AI-based digital image dietary assessment methods compared to humans and ground truth: a systematic review.
Ann Med
; 55(2): 2273497, 2023.
Article
en En
| MEDLINE
| ID: mdl-38060823
These results suggest that AI methods are in line with and have the potential to exceed accuracy of human estimations of nutrient content based on digital food images.Variability in food image databases used and results reported prevented meta-analytic synthesis.The field can advance by testing AI architectures on a limited number of large-scale food image and nutrition databases that the field determines to be accurate and by reporting accuracy of at least absolute and relative error for volume or calorie estimations.Overall, the tools currently available need more development before deployment as stand-alone dietary assessment methods in nutrition research or clinical practice.
Palabras clave
Texto completo:
1
Colección:
01-internacional
Base de datos:
MEDLINE
Asunto principal:
Inteligencia Artificial
/
Evaluación Nutricional
Tipo de estudio:
Systematic_reviews
Límite:
Humans
Idioma:
En
Revista:
Ann Med
Asunto de la revista:
MEDICINA
Año:
2023
Tipo del documento:
Article
País de afiliación:
Estados Unidos
Pais de publicación:
Reino Unido