Comparative accuracy of smartphone apps and a generative <scp>AI</scp> tool for carbohydrate counting: An independent bicentric study
In this controlled hospital-based evaluation, GluciCheck, DiabHealth, and EkiYou provided the most accurate and consistent carbohydrate estimations. ChatGPT-5, despite not being designed for nutritional analysis, achieved intermediate accuracy comparable to several dedicated tools, whereas Gluroo showed the greatest variability. These findings highlight the potential of both structured manual systems and emerging AI-based technologies to support carbohydrate counting in T1D management.
Authors
- Bleuenn Dreves
- Guillaume Nars (ORCID: https://orcid.org/0000-0003-2379-5152)
- Luc Rakotoarisoa (ORCID: https://orcid.org/0000-0001-9583-2130)
- Laurent Meyer
- Michael Joubert
- Corentin Canet
- Awatif Soussi
- Theo Arnould
- Paul‐Antoine Louvet
- Mathilde Lorenzini
- Clement Hurel
- Adrien Louis
- Ariane Grandhaie
Institutions
- Université de Strasbourg (FR)
- Université de Caen Normandie (FR)
Publication Details
- Journal
- Diabetes Obesity and Metabolism
- Published
- 2025-12-22
- DOI
- https://doi.org/10.1111/dom.70396
- Primary Topic
- Nutritional Studies and Diet
- Type
- article
- Field-Weighted Citation Impact
- 0.00