Dietary intake assessment is an essential part of nutrition research and practice, with the use of digital technology now well established(1) and artificial intelligence (AI) in the form of image recognition readily available in research and commercial settings(2). Recent advances in large language models (LLMs), such as ChatGPT, allow computers to converse in a human-like way providing text responses to typed queries. No studies, however, have utilised both the LLM and image recognition components of ChatGPT-4 to evaluate its accuracy to estimate nutritional content of meals.The aim of this study was to evaluate the accuracy of the ChatGPT-4 LLM and image recognition model in estimating the nutritional content of meals.Thirty-eight meal photographs with known nutritional content (from McCance and Widdowson’s Composition of Foods) were uploaded to ChatGPT, and it was asked to provide point estimates for each of the meals for each of the following: energy (kcal), protein (g), total carbohydrate (g), dietary fibre (g), total sugar (g), total fat (g), saturated fat (g), monounsaturated fat (g), polyunsaturated fat (g), calcium (mg), iron (mg), sodium (mg), potassium (mg), vitamin D (mcg), folate (mcg), and vitamin C (mg). Comparisons were made between ChatGPT estimates and those from McCance and Widdowson using the Wilcoxon signed rank test, percent difference, Spearman’s correlation, and cross-classification of quartiles. Interpretation of statistical measures was based on Lombard et al.(3).For estimating the content of meals, differences (p < 0.05) existed between the methods for 11 of the 16 nutrients, and 12 nutrients had a percent difference of >10%, indicating poor agreement for most nutrients. ChatGPT underestimated 15 of the 16 nutrients. Conversely, when considering the ranking of meals, all nutrients had correlation coefficients which indicated good (rs ≥ 0.50)(11 of 16) or acceptable (0.20 < rs < 0.49)(5 of 16) agreement. In the cross-classification of quartiles, ≥50% of meals were classified into the same quartile by both methods for 9 nutrients and 10% of meals were classified into opposite quartiles for 14 nutrients, indicating good agreement. ChatGPT also provided caveats regarding its estimations such as “the caloric estimate assumes the butter is spread thinly” and “cornflakes can often be fortified with vitamins and minerals […] and exact content could also vary based on the brand of cornflakes”.ChatGPT showed poor agreement for estimating the nutritional composition of meal photographs for most nutrients, but the correlation and cross-classification of quartiles indicate good ability to rank meal photographs according to nutritional composition. Further research is required with a wider range of meals and in real-world settings. Future work should consider the training of language models using high-quality nutrition data to improve accuracy and maximise the potential for their use in dietary assessment.

An abstract is not available for this content. As you have access to this content, full HTML content is provided on this page. A PDF of this content is also available in through the ‘Save PDF’ action button.

An abstract is not available for this content. As you have access to this content, full HTML content is provided on this page. A PDF of this content is also available in through the ‘Save PDF’ action button.

Web based dietary assessment methods may offer solutions to the limitations of traditional dietary assessment methodologies (cost, participation rates and accuracy of data collected) especially in large epidemiological studies. Foodbook24 is a web-based 24 hour dietary recall tool which has been developed for use in the Irish adult population. The aim of this project was to investigate the validity of Foodbook24 compared to intakes derived from a 4 day semi weighed food diary and biomarkers of nutrient intake. This study received ethical approval from the UCD Human Research Ethics Committee (LS1527). Forty participants aged 18–64 years (50 % female) were recruited to the study which consisted of three visits to UCD. Participants were required to complete 3 nonconsecutive (2 week day and 1 weekend day) 24 hour recalls using Foodbook24 and subsequently provided a fasted blood sample and 24 hour urine collection. A two week wash out period was included to allow sufficient time to elapse between reporting methods, then participants completed a 4 day semi weighed food diary (3 week days and 1 weekend day) and provided a fasted blood sample and 24 hour urine collection on completion of the food diary. Biological samples were obtained for analysis of select nutritional biomarkers. Data obtained from FoodBook24 was automatically analysed by the tool itself generating a nutrient output. In addition all food diaries were entered into nutrition analysis software, WISP (Tinuviel Software, Anglesey, UK). Statistical analyses were performed in SPSS (Version 20·0). Mean nutrient intake levels and % energy contributions (and standard deviations) recorded using each method were calculated. Spearman correlations and Wilcoxon Signed Rank tests (data was not normally distributed) were used to investigate the agreement and differences in the nutrient output from the two methods.

An abstract is not available for this content. As you have access to this content, full HTML content is provided on this page. A PDF of this content is also available in through the ‘Save PDF’ action button.

An abstract is not available for this content. As you have access to this content, full HTML content is provided on this page. A PDF of this content is also available in through the ‘Save PDF’ action button.

An abstract is not available for this content. As you have access to this content, full HTML content is provided on this page. A PDF of this content is also available in through the ‘Save PDF’ action button.

An abstract is not available for this content. As you have access to this content, full HTML content is provided on this page. A PDF of this content is also available in through the ‘Save PDF’ action button.

An abstract is not available for this content. As you have access to this content, full HTML content is provided on this page. A PDF of this content is also available in through the ‘Save PDF’ action button.