Normalized claim
Content-piece recall: 90%
Content piece recall of 90%
Flo Health scales medical content review using Amazon Bedrock (MACROS)
Use case typeContent review and revisionUpdated Jan 8, 2026
Flo Health is developing MACROS, an AI-assisted medical automated content review and revision optimization solution for reviewing and updating thousands of medical articles. The system uses Amazon Bedrock with AWS Step Functions, Lambda, S3, API Gateway, and ECS/Streamlit to extract rules, chunk long articles, assess adherence, generate revisions, and support human expert validation.
- Organization
- Flo Health
- Industry
- Healthcare
- Location
- United Kingdom
- Published
- January 2026
Reported outcomes
Processing speed: 10×
Time & speed
Catalog median for time & speed deployments: +59% across 138 reported metrics. Compare benchmarks →
Planned next steps
- Targets 90% content-piece recall.
Why do we believe this?Outcome claims, sources, and evidence checks
Normalized claim
Detection time: 90% decrease
Reduce detection time from hours to minutes per guideline
Normalized claim
Processing speed: 10 x increase
Speed: 10x faster than manual review process
Normalized claim
Accuracy: 80%
maintaining 80% accuracy
Normalized claim
Recall for updates: 90%
over 90% recall in identifying content requiring updates
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- Flo Health
- Provider
- AWS
- Maturity
- Unknown
- Linked source
- AWS Machine Learning Blog
No explicit deployment-stage evidence found.
Customer identity supportedSource describes one deploymentMaturity evidence evaluated
Primary read
Use case focus
Showing 2 of 2
- 1Content review and revision
- 2Workflow automation
- Build a custom AI-assisted content review workflow with Amazon Bedrock foundation models.
- Use orchestration and UI services to ingest content, extract and optimize guidelines, review articles section by section, propose revisions, and support expert validation.
- Reduces detection/review time from hours to minutes per guideline.
- Achieves about 80% accuracy with over 90% recall in identifying updates needed.
- Reduces medical expert workload and improves consistency versus manual review.
Architecture
MACROS is a custom-built, AI-assisted medical content review and revision optimization system. Users submit PDF, TXT, JSON, or pasted text through a Streamlit UI hosted on Amazon ECS, with authentication via Amazon API Gateway. Files can also be uploaded to Amazon S3. The ECS frontend orchestrates processing with AWS Step Functions. AWS Lambda performs preprocessing such as PDF text extraction. Rule Optimizer, Content Review, and Content Revision functions are orchestrated by Step Functions and call Amazon Bedrock foundation models to extract rules, review article sections against rule sets, generate compliant revisions, and combine revised sections back into the original text. AWS CloudWatch is used for monitoring and log management. The article also mentions future exploration of Amazon Bedrock Flows.
Sources & evidence1
Evidence: Low35/100Evidence strength
- Customer explicitly identified
- Quantified outcome available
- Technical implementation details available
Type: Blog PostPublished: Jan 8, 2026Publisher: AWSEvidence: VendorConfidence: Medium
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Customer evidence
Provider evidence
Browse the catalog
Was this useful?
Community
Comments
No published comments yet.