What challenges did UC Davis Health Cloud Innovation Center face before AI implementation?

Public health officials and manual fact-checkers could not keep up with rapidly changing misinformation. Overburdened and understaffed health departments lacked tools to thwart misinformation threats before they spread.

What was the impact of the AI solution?

The prototype was validated with public health experts and described as relieving burden on understaffed departments. Users said the platform would be like having an additional entire team of employees and stated they would trust the tool because it separated verified and non-verified sources.

Source

Evidence: Low25/100

UC Davis Health Cloud Innovation Center (Project Heal) builds Amazon Bedrock RAG assistant to generate counter-messaging against health misinformation

Use case typePublic health supportUpdated Apr 17, 2024

UC Davis Health Cloud Innovation Center and AWS Digital Innovation built Project Heal, an open source AI/ML toolkit concept for public health officials to detect emerging health misinformation and generate tailored counter-messaging. The solution combines ML classification, threat scoring, human feedback, and Amazon Bedrock retrieval-augmented generation to help understaffed health departments respond faster and more proactively.

Organization: UC Davis Health Cloud Innovation Center
Industry: Public Sector
Location: United States
Published: April 2024

Planned next steps

The source says this outcome is planned: More proactive public health communications.

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

Customer: UC Davis Health Cloud Innovation Center, University of Pittsburgh, University of Illinois Urbana-Champaign
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

1Public health support
2Content generation
3Decision support

Use ML models to classify misinformation, score threat severity, and support keyword/entity extraction.
Use Amazon Bedrock with RAG to generate counter-messaging tailored to audience and platform, backed by trusted sources.
Use Amazon Augmented AI for human feedback and Amazon SageMaker for model building and deployment.

Technologies

Amazon Bedrock Amazon SageMaker Amazon Augmented AI Amazon Neptune Amazon ECS AWS Fargate Amazon Kinesis Data Streams Amazon Kinesis Data Firehose AWS Lambda Amazon S3 Amazon DynamoDB Amazon API Gateway

The prototype was validated with public health experts and described as relieving burden on understaffed departments.
Users said the platform would be like having an additional entire team of employees and stated they would trust the tool because it separated verified and non-verified sources.

Architecture

The conceptual architecture includes Amazon ECS on AWS Fargate, Amazon Kinesis Data Streams, Amazon Kinesis Data Firehose, AWS Lambda, Amazon S3, Amazon Augmented AI, Amazon Neptune, Amazon SageMaker, Amazon CloudFront, Amazon API Gateway, Amazon DynamoDB, and Amazon Bedrock with RAG. The workflow ingests misinformation content, classifies and scores threats using ML and graph-based components, and generates tailored counter-messaging from trusted sources while maintaining a human feedback loop.

Implementation partners1

AWS Digital Innovation

Sources & evidence1

Evidence: Low25/100Evidence strength