Thanks to advances in AI, popular calorie tracking apps can now use photos of your meals to estimate the nutritional content of what you’re eating. While these apps are useful, a new study found that four photo-based apps underestimated the calorie and fat content of meals by about a third.
Photo-based calorie tracking uses AI image recognition to identify foods in meal photos and estimate portion sizes. This information is compared to nutritional databases to calculate estimated calories and nutrients.
Photo-based calorie tracking apps are extremely popular, especially among people looking to manage their health or lose weight. However, many of these apps have not been fully evaluated for accuracy. Our study helps address this issue by examining whether these apps can reliably estimate calories. ”
Aaron Hengist, Postdoctoral Visiting Scholar in the Intramural Program at the National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK), part of the National Institutes of Health
Olivia Charles, a post-baccalaureate intramural research fellow at NIDDK, will present her research findings at NUTRITION 2026, the American Academy of Nutrition’s flagship annual meeting, to be held July 25-28 in National Harbor, Maryland, just outside Washington, DC.
This new study is part of a larger NIH Clinical Center dietary study investigating how the body processes nutrients when people consume a low-carbohydrate (ketogenic) or standard diet. The clinical trial meals are prepared in a metabolically controlled kitchen, a type of research kitchen, and ingredients are carefully weighed to the nearest 0.1 gram.
To assess how well photo-based calorie tracking apps estimate nutritional content from images, researchers took standardized photos of 102 meals prepared as part of a dietary study and ran them through the MyFitnessPal, LoseIt!, CalAI, and Appediet apps.
“By using meals prepared in a tightly controlled metabolic kitchen, we were able to compare the app’s estimates to an accurate standard,” Hengist said. “This kind of direct, high-quality comparison has not been available until now.”
All four apps underestimated the calorie content of meals by about 250 to 345 calories and about 30 grams of fat, on average. In our analysis, MyFitnessPal and LoseIt! apps more accurately estimated the energy content of high-calorie meals than low-calorie meals, and all four apps more consistently estimated carbohydrates than other macronutrients.
“People who use photo-based tracking apps without adjusting or entering food amounts should take the results with a grain of salt,” Hengist says. “These apps tend to underestimate calories, especially fat calories, so the amount you actually eat may be higher than the calories shown on the app.”
After conducting the initial analysis, the researchers looked at more than 200 additional meals to better understand what influences the app’s accuracy. Their early results suggest that the app may struggle even more with meals that are part of a low-carb ketogenic diet. This is probably because the high fat content of these meals tends to be consistently underestimated.
Researchers say combining photo-based features with traditional methods of measuring diet quality could improve the real-world accuracy of calorie-tracking apps.
sauce:
American Academy of Nutrition
