME_TO_PROCEDURE_NAME'|'TIME_TO_TREATMENT_NAME',
'Score': ...,
'RelationshipScore': ...,
'RelationshipType': 'EVERY'|'WITH_DOSAGE'|'ADMINISTERED_VIA'|'FOR'|'NEGATIVE'|'OVERLAP'|'DOSAGE'|'ROUTE_OR_MODE'|'FORM'|'FREQUENCY'|'DURATION'|'STRENGTH'|'RATE'|'ACUITY'|'TEST_VALUE'|'TEST_UNITS'|'TEST_UNIT'|'DIRECTION'|'SYSTEM_ORGAN_SITE',
'Id': 123,
'BeginOffset': 123,
'EndOffset': 123,
'Text': 'string',
'Category': 'MEDICATION'|'MEDICAL_CONDITION'|'PROTECTED_HEALTH_INFORMATION'|'TEST_TREATMENT_PROCEDURE'|'ANATOMY'|'TIME_EXPRESSION',
'Traits': [
{
'Name': 'SIGN'|'SYMPTOM'|'DIAGNOSIS'|'NEGATION',
'Score': ...
},
]
}
},
],
'PaginationToken': 'string',
'ModelVersion': 'string'
}
Response Structure
(dict) --
Entities (list) --
The collection of medical entities extracted from the input text and their associated information. For each entity, the response provides the entity text, the entity category, where the entity text begins and ends, and the level of confidence that Comprehend Medical; has in the detection and analysis. Attributes and traits of the entity are also returned.
(dict) --
Provides information about an extracted medical entity.
Id (integer) --
The numeric identifier for the entity. This is a monotonically increasing id unique within this response rather than a global unique identifier.
BeginOffset (integer) --
The 0-based character offset in the input text that shows where the entity begins. The offset returns the UTF-8 code point in the string.
EndOffset (integer) --
The 0-based character offset in the input text that shows where the entity ends. The offset returns the UTF-8 code point in the string.
Score (float) --
The level of confidence that Comprehend Medical; has in the accuracy of the detection.
Text (string) --
The segment of input text extracted as this entity.
Category (string) --
The category of the entity.
Type (string) --
Describes the specific type of entity with category of entities.
Traits (list) --
Contextual information for the entity.
(dict) --
Provides contextual information about the extracted entity.
Name (string) --
Provides a name or contextual description about the trait.
Score (float) --
The level of confidence that Comprehend Medical; has in the accuracy of this trait.
Attributes (list) --
The extracted attributes that relate to this entity.
(dict) --
An extracted segment of the text that is an attribute of an entity, or otherwise related to an entity, such as the dosage of a medication taken. It contains information about the attribute such as id, begin and end offset within the input text, and the segment of the input text.
Type (string) --
The type of attribute.
Score (float) --
The level of confidence that Comprehend Medical; has that the segment of text is correctly recognized as an attribute.
RelationshipScore (float) --
The level of confidence that Comprehend Medical; has that this attribute is correctly related to this entity.
RelationshipType (string) --
The type of relationship between the entity and attribute. Type for the relationship is OVERLAP, indicating that the entity occurred at the same time as the Date_Expression.
Id (integer) --
The numeric identifier for this attribute. This is a monotonically increasing id unique within this response rather than a global unique identifier.
BeginOffset (integer) --
The 0-based character offset in the input text that shows where the attribute begins. The offset returns the UTF-8 code point in the string.
EndOffset (integer) --
The 0-based character offset in the input text that shows where the attribute ends. The offset returns the UTF-8 code point in the string.
Text (string) --
The segment of input text extracted as this attribute.
Category (string) --
The category of attribute.
Traits (list) --
Contextual information for this attribute.
(dict) --
Provides contextual information about the extracted entity.
Name (string) --
Provides a name or contextual description about the trait.
Score (float) --
The level of confidence that Comprehend Medical; has in the accuracy of this trait.
UnmappedAttributes (list) --
Attributes extracted from the input text that we were unable to relate to an entity.
(dict) --
An attribute that was extracted, but Comprehend Medical; was unable to relate to an entity.
Type (string) --
The type of the unmapped attribute, could be one of the following values: "MEDICATION", "MEDICAL_CONDITION", "ANATOMY", "TEST_AND_TREATMENT_PROCEDURE" or "PROTECTED_HEALTH_INFORMATION".
