Myriad Genetics speeds document processing with AWS GenAI Intelligent Document Processing Accelerator

Overview

Myriad Genetics partnered with the AWS Generative AI Innovation Center to replace an Amazon Textract/Comprehend pipeline with Amazon Bedrock foundation models (Nova Pro for classification, Nova Premier for extraction) using the open-source GenAI IDP Accelerator. Document classification accuracy rose from 94% to 98%, classification cost per page fell 77% (3.1 cents to 0.7 cents), and classification time fell 80% (8.5 minutes to 1.5 minutes per document). Automated key information extraction reached 90% accuracy matching the manual baseline, with a projected $132K in annual savings and 300 hours saved monthly across 9,000 prior authorizations in the Women's Health unit alone.

The challenge

Healthcare organizations face challenges processing and managing high volumes of complex medical documentation while maintaining quality in patient care. Myriad's Revenue Engineering Department processes thousands of healthcare documents daily across Women's Health, Oncology, and Mental Health divisions. Despite 94% classification accuracy from its existing Amazon Textract/Comprehend pipeline, the solution cost 3 cents per page (about $15,000 in monthly expenses per business unit), took 8.5 minutes of classification latency per document, and required entirely manual information extraction involving up to 10 full-time employees contributing 78 hours daily in the Women's Health unit alone.

The solution

Myriad Genetics partnered with the AWS Generative AI Innovation Center to transform its document processing pipeline using Amazon Bedrock and Amazon Nova foundation models via the open-source GenAI Intelligent Document Processing (IDP) Accelerator (Pattern 2, combining Amazon Textract with Amazon Bedrock). Amazon Nova Pro was used for document classification and Amazon Nova Premier for information extraction, using prompt engineering techniques including document-format-based classification strategies, negative prompting, few-shot visual examples and Chain of Thought reasoning to handle checkbox and other complex form data.

Reported business value

Document classification accuracy rose from 94% to 98%, classification costs fell 77% (from 3.1 to 0.7 cents per page), and classification time fell 80% (from 8.5 to 1.5 minutes per document). Automated key information extraction reached 90% accuracy, matching the manual baseline. Myriad projects up to $132K in annual savings in document classification costs, and the solution saves 300 hours monthly across 9,000 prior authorizations in the Women's Health unit alone by reducing each prior authorization submission time by 2 minutes.