Book Image

Intelligent Document Processing with AWS AI/ML

By : Sonali Sahu
Book Image

Intelligent Document Processing with AWS AI/ML

By: Sonali Sahu

Overview of this book

With the volume of data growing exponentially in this digital era, it has become paramount for professionals to process this data in an accelerated and cost-effective manner to get value out of it. Data that organizations receive is usually in raw document format, and being able to process these documents is critical to meeting growing business needs. This book is a comprehensive guide to helping you get to grips with AI/ML fundamentals and their application in document processing use cases. You’ll begin by understanding the challenges faced in legacy document processing and discover how you can build end-to-end document processing pipelines with AWS AI services. As you advance, you'll get hands-on experience with popular Python libraries to process and extract insights from documents. This book starts with the basics, taking you through real industry use cases for document processing to deliver value-based care in the healthcare industry and accelerate loan application processing in the financial industry. Throughout the chapters, you'll find out how to apply your skillset to solve practical problems. By the end of this AWS book, you’ll have mastered the fundamentals of document processing with machine learning through practical implementation.
Table of Contents (16 chapters)
Part 1: Accurate Extraction of Documents and Categorization
Part 2: Enrichment of Data and Post-Processing of Data
Part 3: Intelligent Document Processing in Industry Use Cases

Handling documents with an FHIR data store

Now let’s see what happens when our input for HealthLake is not in FHIR format, but is a document instead. Amazon HealthLake currently only supports data in FHIR format. What if we need to process document-based health data along with FHIR data? Can we still create a centralized scalable FHIR data store for health data?

And the answer is yes. We can use Amazon Textract to get raw text from the document and convert it to an FHIR resource (a DocumentReference resource). This DocumentReference FHIR resource can then be input into Amazon HealthLake with additional FHIR resources.

This is a three-step process:

  1. Extracting data from the document with Amazon Textract
  2. Creating a DocumentReference FHIR resource from the extracted Textract response
  3. Ingesting the DocumentReference FHIR resource to Amazon HealthLake

You can see the architecture in the following figure:

Figure 7.15 – Document...