AI Predicts the Unhealthiness of Menus in the UK – Technology Networks

2 minutes, 50 seconds Read
Listen with


Register for free to listen to this article

Thank you. Listen to this article using the player above.

Want to listen to this article for FREE?

Complete the form below to unlock access to ALL audio articles.

The most deprived areas in the UK tend to have the unhealthiest cuisine, according to an artificial intelligence (AI) model.

After researchers at the University of Cambridge trained the AI on menus taken from the food delivery website Just Eat, the computer model predicted the unhealthiness of 177,926 dine-in and take-out restaurants across Britain. 

Restaurants, on average, had the healthiest menus, followed by cafes, snack bars, pubs and, lastly, fast food and take-out vendors, which were most likely to be found in high concentrations in deprived areas.

The findings were published in Health & Place.

Did somebody say spreadsheet?

To begin with, the researchers identified 54,575 food outlets available on Just Eat and rated their menu healthiness out of 12; lower scores were handed out to the menus with less vegetable diversity and more mentions of meal deals, desserts and chips (fries).

Using these data, the team then developed a deep learning model to predict the menu healthiness of all food outlets in the country, including those not on Just Eat. Their final model gave priority to the name of the food outlet.

Local authority districts with the highest menu healthiness scores included the City of London, Kensington and Chelsea and Westminster. Districts with the lowest scores included Lincolnshire, Luton and Kingston upon Hull.

The researchers found that, in general, the higher the level of deprivation in an area, the lower the average menu healthiness across all its food outlets, from restaurants to take-out vendors.

These outlets also tended to cluster in more deprived, post-industrial areas of the UK such as parts of south Wales, west Yorkshire and the northeast of England. In such areas, there were 8.39 food outlets per 1,000-3,000 people, compared to just 3.85 in the least deprived areas.

“There’s a clear pattern between the healthiness of menus at out-of-home food outlets in an area and its level of deprivation,” said Yuru Huang, a researcher at Cambridge’s epidemiology unit.

“This can create a ‘double burden’ for people living in deprived neighborhoods, where there are more outlets and these tend to be less healthy, compared to less deprived neighborhoods.”

“On top of this, there are studies that show, for example, that people with the lowest income were more likely to be obese when living in areas with a high proportion of fast-food outlets. This could even create a ‘triple burden’ for people living in these areas.”

While Huang and her colleagues note their study’s limitations – no portion sizes, cooking methods or levels of food processing were accounted for – they say their findings are still robust enough to help inform future public health policies and interventions. 

“Given the link between the food environment and diet, it’s important to understand how healthy this environment is at a local level. This will empower local authorities to take action to try and improve the consumer food environment,” Huang added.

Reference: Huang Y, Burgoine T, Bishop TRP, Adams J. Assessing the healthiness of menus of all out-of-home food outlets and its socioeconomic patterns in Great Britain. Health & Place 2024. doi: 10.1016/j.healthplace.2023.103146

This article is a rework of 
a press release issued by Cambridge University. Material has been edited for length and content.

This post was originally published on this site

Similar Posts