The technology behind these apps is impressive: computer vision, large food databases, and machine learning models working to translate a photo into numbers. But when a measurement system leaves out a meaningful slice of fat or misjudges a portion, the consequence is more than a statistic. Underestimates can lead people to overconsume thinking they are within targets, or to misunderstand how different diets affect energy and satiety.
Understanding where the errors happen helps us make smarter choices about tools and about food. If certain cuisines or high-fat dishes are likely to be miscounted, users and clinicians can adjust expectations, use weighing methods, or seek app improvements that prioritize equity across diets. Read the full study to see which meals caused trouble and what that means for including diverse food ways in tools that support human growth and wellbeing.
Popular AI-powered food apps may make calorie counting easier, but they may also leave out a surprisingly large part of the meal. Four apps underestimated calories and fat by about one-third when tested against carefully prepared meals. High-fat ketogenic dishes appeared to cause the most trouble, while carbohydrates were measured more consistently.
