BACKGROUND
Measuring food and nutrient intakes has historically been challenging, often relying on subjective recall or labor-intensive diaries. With the advent of artificial intelligence (AI), there exists potential for more precise and efficient dietary assessment.
OBJECTIVE
This scoping review aimed to synthesize existing literature on the efficacy, accuracy, and challenges of employing AI tools in assessing food and nutrient intakes, offering insights into their current advantages and areas of improvement.
METHODS
A systematic literature search was conducted in PubMed, Web of Science, Cochrane Library, and EBSCO databases.
RESULTS
Our search revealed 25 pertinent studies published between 2010 and 2023. The included studies showcased the utility of AI in dietary assessments across various contexts and populations. Measures of food intake ranged from visual recognition of food items to intricate nutrient analyses facilitated by advanced machine learning algorithms. Comparative results underscored the superiority of AI in certain aspects, such as real-time data collection and minimizing recall bias, over traditional methods.
CONCLUSIONS
AI-based approaches also presented limitations, including challenges with diverse food items and potential biases in algorithms. The broader implications encompassed the potential of AI in population-level dietary assessment studies, precision nutrition, and disease management.