Attribute (dict) --
The specific attribute that has been extracted but not mapped to an entity.
Type (string) --
The type of attribute.
Score (float) --
The level of confidence that Comprehend Medical; has that the segment of text is correctly recognized as an attribute.
RelationshipScore (float) --
The level of confidence that Comprehend Medical; has that this attribute is correctly related to this entity.
RelationshipType (string) --
The type of relationship between the entity and attribute. Type for the relationship is OVERLAP, indicating that the entity occurred at the same time as the Date_Expression.
Id (integer) --
The numeric identifier for this attribute. This is a monotonically increasing id unique within this response rather than a global unique identifier.
BeginOffset (integer) --
The 0-based character offset in the input text that shows where the attribute begins. The offset returns the UTF-8 code point in the string.
EndOffset (integer) --
The 0-based character offset in the input text that shows where the attribute ends. The offset returns the UTF-8 code point in the string.
Text (string) --
The segment of input text extracted as this attribute.
Category (string) --
The category of attribute.
Traits (list) --
Contextual information for this attribute.
(dict) --
Provides contextual information about the extracted entity.
Name (string) --
Provides a name or contextual description about the trait.
Score (float) --
The level of confidence that Comprehend Medical; has in the accuracy of this trait.
PaginationToken (string) --
If the result of the previous request to DetectEntities was truncated, include the PaginationToken to fetch the next page of entities.
ModelVersion (string) --
The version of the model used to analyze the documents. The version number looks like X.X.X. You can use this information to track the model used for a particular batch of documents.
{'Entities': {'Attributes': {'RelationshipType': {'TEST_UNIT'},
'Type': {'DX_NAME',
'ID',
'PHONE_OR_FAX',
'TEST_UNIT'}},
'Type': {'DX_NAME', 'TEST_UNIT', 'PHONE_OR_FAX', 'ID'}},
'UnmappedAttributes': {'Attribute': {'RelationshipType': {'TEST_UNIT'},
'Type': {'DX_NAME',
'ID',
'PHONE_OR_FAX',
'TEST_UNIT'}}}}
Inspects the clinical text for a variety of medical entities and returns specific information about them such as entity category, location, and confidence score on that information. Amazon Comprehend Medical only detects medical entities in English language texts.
The DetectEntitiesV2 operation replaces the DetectEntities operation. This new action uses a different model for determining the entities in your medical text and changes the way that some entities are returned in the output. You should use the DetectEntitiesV2 operation in all new applications.
The DetectEntitiesV2 operation returns the Acuity and Direction entities as attributes instead of types.
See also: AWS API Documentation
Request Syntax
client.detect_entities_v2(
Text='string'
)
string
[REQUIRED]
A UTF-8 string containing the clinical content being examined for entities. Each string must contain fewer than 20,000 bytes of characters.
dict
Response Syntax
{
'Entities': [
{
'Id': 123,
'BeginOffset': 123,
'EndOffset': 123,
'Score': ...,
'Text': 'string',
'Category': 'MEDICATION'|'MEDICAL_CONDITION'|'PROTECTED_HEALTH_INFORMATION'|'TEST_TREATMENT_PROCEDURE'|'ANATOMY'|'TIME_EXPRESSION',
'Type': 'NAME'|'DX_NAME'|'DOSAGE'|'ROUTE_OR_MODE'|'FORM'|'FREQUENCY'|'DURATION'|'GENERIC_NAME'|'BRAND_NAME'|'STRENGTH'|'RATE'|'ACUITY'|'TEST_NAME'|'TEST_VALUE'|'TEST_UNITS'|'TEST_UNIT'|'PROCEDURE_NAME'|'TREATMENT_NAME'|'DATE'|'AGE'|'CONTACT_POINT'|'PHONE_OR_FAX'|'EMAIL'|'IDENTIFIER'|'ID'|'URL'|'ADDRESS'|'PROFESSION'|'SYSTEM_ORGAN_SITE'|'DIRECTION'|'QUALITY'|'QUANTITY'|'TIME_EXPRESSION'|'TIME_TO_MEDICATION_NAME'|'TIME_TO_DX_NAME'|'TIME_TO_TEST_NAME'|'TIME_TO_PROCEDURE_NAME'|'TIME_TO_TREATMENT_NAME',
'Traits': [
{
'Name': 'SIGN'|'SYMPTOM'|'DIAGNOSIS'|'NEGATION',
'Score': ...
