Emory University researchers have developed NutriCamp, a dietary assessment app available on iOS and Android that uses advanced artificial intelligence to track nutritional intake. Users can record meals through photos, text or voice input, and the app identifies foods, estimates portions and calculates 65 nutrients and food components, including macronutrients and micronutrients such as vitamin D, iron and folate.
The app's food database covers 5,624 unique foods and beverages along with more than 23,000 common portion descriptions. The research team built advanced AI models to address challenges in real-world food assessment, including multiple ingredients in a single meal, varying portion sizes and differences in lighting and camera angles. In a study published in Communications Medicine, NutriCamp reduced average estimation error by 63% for food weight and four key nutritional measures when tested on photographs of everyday meals containing multiple foods and ingredients.
The app outperformed three popular AI-based dietary assessment applications, existing computer vision models designed for food-image analysis and GPT Vision, the image-capable AI model used in ChatGPT, according to the researchers. Dietitians also reviewed NutriCamp's estimates using real-world food examples.
Most existing dietary apps focus on lifestyle, appearance and calorie counting, while NutriCamp provides more comprehensive nutritional information that can support disease prevention and management, according to Runze Yan, co-principal investigator of the study and an assistant professor at Emory University's Nell Hodgson Woodruff School of Nursing. People with cancer, stroke survivors and others with medical conditions may need to monitor specific micronutrients and macronutrients beyond calories, Yan noted.
The research team plans to continue evaluating NutriCamp across different populations and health conditions to determine how it can support nutrition research, public health and clinical care.
