Description
The Amazon Comprehend Medical plugin is a batch-transform* plugin that communicates with Amazon Comprehend Medical from Amazon to enrich data using their NLP service.
* More information about the different DISQOVER plugin types can be found here.
Download and installation
The plugin code can be downloaded from the table below and installed on your DISQOVER instance. Following steps are necessary to install the plugin:
- Unzip the downloaded plugin in the /disqover/data/plugins/ folder on your DISQOVER instance.
- Restart your DISQOVER instance.
DISQOVER version |
Download plugin code |
Version 6.10 and higher |
After installation on the DISQOVER server, the Amazon Comprehend Medical plugin will show up in the list of components in the Plugins section.
The Amazon Comprehend Medical component behaves the same way as the other default components of the Data Ingestion Engine.
Component fields
Basic section
- Class: The pipeline class from which you want to select data to process in the plugin (required).
- Filter: The option to apply a filter to this class to select a subset of data to process.
Input predicates section
- Text: The input predicate from the selected class to push to the Amazon Comprehend Medical service for NLP (required).
- Amazon Access Key: The AWS access key for the usage of the service.
- Amazon Secret Key: The AWS secret key for the usage of the service.
Output predicates section
- Response: A newly defined predicate in which the output of the Amazon Comprehend Medical service will be stored (required).
Output
The data stored in the response predicate will be JSON structured data: the response from the Amazon Comprehend Medical service. Different fields can be further extracted and further processed in e.g., an Extract Distinct component and synced/merged with public data.
Technical information and requirements
To limit the load and cost on the Amazon Comprehend Medical service, the responses captured from the Amazon Comprehend Medical service are cached. This means the response data is stored locally on the DISQOVER server for faster retrieval when rerunning the plugin component in the Data Ingestion Engine and limiting the number of requests to the Amazon Comprehend Medical service. For more information on this Asset, please reach out to us!