MediaFutures is presenting AI-powered platform to help critically assess health-related claims online. Illustration image: OpenAI
Every day, millions of people encounter health claims online—from news articles and social media posts to blogs and commercial websites. While access to health information has never been greater, distinguishing trustworthy advice from misleading or unsupported claims is becoming increasingly difficult.
Researchers at MediaFutures are addressing this challenge through VITAL—the Verification & Intelligence Tool for Accurate Health Literacy.
VITAL is an AI-powered platform designed to help citizens critically assess health-related claims by combining large language models, natural language processing, trustworthy scientific evidence, and transparent sourcing.
Instead of simply telling users whether a claim is “true” or “false,” VITAL provides context. The platform is being developed to analyse health claims, identify supporting or contradicting scientific evidence, explain its reasoning in accessible language, and direct users to reliable sources so they can make informed decisions themselves.
“Our goal is to empower users. We want AI to become a partner that helps citizens understand why a health claim is credible—or why they should remain sceptical.”
The current prototype focuses on analysing health-related news articles. Future developments will include support for social media content, browser-based assistance, personalised explanations and alternative sources, multilingual support, and large-scale user evaluations.
MediaFutures will publicly present VITAL during Arendalsuka 2026 as part of the session Responsible AI in News Media—From Research to Practice.
Over the coming months, the team will continue developing VITAL together with research partners, industry collaborators, and end users. The long-term vision is to build AI systems that not only provide answers, but also help people understand, question, and make informed decisions about the information they encounter every day.