New Tool Tackles Health Misinformation on Social Media and AI Platforms

A groundbreaking tool developed by researchers at University College London (UCL) aims to combat potentially life-threatening diet and vaccine misinformation that proliferates across social media and appears in AI search summaries.

The World Health Organization has identified health misinformation as a major public health threat with serious consequences. From dangerous fad diets and extreme fasting regimens to the improper use of dietary supplements, misleading health information can lead to severe medical complications and poor health outcomes.

Research suggests herbal and dietary supplements alone contribute to approximately 20 percent of drug-induced liver injury cases and result in roughly 23,000 emergency department visits annually in the United States.

Unlike existing fact-checking methods that simply categorize content as “true” or “false,” UCL’s new tool addresses the more nuanced problem of content that isn’t overtly false but carries the potential to dangerously mislead readers, particularly those in vulnerable populations.

“When it comes to diet and nutrition, misinformation often operates through selective framing that masks potential health risks. Harmful misleading content tends to fly under fact-checkers’ radars and escape meaningful oversight until high-profile cases make the headlines,” explained lead author and developer Alex Ruani from UCL.

The consequences of such misinformation can be severe. Researchers cited a 2025 case where a man developed cholesterol-induced skin lesions after adopting a carnivore diet—a trend amplified by social media algorithms, particularly within so-called “manosphere” communities. In another case, a person was hospitalized after following incorrect AI-generated advice to replace sodium chloride (table salt) with sodium bromide, a toxic substance with no nutritional value.

Even more concerning, online misinformation has been linked to cancer patients abandoning proven medical treatments in favor of unproven dietary alternatives, potentially costing them their lives.

Named the Diet-Nutrition Misinformation Risk Assessment Tool (Diet-MisRAT), the system analyzes content and evaluates its potential to mislead readers. It then assigns material to green, amber, or red categories based on a weighted misinformation risk score.

For instance, content claiming “it is safer to give your child high-dose vitamin A than the MMR vaccine” would be classified as critical risk due to its false safety framing, which could lead parents to make dangerous health decisions for their children.

The researchers validated the tool’s accuracy by comparing its assessments against the judgments of nearly 60 specialists in dietetics, nutrition, and public health, with results published in the journal Scientific Reports.

Dr. Ruani highlighted the particular dangers of AI-generated health advice: “When AI chatbots speak confidently, users may assume their advice is safe. If we can properly measure how misleading a piece of advice is and how much harm it may pose, we can build stronger safeguards into models and AI agents before deployment rather than reacting after harm occurs.”

The implications extend beyond individual health decisions. The tool could help policymakers, digital platforms, and regulators implement stronger safeguards against harmful health misinformation online.

Professor Michael Reiss, a co-author of the study, noted the educational potential of the tool: “By spelling out the typical patterns that distort diet, nutrition or supplement information, the tool’s risk assessment criteria can be taught and applied in education and professional training. This will help learners understand not just whether something is wrong, but how and why it can skew judgment, equipping them to recognize and challenge it.”

As both social media and AI continue to serve as primary information sources for health decisions, tools like Diet-MisRAT represent crucial steps toward protecting public health in the digital age.