Using One-Shot Prompting of Non-Fine-Tuned Commercial Artificial Intelligence to Assess Nutrients from Photographs of Japanese Meals

Abstract

Background:

Diet interventions often have poor adherence due to burdensome food logging. Approaches using photographs assessed by artificial intelligence (AI) may make food logging easier, if they are adequately accurate.

Method:

We used OpenAI’s GPT-4o model with one-shot prompts and no fine-tuning to assess energy, fat, protein, carbohydrate, fiber, and salt through photographs of 22 meals, comparing assessments to weighed food records for each meal and to assessments of dieticians.

Results:

The model had poor performance overall. For fiber, though, the model achieved an intraclass correlation coefficient of 0.71 (0.67-0.74 95% CI), well above the dietician performance of 0.57.

Conclusions:

The simplest use of current AI via one-shot prompting and no fine-tuning accurately assesses fiber content in meals but is inaccurate for other nutritional parameters.