},
],
'Attributes': [
{
'Type': 'NAME'|'DX_NAME'|'DOSAGE'|'ROUTE_OR_MODE'|'FORM'|'FREQUENCY'|'DURATION'|'GENERIC_NAME'|'BRAND_NAME'|'STRENGTH'|'RATE'|'ACUITY'|'TEST_NAME'|'TEST_VALUE'|'TEST_UNITS'|'TEST_UNIT'|'PROCEDURE_NAME'|'TREATMENT_NAME'|'DATE'|'AGE'|'CONTACT_POINT'|'PHONE_OR_FAX'|'EMAIL'|'IDENTIFIER'|'ID'|'URL'|'ADDRESS'|'PROFESSION'|'SYSTEM_ORGAN_SITE'|'DIRECTION'|'QUALITY'|'QUANTITY'|'TIME_EXPRESSION'|'TIME_TO_MEDICATION_NAME'|'TIME_TO_DX_NAME'|'TIME_TO_TEST_NAME'|'TIME_TO_PROCEDURE_NAME'|'TIME_TO_TREATMENT_NAME',
'Score': ...,
'RelationshipScore': ...,
'RelationshipType': 'EVERY'|'WITH_DOSAGE'|'ADMINISTERED_VIA'|'FOR'|'NEGATIVE'|'OVERLAP'|'DOSAGE'|'ROUTE_OR_MODE'|'FORM'|'FREQUENCY'|'DURATION'|'STRENGTH'|'RATE'|'ACUITY'|'TEST_VALUE'|'TEST_UNITS'|'TEST_UNIT'|'DIRECTION'|'SYSTEM_ORGAN_SITE',
'Id': 123,
'BeginOffset': 123,
'EndOffset': 123,
'Text': 'string',
'Category': 'MEDICATION'|'MEDICAL_CONDITION'|'PROTECTED_HEALTH_INFORMATION'|'TEST_TREATMENT_PROCEDURE'|'ANATOMY'|'TIME_EXPRESSION',
'Traits': [
{
'Name': 'SIGN'|'SYMPTOM'|'DIAGNOSIS'|'NEGATION',
'Score': ...
},
]
},
]
},
],
'UnmappedAttributes': [
{
'Type': 'MEDICATION'|'MEDICAL_CONDITION'|'PROTECTED_HEALTH_INFORMATION'|'TEST_TREATMENT_PROCEDURE'|'ANATOMY'|'TIME_EXPRESSION',
'Attribute': {
'Type': 'NAME'|'DX_NAME'|'DOSAGE'|'ROUTE_OR_MODE'|'FORM'|'FREQUENCY'|'DURATION'|'GENERIC_NAME'|'BRAND_NAME'|'STRENGTH'|'RATE'|'ACUITY'|'TEST_NAME'|'TEST_VALUE'|'TEST_UNITS'|'TEST_UNIT'|'PROCEDURE_NAME'|'TREATMENT_NAME'|'DATE'|'AGE'|'CONTACT_POINT'|'PHONE_OR_FAX'|'EMAIL'|'IDENTIFIER'|'ID'|'URL'|'ADDRESS'|'PROFESSION'|'SYSTEM_ORGAN_SITE'|'DIRECTION'|'QUALITY'|'QUANTITY'|'TIME_EXPRESSION'|'TIME_TO_MEDICATION_NAME'|'TIME_TO_DX_NAME'|'TIME_TO_TEST_NAME'|'TIME_TO_PROCEDURE_NAME'|'TIME_TO_TREATMENT_NAME',
'Score': ...,
'RelationshipScore': ...,
'RelationshipType': 'EVERY'|'WITH_DOSAGE'|'ADMINISTERED_VIA'|'FOR'|'NEGATIVE'|'OVERLAP'|'DOSAGE'|'ROUTE_OR_MODE'|'FORM'|'FREQUENCY'|'DURATION'|'STRENGTH'|'RATE'|'ACUITY'|'TEST_VALUE'|'TEST_UNITS'|'TEST_UNIT'|'DIRECTION'|'SYSTEM_ORGAN_SITE',
'Id': 123,
'BeginOffset': 123,
'EndOffset': 123,
'Text': 'string',
'Category': 'MEDICATION'|'MEDICAL_CONDITION'|'PROTECTED_HEALTH_INFORMATION'|'TEST_TREATMENT_PROCEDURE'|'ANATOMY'|'TIME_EXPRESSION',
'Traits': [
{
'Name': 'SIGN'|'SYMPTOM'|'DIAGNOSIS'|'NEGATION',
'Score': ...
