Using a Fine-Tuned Commercial Artificial Intelligence Model to Assess Nutrients from Photographs of Japanese Meals.

Authors

Daniel R Lane, Yuexiang Ji, Naoto Otaki, Maiko Kitagawa, Kenji Obayashi, Keigo Saeki, Toshimasa Yamauchi, Masaomi Nangaku, Kayo Waki

Published in

Journal of diabetes science and technology. Pages 19322968261462556. Jul 06, 2026. Epub Jul 06, 2026.

Abstract

To reduce meal logging burden in diet interventions, we fine-tuned OpenAI's GPT-4o on 1269 Japanese meal photographs (train/val/eval: 912/252/105) to estimate nutrients, using weighed food records or dietitian estimates as ground truth, and compared it with 27 non-fine-tuned models and a human dietitian. Non-fine-tuned models did poorly for fiber. Most models did well for carbohydrates, protein, and energy, while performance for salt and fat varied by model. GPT-5.1 (minimal reasoning) and non-fine-tuned GPT-4o models both provided strong accuracy, though not universally better than dietitian performance. The fine-tuned GPT-4o model's accuracy exceeded that of the dietitian for all nutrients, with the intra-class correlation coefficient for fiber of 0.79 (95% CI 0.782-0.797) greatly exceeded the dietitian performance of 0.68, validating the accuracy of the model.

PMID:
42410932
Bibliographic data and abstract were imported from PubMed on 07 Jul 2026.

Read full publication at:
Please sign in to see all details.

Stats

1-terrible, 9-excellent. How would you rate this publication? Sign in in to submit your rating.

Post a comment

You need to be signed in to post comments. You can sign in here.

Comments

There are no comments yet.