Recent interest in seaweeds as a source of macronutrients, micronutrients, and bioactive components has highlighted prospective applications within the functional food and nutraceutical industries, with impetus toward the alleviation of risk factors associated with noncommunicable diseases such as obesity, type 2 diabetes, and cardiovascular disease. This narrative review summarizes the nutritional composition of edible seaweeds; evaluates the evidence regarding the health benefits of whole seaweeds, extracted bioactive components, and seaweed-based food products in humans; and assesses the potential adverse effects of edible seaweeds, including those related to ingestion of excess iodine and arsenic. If the potential functional food and nutraceutical applications of seaweeds are to be realized, more evidence from human intervention studies is needed to evaluate the nutritional benefits of seaweeds and the efficacy of their purported bioactive components. Mechanistic evidence, in particular, is imperative to substantiate health claims.

Background/Objectives: Advances in artificial intelligence now allow combined use of large language and vision models; however, there has been limited evaluation of their potential in dietary assessment. This study aimed to evaluate the accuracy of ChatGPT-4 in estimating nutritional content of commonly consumed meals using meal photographs derived from national dietary survey data. Methods: Meal photographs (n = 114) were uploaded to ChatGPT and it was asked to identify the foods in each meal, estimate their weight, and estimate the nutrient content of the meals for 16 nutrients for comparison with the known values using precision, paired t-tests, Wilcoxon signed rank test, percentage difference, and Spearman correlation (r_s). Seven dietitians also estimated energy, protein, and carbohydrate content of thirty-eight meal photographs for comparison with ChatGPT using intraclass correlation (ICC). Results: Comparing ChatGPT and actual meals, ChatGPT showed good precision (93.0%) for correctly identifying the foods in the photographs. There was good agreement for meal weight (p = 0.221) for small meals, but poor agreement for medium (p < 0.001) and large (p < 0.001) meals. There was poor agreement for 10 of the 16 nutrients (p < 0.05). Percentage difference from actual values was >10% for 13 nutrients, with ChatGPT underestimating 11 nutrients. Correlations were adequate or good for all nutrients with r_s ranging from 0.29 to 0.83. When comparing ChatGPT and dietitians, the ICC ranged from 0.31 to 0.67 across nutrients. Conclusions: ChatGPT performed well for identifying foods, estimating weights of small portion sizes, and ranking meals according to nutrient content, but performed poorly for estimating weights of medium and large portion sizes and providing accurate estimates of nutrient content.

There is a scarcity of dietary intake research focusing on the intake of whole meals rather than on the nutrients and foods of which those meals are composed. This growing area of research has recently begun to utilize advanced statistical techniques to manage the large number of variables and permutations associated with these complex meal patterns. The aim of this narrative review was to evaluate those techniques and the meal patterns they detect. The 10 observational studies identified used techniques such as principal components analysis, clustering, latent class analysis, and decision trees. They examined meal patterns under 3 categories: temporal patterns (relating to the timing and distribution of meals), content patterns (relating to combinations of foods within a meal and combinations of those meals over a day), and context patterns (relating to external elements of the meal, such as location, activities while eating, and the presence or absence of others). The most common temporal meal patterns were the 3 meals/d pattern, the skipped breakfast pattern, and a grazing pattern consisting of smaller but more frequent meals. The 3 meals/d pattern was associated with increased diet quality compared with the other 2 patterns. Studies identified between 7 and 12 content patterns with limited similarities between studies and no clear associations between the patterns and diet quality or health. One study simultaneously examined temporal and context meal patterns, finding limited associations with diet quality. No study simultaneously examined other combinations of meal patterns. Future research that further develops the statistical techniques required for meal pattern analysis is necessary to clarify the relations between meal patterns and diet quality and health.

