Food labels are low-cost, informational tools that can help curb the spread of diet-related non-communicable diseases. This study described consumers\' knowledge, attitudes, and practices related to food labels in Jordan and explored the relationship between knowledge and attitude with comprehensive use of food labels. A cross-sectional, online survey assessed Jordanian adult consumers\' ability to comprehend the nutritional contents of food labels (knowledge score), their attitudes towards food labels (attitude scale), and how frequently they used different parts of food labels (practice scale). Multivariate logistic regression models assessed predictors of comprehensive use of food labels. A total of 939 adults participated in the study. Total mean scores for the practice scale (14 questions), attitude scale (8 questions), and knowledge score (4 questions) were 49.50 (SD, 11.36; min, 5; max, 70), 29.70 (SD, 5.23; min, 5; max, 40), and 1.39 (SD, 1.33; min, 0; max, 4), respectively. Comprehensive users of food labels (26.4%) were more likely female, responsible for grocery shopping, and had higher mean knowledge and attitude scores. Jordanian consumers seem to have good practices and attitudes related to food label use but suboptimal knowledge regarding content. Future interventions should focus more on enhancing knowledge and awareness related to food labels.

We investigated the relationship between nutrition literacy, diet quality, carotenoid status, and cognition.
Adults aged 37.5 ± 17.0 years (n = 52) completed the 42-item Nutrition Literacy Assessment Instrument (NLit). The Dietary History Questionnaire III was analyzed to determine the Healthy Eating Index. Skin carotenoids were assessed as a diet quality biomarker. Selective attention, relational memory, and pattern separation abilities were assessed using the flanker, spatial reconstruction, and mnemonic similarity tasks, respectively. Statistical adjustments included age, sex, education, and body mass index.
No correlations were observed for NLit scores and NLit subscales with Healthy Eating Index and skin carotenoid status. However, the NLit\'s food label and numeracy subscale was related to greater pattern separation abilities (ρ = 0.33, r2 = 0.11, P = 0.03).
Comprehension of food labels and numeracy information was associated with memory abilities. Future work is needed to test whether targeting working memory and attentional processes during memory retrieval in larger samples may facilitate the acquisition of nutrition knowledge.

The consumption and availability of ultra-processed foods (UPFs), which are associated with an increased risk of noncommunicable diseases, have increased in most countries. While many countries have or are planning to incorporate UPF recommendations in their national dietary guidelines, the classification of food processing levels relies on expertise-based manual categorization, which is labor-intensive and time-consuming. Our study utilized transformer-based language models to automate the classification of food processing levels according to the NOVA classification system in the Canada, Argentina, and US national food databases. We showed that fine-tuned language models using the ingredient list text found on food labels as inputs achieved a high overall accuracy (F1 score of 0.979) in predicting the food processing levels of Canadian food products, outperforming traditional machine learning models using structured nutrient data and bag-of-words. Most of the food categories reached a prediction accuracy of 0.98 using a fined-tuned language model, especially for predicting processed foods and ultra-processed foods. Our automation strategy was also effective and generalizable for classifying food products in the Argentina and US databases, providing a cost-effective approach for policymakers to monitor and regulate the UPFs in the global food supply.

This study aims to compare the classification of foods available in the Portuguese market using Nutri-Score and NOVA classifications and to analyse their ability to discriminate the fat, saturated fat, sugar, and salt content of foods. A sample of 2682 food products was collected. The nutritional quality of foods was established using the Nutri-Score, classifying them into five categories (from A to E). The NOVA classification was used to classify foods according to the degree of food processing into unprocessed/minimally processed foods, processed culinary ingredients, processed foods, and ultra-processed foods (UPF). The nutritional content of food products was classified using a Multiple Traffic Light label system. It was observed that 73.7% of UPF were classified as Nutri-Score C, D, and E, 10.1% as Nutri-Score A, and 16.2% as Nutri-Score B. Nutri-Score was positively correlated with NOVA classification (ρ = 0.140, p < 0.001) and with the Multiple Traffic Lights system (ρTotal Fat = 0.572, ρSaturated Fat = 0.668, ρSugar = 0.215, ρSalt = 0.321, p < 0.001). NOVA classification negatively correlated with the Multiple Traffic Lights system for total fat (ρ = -0.064, p < 0.001). Our findings indicate the presence of many UPFs in all Nutri-Score categories. Since food processing and nutritional quality are complementary, both should be considered in labelling.

This study aimed to compare the level of processing (as assessed by the NOVA classification) and the nutritional quality (as assessed by nutrition values, Nutri-Score and NutrInform battery) of breakfast cereals currently on the Italian market. A total of 349 items were found, mostly belonging to the NOVA 4 group (66.5%) and to Nutri-Score C and A (40% and 30%, respectively). The NOVA 4 products showed the highest energy, total fat, saturates, and sugar content per 100 g and had the highest number of items with Nutri-Score C (49%) and D (22%). Conversely, NOVA 1 products had the highest content of fibre and protein, the lowest amounts of sugars and salt, and 82% of them were Nutri-Score A, while few Nutri-Score B and C were found. Differences were attenuated when products were compared for their NutrInform battery, with NOVA 4 items showing only slightly fuller batteries for saturated fats, sugar, and salt than NOVA 1 and NOVA 3 products. Overall, these results suggest that the NOVA classification partially overlaps with systems based on the nutritional quality of foods. The lower nutritional quality of NOVA 4 foods may at least partially explain the association found between the consumption of ultra-processed foods and the risk of chronic diseases.