},
]
}
},
],
'PaginationToken': 'string',
'ModelVersion': 'string'
}
Response Structure
(dict) --
Entities (list) --
The collection of medical entities extracted from the input text and their associated information. For each entity, the response provides the entity text, the entity category, where the entity text begins and ends, and the level of confidence in the detection and analysis. Attributes and traits of the entity are also returned.
(dict) --
Provides information about an extracted medical entity.
Id (integer) --
The numeric identifier for the entity. This is a monotonically increasing id unique within this response rather than a global unique identifier.
BeginOffset (integer) --
The 0-based character offset in the input text that shows where the entity begins. The offset returns the UTF-8 code point in the string.
EndOffset (integer) --
The 0-based character offset in the input text that shows where the entity ends. The offset returns the UTF-8 code point in the string.
Score (float) --
The level of confidence that Comprehend Medical; has in the accuracy of the detection.
Text (string) --
The segment of input text extracted as this entity.
Category (string) --
The category of the entity.
Type (string) --
Describes the specific type of entity with category of entities.
Traits (list) --
Contextual information for the entity.
(dict) --
Provides contextual information about the extracted entity.
Name (string) --
Provides a name or contextual description about the trait.
Score (float) --
The level of confidence that Comprehend Medical; has in the accuracy of this trait.
Attributes (list) --
The extracted attributes that relate to this entity.
(dict) --
An extracted segment of the text that is an attribute of an entity, or otherwise related to an entity, such as the dosage of a medication taken. It contains information about the attribute such as id, begin and end offset within the input text, and the segment of the input text.
Type (string) --
The type of attribute.
Score (float) --
The level of confidence that Comprehend Medical; has that the segment of text is correctly recognized as an attribute.
RelationshipScore (float) --
The level of confidence that Comprehend Medical; has that this attribute is correctly related to this entity.
RelationshipType (string) --
The type of relationship between the entity and attribute. Type for the relationship is OVERLAP, indicating that the entity occurred at the same time as the Date_Expression.
Id (integer) --
The numeric identifier for this attribute. This is a monotonically increasing id unique within this response rather than a global unique identifier.
BeginOffset (integer) --
The 0-based character offset in the input text that shows where the attribute begins. The offset returns the UTF-8 code point in the string.
EndOffset (integer) --
The 0-based character offset in the input text that shows where the attribute ends. The offset returns the UTF-8 code point in the string.
Text (string) --
The segment of input text extracted as this attribute.
Category (string) --
The category of attribute.
Traits (list) --
Contextual information for this attribute.
(dict) --
Provides contextual information about the extracted entity.
Name (string) --
Provides a name or contextual description about the trait.
Score (float) --
The level of confidence that Comprehend Medical; has in the accuracy of this trait.
UnmappedAttributes (list) --
Attributes extracted from the input text that couldn't be related to an entity.
(dict) --
An attribute that was extracted, but Comprehend Medical; was unable to relate to an entity.
Type (string) --
The type of the unmapped attribute, could be one of the following values: "MEDICATION", "MEDICAL_CONDITION", "ANATOMY", "TEST_AND_TREATMENT_PROCEDURE" or "PROTECTED_HEALTH_INFORMATION".
Attribute (dict) --
The specific attribute that has been extracted but not mapped to an entity.
Type (string) --
The type of attribute.
Score (float) --
The level of confidence that Comprehend Medical; has that the segment of text is correctly recognized as an attribute.
RelationshipScore (float) --
The level of confidence that Comprehend Medical; has that this attribute is correctly related to this entity.
RelationshipType (string) --
The type of relationship between the entity and attribute. Type for the relationship is OVERLAP, indicating that the entity occurred at the same time as the Date_Expression.
