DetectEntitiesV2 - Amazon Comprehend Medical

DetectEntitiesV2

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.

Request Syntax

{ "Text": "string" }

Request Parameters

For information about the parameters that are common to all actions, see Common Parameters.

The request accepts the following data in JSON format.

Text

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

Type: String

Length Constraints: Minimum length of 1. Maximum length of 20000.

Required: Yes

Response Syntax

{ "Entities": [ { "Attributes": [ { "BeginOffset": number, "Category": "string", "EndOffset": number, "Id": number, "RelationshipScore": number, "RelationshipType": "string", "Score": number, "Text": "string", "Traits": [ { "Name": "string", "Score": number } ], "Type": "string" } ], "BeginOffset": number, "Category": "string", "EndOffset": number, "Id": number, "Score": number, "Text": "string", "Traits": [ { "Name": "string", "Score": number } ], "Type": "string" } ], "ModelVersion": "string", "PaginationToken": "string", "UnmappedAttributes": [ { "Attribute": { "BeginOffset": number, "Category": "string", "EndOffset": number, "Id": number, "RelationshipScore": number, "RelationshipType": "string", "Score": number, "Text": "string", "Traits": [ { "Name": "string", "Score": number } ], "Type": "string" }, "Type": "string" } ] }

Response Elements

If the action is successful, the service sends back an HTTP 200 response.

The following data is returned in JSON format by the service.

Entities

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.

Type: Array of Entity objects

ModelVersion

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.

Type: String

Length Constraints: Minimum length of 1.

PaginationToken

If the result to the DetectEntitiesV2 operation was truncated, include the PaginationToken to fetch the next page of entities.

Type: String

Length Constraints: Minimum length of 1.

UnmappedAttributes

Attributes extracted from the input text that couldn't be related to an entity.

Type: Array of UnmappedAttribute objects

Errors

For information about the errors that are common to all actions, see Common Errors.

InternalServerException

An internal server error occurred. Retry your request.

HTTP Status Code: 500

InvalidEncodingException

The input text was not in valid UTF-8 character encoding. Check your text then retry your request.

HTTP Status Code: 400

InvalidRequestException

The request that you made is invalid. Check your request to determine why it's invalid and then retry the request.

HTTP Status Code: 400

ServiceUnavailableException

The Comprehend Medical; service is temporarily unavailable. Please wait and then retry your request.

HTTP Status Code: 400

TextSizeLimitExceededException

The size of the text you submitted exceeds the size limit. Reduce the size of the text or use a smaller document and then retry your request.

HTTP Status Code: 400

TooManyRequestsException

You have made too many requests within a short period of time. Wait for a short time and then try your request again. Contact customer support for more information about a service limit increase.

HTTP Status Code: 400

See Also

For more information about using this API in one of the language-specific AWS SDKs, see the following: