What challenges did Acentra Health face before AI implementation?

Processing tens of millions of Medicare document pages each year with legacy OCR required manual search and data entry across multiple systems, creating delays, higher costs, and human error for clinicians reviewing appeal and evidence documents.

What was the impact of the AI solution?

Document processing time was reduced by more than 50%. Document processing costs were lowered by 40%. The solution improved accuracy by reducing human error in manual entries. Clinicians can navigate lengthy medical records and find evidence more efficiently.

Source

Evidence: Low35/100

Acentra Health: intelligent document processing for Medicare appeals and quality of care cases with Amazon Textract

Use case typeIntelligent document processingUpdated Oct 9, 2024

Acentra Health, a BFCC-QIO serving Medicare beneficiaries, built an intelligent document processing pipeline to handle appeals and quality-of-care cases more efficiently. The solution converts scanned images and faxed medical records into searchable text and stores extracted outputs and metadata for audit, analytics, and fast evidence access.

Organization: Acentra Health
Industry: Healthcare
Location: United States
Published: October 2024

Why do we believe this?Outcome claims, sources, and evidence checks

Normalized claim

Document processing time: 50% decrease

AWS Public Sector BlogOct 9, 2024Blog postExplicit claimLow evidence strength

reduced document processing times by more than 50 percent

Normalized claim

Document processing cost: 40% decrease

AWS Public Sector BlogOct 9, 2024Blog postExplicit claimLow evidence strength

lowered document processing costs by 40 percent

Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks

Customer: Acentra Health
Provider: AWS
Maturity: Unknown
Linked source: AWS Public Sector Blog

No explicit deployment-stage evidence found.

Customer identity supportedSource describes one deploymentMaturity evidence evaluated

Primary read

Use case focus

Showing 3 of 3

1Intelligent document processing
2Document processing automation
3Case management

Acentra Health implemented a serverless intelligent document processing pipeline on AWS.
The workflow uses Amazon S3 for document storage, AWS Step Functions for orchestration, and Amazon Textract to extract text and key information from scanned images and faxed documents.
Extracted data and original documents are stored in Amazon S3, while metadata is kept for cost attribution, analytics, and audit purposes.
The solution also supports keyword-based bookmarking so healthcare practitioners can locate relevant evidence faster.

Technologies

Amazon Textract Amazon Simple Storage Service (Amazon S3)AWS Step Functions AWS Lambda

Document processing time was reduced by more than 50%.
Document processing costs were lowered by 40%.
The solution improved accuracy by reducing human error in manual entries.
Clinicians can navigate lengthy medical records and find evidence more efficiently.

Architecture

A serverless, event-driven IDP pipeline stores uploaded documents in Amazon S3, triggers AWS Step Functions workflows, sends files to Amazon Textract for OCR and extraction, and persists extracted data, originals, and metadata for audit and analytics. The solution also adds keyword-based bookmarking for faster evidence retrieval.

Sources & evidence1

Evidence: Low35/100Evidence strength

Customer explicitly identified
Quantified outcome available
Technical implementation details available

Type: Blog PostPublished: Oct 9, 2024Publisher: AWSEvidence: VendorConfidence: Medium

Primary source

AI-generated summary. Verify important details with the linked sources before relying on this case.

Acentra Health: intelligent document processing for Medicare appeals and quality of care cases with Amazon Textract

Use case focus

Challenges

Solution

Reported impact

Comments

Similar cases