UCL Tool Rates Risk of Online Diet & Nutrition Misinformation | News

A new tool designed to assess the potential harm of nutrition misinformation online has been developed by researchers at University College London (UCL), offering a more nuanced approach than existing “true or false” fact-checking methods.

The Diet-Nutrition Misinformation Risk Assessment Tool, or Diet-MisRAT, doesn’t simply identify inaccurate claims. Instead, it evaluates the degree to which online content could mislead individuals, particularly those vulnerable to harmful dietary advice. The tool’s development comes as the World Health Organization (WHO) recognizes the spread of health misinformation as a major public health threat.

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

Unlike current methods, Diet-MisRAT acknowledges that misleading information can influence behaviour even if it isn’t demonstrably false. The tool adapts the WHO’s framework for assessing hazardous exposures – typically used in physical environments – to the digital realm, treating online content as the “medium” and misleading traits as “risk agents.” Content is then ranked as green, amber, or red based on a weighted misinformation risk score.

The assessment considers not only the content itself, but also the context in which it’s presented and the susceptibility of the audience. Researchers tested and refined the tool through five rounds of verification, incorporating feedback from nearly 60 specialists in dietetics, nutrition, and public health to ensure assessments align with professional judgement. This process identified key characteristics of misinformation – inaccuracy, hazardous omissions, and manipulative framing – and indicators that amplify risk, such as how and where the content is consumed.

The tool’s capabilities were demonstrated in assessing claims such as suggesting high-dose vitamin A as a safer alternative to the MMR vaccine. Diet-MisRAT classified this as a critical risk due to its false safety framing, omission of the dangers of excessive vitamin A, and undermining of public health guidance.

“It is essential to include specialist expertise when assessing misinformation risk,” said Professor Anastasia Kalea, co-author from the UCL Division of Medicine. “Our tool was calibrated and validated with feedback from nearly 60 subject-matter experts. This helps ensure that assessments of potential harm reflect appropriate professional judgement.”

The researchers found that isolating misleading features and linking them to potential outcomes allows for a clearer understanding of what makes content high-risk and the scale of its potential impact. This is particularly relevant given recent cases of harm linked to online misinformation, including a 2025 diagnosis of cholesterol-induced skin lesions in a man following a carnivore diet promoted on social media, and a hospitalisation resulting from someone replacing salt with toxic sodium bromide based on incorrect AI-generated advice.

The development of Diet-MisRAT contributes to ongoing discussions about how digital platforms, public health authorities, and policymakers should respond to the growing influence of misleading health advice, particularly on social media, in search summaries, and through generative AI. Ruani emphasized the need to treat misleading health information as a risk factor, arguing that mitigation strategies should be proportionate to the level of potential harm.

“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,” Ruani stated.

Professor Michael Reiss, co-author from the UCL Institute of Education, added that the tool’s risk assessment criteria can be incorporated into educational programs and professional training, equipping individuals to recognize and challenge misleading information. “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.”