Id (integer) --
The numeric identifier for this attribute. This is a monotonically increasing id unique within this response rather than a global unique identifier.
BeginOffset (integer) --
The 0-based character offset in the input text that shows where the attribute begins. The offset returns the UTF-8 code point in the string.
EndOffset (integer) --
The 0-based character offset in the input text that shows where the attribute ends. The offset returns the UTF-8 code point in the string.
Text (string) --
The segment of input text extracted as this attribute.
Category (string) --
The category of attribute.
Traits (list) --
Contextual information for this attribute.
(dict) --
Provides contextual information about the extracted entity.
Name (string) --
Provides a name or contextual description about the trait.
Score (float) --
The level of confidence that Comprehend Medical; has in the accuracy of this trait.
PaginationToken (string) --
If the result to the DetectEntitiesV2 operation was truncated, include the PaginationToken to fetch the next page of entities.
ModelVersion (string) --
The version of the model used to analyze the documents. The version number looks like X.X.X. You can use this information to track the model used for a particular batch of documents.
{'Entities': {'Attributes': {'RelationshipType': {'TEST_UNIT'},
'Type': {'DX_NAME',
'ID',
'PHONE_OR_FAX',
'TEST_UNIT'}},
'Type': {'DX_NAME', 'TEST_UNIT', 'PHONE_OR_FAX', 'ID'}}}
Inspects the clinical text for protected health information (PHI) entities and returns the entity category, location, and confidence score for each entity. Amazon Comprehend Medical only detects entities in English language texts.
See also: AWS API Documentation
Request Syntax
client.detect_phi(
Text='string'
)
string
[REQUIRED]
A UTF-8 text string containing the clinical content being examined for PHI entities. Each string must contain fewer than 20,000 bytes of characters.
dict
Response Syntax
{
'Entities': [
{
'Id': 123,
'BeginOffset': 123,
'EndOffset': 123,
'Score': ...,
'Text': 'string',
'Category': 'MEDICATION'|'MEDICAL_CONDITION'|'PROTECTED_HEALTH_INFORMATION'|'TEST_TREATMENT_PROCEDURE'|'ANATOMY'|'TIME_EXPRESSION',
'Type': 'NAME'|'DX_NAME'|'DOSAGE'|'ROUTE_OR_MODE'|'FORM'|'FREQUENCY'|'DURATION'|'GENERIC_NAME'|'BRAND_NAME'|'STRENGTH'|'RATE'|'ACUITY'|'TEST_NAME'|'TEST_VALUE'|'TEST_UNITS'|'TEST_UNIT'|'PROCEDURE_NAME'|'TREATMENT_NAME'|'DATE'|'AGE'|'CONTACT_POINT'|'PHONE_OR_FAX'|'EMAIL'|'IDENTIFIER'|'ID'|'URL'|'ADDRESS'|'PROFESSION'|'SYSTEM_ORGAN_SITE'|'DIRECTION'|'QUALITY'|'QUANTITY'|'TIME_EXPRESSION'|'TIME_TO_MEDICATION_NAME'|'TIME_TO_DX_NAME'|'TIME_TO_TEST_NAME'|'TIME_TO_PROCEDURE_NAME'|'TIME_TO_TREATMENT_NAME',
'Traits': [
{
'Name': 'SIGN'|'SYMPTOM'|'DIAGNOSIS'|'NEGATION',
'Score': ...
