detect-entities-v2¶

Description¶

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.

Synopsis¶

  detect-entities-v2
--text <value>
[--cli-input-json | --cli-input-yaml]
[--generate-cli-skeleton <value>]

Options¶

--text (string)

A UTF-8 string containing the clinical content being examined for entities. Each string must contain fewer than 20,000 bytes of characters.

--cli-input-json | --cli-input-yaml (string) Reads arguments from the JSON string provided. The JSON string follows the format provided by --generate-cli-skeleton. If other arguments are provided on the command line, those values will override the JSON-provided values. It is not possible to pass arbitrary binary values using a JSON-provided value as the string will be taken literally. This may not be specified along with --cli-input-yaml.

--generate-cli-skeleton (string) Prints a JSON skeleton to standard output without sending an API request. If provided with no value or the value input, prints a sample input JSON that can be used as an argument for --cli-input-json. Similarly, if provided yaml-input it will print a sample input YAML that can be used with --cli-input-yaml. If provided with the value output, it validates the command inputs and returns a sample output JSON for that command.

See ‘aws help’ for descriptions of global parameters.

Examples¶

Example 1: To detect entities directly from text

The following detect-entities-v2 example shows the detected entities and labels them according to type, directly from input text.

aws comprehendmedical detect-entities-v2 \
    --text "Sleeping trouble on present dosage of Clonidine. Severe rash on face and leg, slightly itchy."

Output:

{
    "Id": 0,
    "BeginOffset": 38,
    "EndOffset": 47,
    "Score": 0.9942955374717712,
    "Text": "Clonidine",
    "Category": "MEDICATION",
    "Type": "GENERIC_NAME",
    "Traits": []
},

For more information, see Detect Entities Version 2 in the Amazon Comprehend Medical Developer Guide.

Example 2: To detect entities from a file path

The following detect-entities-v2 example shows the detected entities and labels them according to type from a file path.

aws comprehendmedical detect-entities-v2 \
    --text file://medical_entities.txt

Contents of medical_entities.txt:

{
    "Sleeping trouble on present dosage of Clonidine. Severe rash on face and leg, slightly itchy."
}

Output:

{
    "Id": 0,
    "BeginOffset": 38,
    "EndOffset": 47,
    "Score": 0.9942955374717712,
    "Text": "Clonidine",
    "Category": "MEDICATION",
    "Type": "GENERIC_NAME",
    "Traits": []
},

For more information, see Detect Entities Version 2 in the Amazon Comprehend Medical Developer Guide.

Output¶

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.

(structure)

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.

(structure)

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.

(structure)

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.

(structure)

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.

(structure)

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 -> (structure)

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.

(structure)

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.

Table of Contents

Feedback

User Guide