Examination of meal intakes can elucidate the role of individual meals or meal patterns in health not evident by examining nutrient and food intakes. To date, meal-based research has been limited to focus on population rather than individual intakes, without considering portions or nutrient content when characterizing meals. To characterize meals commonly consumed, incorporating portions and nutritional content, and to determine the accuracy of nutrient intake estimates using these meals at both population and individual levels. The 2008–2010 Irish National Adult Nutrition Survey (NANS) data were used. 1500 participants, with an age (mean ± SD) of 44.5 ± 17.0 and BMI of 27.1 ± 5.0, recorded their intake using a 4-day weighed food diary. Food groups were identified using k-means clustering. Partitioning around the medoids clustering was used to categorize similar meals into groups (generic meals) based on their Nutrient Rich Foods Index (NRF9.3) score and the food groups that they contained. The nutrient content for each generic meal was defined as the mean content of the grouped meals. 7 standard portion sizes were defined for each generic meal. Mean daily nutrient intakes were estimated using the original and the generic data. The 27,336 meals consumed were aggregated to 63 generic meals. Effect sizes from the comparisons of mean daily nutrient intakes (from the original v generic meals) were negligible or small, with P values ranging from < 0.001 to 0.941. When participants were classified according to nutrient-based guidelines (high, adequate, or low), the proportion of individuals who were classified into the same category ranged from 55.3% to 91.5%. A generic meal-based method can estimate nutrient intakes based on meal rather than food intake at the sample population and individual levels. Future work will focus on incorporating this concept to a meal-based dietary intake assessment tool.

Language models are a form of generative artificial intelligence that excel at natural language understanding and generation, with possible applications for providing evidence-based nutrition information in an interactive and personalized manner. However, they also pose risks to public health related to inaccuracy, bias, and data protection. It is unclear what quantity or type of research has been conducted on these models applied within nutrition and dietetics. This scoping review aims to identify the ways in which language models are being applied to nutrition and dietetics and the associated opportunities and challenges. The review was conducted in accordance with a pre-defined protocol, and included original studies from peer-reviewed journals. The databases Medline, EMBASE, PsycINFO, CINAHL, PubMed, Global Health, Web of Science, Scopus, DBLP, and IEEE Xplore were searched, and forward and backward citation chasing conducted for included articles. There were 2118 articles identified, and after screening 40 remained for data charting. All studies were published between 2022 and 2024. A total of 23 different language models were used with nine studies creating domain-specific models using retrieval augmented generation or fine-tuning. A total of 17 nutrition-related diseases were considered. The tasks assigned to the language models included extraction or summarization of data from the scientific literature or electronic health records (n = 5), estimation of food composition (n = 9), creation of meal plans (n = 7), and provision of dietary advice (n = 21). Most studies (n = 38) focused on evaluating the models in hypothetical situations such as researcher-designed case studies or questions. In conclusion, this is an emerging area with limited evidence for real-world implementations or domain-specific models in nutrition and dietetics. Future work is required in real-world settings to strengthen this evidence base and to broaden it to incorporate the views of nutritionists, dietitians, people with medical conditions, and the general public.

Recent work has focused on understanding the link between diet quality and environmental impact, however it is also important to consider the role food processing plays in this relationship. Using model meal plans, this paper examines the link between nutrient content, environmental impact, and processing. Four distinct meal plans were considered – ‘Healthy’, ‘Unhealthy’, ‘Healthy (plant-based)’, ‘Healthy (plant-based, processed)’. For each a variety of environmental impact, processing and nutritional composition metrics were compared. Alternative healthy eating index (AHEI) score for the Unhealthy diet was significantly lower than the other three diets. The ‘Healthy (plant-based)’ diet had the highest AHEI score but was not significantly different to the ‘Healthy (plant-based, processed)’ and ‘Healthy’ diet scores. The greenhouse gas emissions for the two plant based diets were not significantly different to each other or to the ‘Healthy’ diet but were significantly lower than the ‘Unhealthy’ diet. The ‘Healthy’, ‘Unhealthy’, and ‘Healthy (plant-based)’ diets had similar processing specific energy consumption values however, the ‘Healthy (plant-based, processed)’ diets had significantly greater specific energy consumption. There was no clear link between diet quality and food processing when considered using processing specific energy value. When the number of processes in each diet was estimated, the unhealthier diet had considerably more processes associated with it. Examining the interaction of nutritional quality, environmental impact and processing of diets in this way highlights the complexity of the inter-relationships. Understanding these interactions is necessary to support the transition to healthy diets from sustainable sources.