},
],
'Attributes': [
{
'Type': 'NAME'|'DX_NAME'|'DOSAGE'|'ROUTE_OR_MODE'|'FORM'|'FREQUENCY'|'DURATION'|'GENERIC_NAME'|'BRAND_NAME'|'STRENGTH'|'RATE'|'ACUITY'|'TEST_NAME'|'TEST_VALUE'|'TEST_UNITS'|'TEST_UNIT'|'PROCEDURE_NAME'|'TREATMENT_NAME'|'DATE'|'AGE'|'CONTACT_POINT'|'PHONE_OR_FAX'|'EMAIL'|'IDENTIFIER'|'ID'|'URL'|'ADDRESS'|'PROFESSION'|'SYSTEM_ORGAN_SITE'|'DIRECTION'|'QUALITY'|'QUANTITY'|'TIME_EXPRESSION'|'TIME_TO_MEDICATION_NAME'|'TIME_TO_DX_NAME'|'TIME_TO_TEST_NAME'|'TIME_TO_PROCEDURE_NAME'|'TIME_TO_TREATMENT_NAME',
'Score': ...,
'RelationshipScore': ...,
'RelationshipType': 'EVERY'|'WITH_DOSAGE'|'ADMINISTERED_VIA'|'FOR'|'NEGATIVE'|'OVERLAP'|'DOSAGE'|'ROUTE_OR_MODE'|'FORM'|'FREQUENCY'|'DURATION'|'STRENGTH'|'RATE'|'ACUITY'|'TEST_VALUE'|'TEST_UNITS'|'TEST_UNIT'|'DIRECTION'|'SYSTEM_ORGAN_SITE',
'Id': 123,
'BeginOffset': 123,
'EndOffset': 123,
'Text': 'string',
'Category': 'MEDICATION'|'MEDICAL_CONDITION'|'PROTECTED_HEALTH_INFORMATION'|'TEST_TREATMENT_PROCEDURE'|'ANATOMY'|'TIME_EXPRESSION',
'Traits': [
{
'Name': 'SIGN'|'SYMPTOM'|'DIAGNOSIS'|'NEGATION',
'Score': ...
},
]
},
]
},
],
'PaginationToken': 'string',
'ModelVersion': 'string'
}
Response Structure
(dict) --
Entities (list) --
The collection of PHI entities extracted from the input text and their associated information. For each entity, the response provides the entity text, the entity category, where the entity text begins and ends, and the level of confidence that Comprehend Medical; has in its detection.
(dict) --
Provides information about an extracted medical entity.
Id (integer) --
The numeric identifier for the entity. This is a monotonically increasing id unique within this response rather than a global unique identifier.
BeginOffset (integer) --
The 0-based character offset in the input text that shows where the entity begins. The offset returns the UTF-8 code point in the string.
EndOffset (integer) --
The 0-based character offset in the input text that shows where the entity ends. The offset returns the UTF-8 code point in the string.
Score (float) --
The level of confidence that Comprehend Medical; has in the accuracy of the detection.
Text (string) --
The segment of input text extracted as this entity.
Category (string) --
The category of the entity.
Type (string) --
Describes the specific type of entity with category of entities.
Traits (list) --
Contextual information for the entity.
(dict) --
Provides contextual information about the extracted entity.
Name (string) --
Provides a name or contextual description about the trait.
Score (float) --
The level of confidence that Comprehend Medical; has in the accuracy of this trait.
Attributes (list) --
The extracted attributes that relate to this entity.
(dict) --
An extracted segment of the text that is an attribute of an entity, or otherwise related to an entity, such as the dosage of a medication taken. It contains information about the attribute such as id, begin and end offset within the input text, and the segment of the input text.
Type (string) --
The type of attribute.
Score (float) --
The level of confidence that Comprehend Medical; has that the segment of text is correctly recognized as an attribute.
RelationshipScore (float) --
The level of confidence that Comprehend Medical; has that this attribute is correctly related to this entity.
RelationshipType (string) --
The type of relationship between the entity and attribute. Type for the relationship is OVERLAP, indicating that the entity occurred at the same time as the Date_Expression.
Id (integer) --
The numeric identifier for this attribute. This is a monotonically increasing id unique within this response rather than a global unique identifier.
BeginOffset (integer) --
The 0-based character offset in the input text that shows where the attribute begins. The offset returns the UTF-8 code point in the string.
EndOffset (integer) --
The 0-based character offset in the input text that shows where the attribute ends. The offset returns the UTF-8 code point in the string.
Text (string) --
The segment of input text extracted as this attribute.
Category (string) --
The category of attribute.
Traits (list) --
Contextual information for this attribute.
(dict) --
Provides contextual information about the extracted entity.
Name (string) --
Provides a name or contextual description about the trait.
Score (float) --
The level of confidence that Comprehend Medical; has in the accuracy of this trait.
PaginationToken (string) --
If the result of the previous request to DetectPHI was truncated, include the PaginationToken to fetch the next page of PHI entities.
ModelVersion (string) --
The version of the model used to analyze the documents. The version number looks like X.X.X. You can use this information to track the model used for a particular batch of documents.