Summary
In this chapter, we discussed the document enrichment stage of intelligent document processing with medical insights to augment our document processing with additional insights. We introduced Amazon Comprehend Medical and dove deep into its core features, extracting medical insights such as medical conditions, medication, affected anatomy, time expressions, entity traits, and more from text. We also discussed leveraging Amazon Textract to extract text from medical documents and then passing it to Amazon Comprehend Medical for medical entity extraction. This helps to build a document extraction/enrichment stage for IDP.
We then gave a high-level overview of medical ontology linking and reviewed the need for it. We then looked into the implementation of Amazon Comprehend Medical’s ontology linking to extract ICD-10-CM, RXNorm, and SNOMED CT codes from medical documents.
In the next chapter, we will extend the extraction and enrichment stage of the document processing...