UNASSIGNED: The most challenging part of diabetes management for a patient with diabetes is selecting a healthy diet. The purpose of this study is to evaluate participants\' knowledge of food labels, to find out the relationship between the type of diabetes mellitus (DM) and knowledge score of food labels, and to explore the barriers that prevent patients from reading food labels.
UNASSIGNED: This observational study was conducted on patients with type 1 or type 2 diabetes using a validated self-administered questionnaire. The study was conducted at diabetes clinics at King Khalid University Hospital and King Abdul-Aziz University Hospital, Riyadh, Saudi Arabia, from November 2019 to February 2020. Data were analyzed using SPSS.
UNASSIGNED: A total of 310 participants were enrolled in this study, of which 50.3% had type 1 DM, and more than half of them were female (51.6%). Patients with type 1 DM had higher mean declarative and applied knowledge scores than those with type 2 DM, regardless of whether they were taking pre meals insulin or not. The highest proportion (39.9%) had difficulty in understanding the content of the nutrition labels, and some of them (37.2%) did not receive any educational session about it. Only 9.5% of the participants did not have any difficulties in reading food labels.
UNASSIGNED: Patients with both types of diabetes tended to have poor total knowledge about food labels and faced difficulties in reading them. Provided educational sessions by primary health care and specialized physician and DM educator about food labels are recommended to help them to choose food properly.

Food allergies have increased in prevalence over the last few decades and continue to grow. Consumption of even trace amounts of common foods can cause a rapid allergic reaction (generally within minutes) which can be mild to severe to even life-threatening. Eating at restaurants poses a risk of allergic reactions for those with food allergies due to inadequate, inconsistent labeling of allergens in foods. Here, we review food labeling rules and practices in the restaurant industry and compare and contrast it with food labeling for prepackaged foods. We review global and United States trends, and provide a brief historical overview. The paper describes the key legal and economic motivations behind restaurant food labeling. Next, we describe novel risk-driven policies and new biotechnologies that have the potential to change food labeling practices worldwide. Finally, we outline desirable federal regulations and voluntary information disclosures that would positively impact the public health aspects of restaurant food labeling and improve the quality of life for people with severe food allergies.

Micronutrient deficiencies represent a major global health issue, with over 2 billion individuals experiencing deficiencies in essential vitamins and minerals. Food labels provide consumers with information regarding the nutritional content of food items and have been identified as a potential tool for improving diets. However, due to governmental regulations and the physical limitations of the labels, food labels often lack comprehensive information about the vitamins and minerals present in foods. As a result, information about most of the micronutrients is absent from existing food labels.
This paper aims to examine the possibility of using machine learning algorithms to predict unreported micronutrients such as vitamin A (retinol), vitamin C, vitamin B1 (thiamin), vitamin B2 (riboflavin), vitamin B3 (niacin), vitamin B6, vitamin B12, vitamin E (alpha-tocopherol), vitamin K, and minerals such as magnesium, zinc, phosphorus, selenium, manganese, and copper from nutrition information provided on existing food labels. If unreported micronutrients can be predicted with acceptable accuracies from existing food labels using machine learning predictive models, such models can be integrated into mobile apps to provide consumers with additional micronutrient information about foods and help them make more informed diet decisions.
Data from the Food and Nutrient Database for Dietary Studies (FNDDS) data set, representing a total of 5624 foods, were used to train a diverse set of machine learning classification and regression algorithms to predict unreported vitamins and minerals from existing food label data. For each model, hyperparameters were adjusted, and the models were evaluated using repeated cross-validation to ensure that the reported results were not subject to overfitting.
According to the results, while predicting the exact quantity of vitamins and minerals is shown to be challenging, with regression R2 varying in a wide range from 0.28 (for magnesium) to 0.92 (for manganese), the classification models can accurately predict the category (\"low,\" \"medium,\" or \"high\") level of all minerals and vitamins with accuracies exceeding 0.80. The highest classification accuracies for specific micronutrients are achieved for vitamin B12 (0.94) and phosphorus (0.94), while the lowest are for vitamin E (0.81) and selenium (0.83).
This study demonstrates the feasibility of predicting unreported micronutrients from existing food labels using machine learning algorithms. The results show that the approach has the potential to significantly improve consumer knowledge about the micronutrient content of the foods they consume. Integrating these predictive models into mobile apps can enhance their accessibility and engagement with consumers. The implications of this research for public health are noteworthy, underscoring the potential of technology to augment consumers\' understanding of the micronutrient content of their diets while also facilitating the tracking of food intake and providing personalized recommendations based on the micronutrient content and individual preferences.

Food categorization and nutrient profiling are labor intensive, time consuming, and costly tasks, given the number of products and labels in large food composition databases and the dynamic food supply.
This study used a pretrained language model and supervised machine learning to automate food category classification and nutrition quality score prediction based on manually coded and validated data, and compared prediction results with models using bag-of-words and structured nutrition facts as inputs for predictions.
Food product information from University of Toronto Food Label Information and Price Database 2017 (n = 17,448) and University of Toronto Food Label Information and Price Database 2020 (n = 74,445) databases were used. Health Canada\'s Table of Reference Amounts (TRA) (24 categories and 172 subcategories) was used for food categorization and the Food Standards of Australia and New Zealand (FSANZ) nutrient profiling system was used for nutrition quality score evaluation. TRA categories and FSANZ scores were manually coded and validated by trained nutrition researchers. A modified pretrained sentence-Bidirectional Encoder Representations from Transformers model was used to encode unstructured text from food labels into lower-dimensional vector representations, followed by supervised machine learning algorithms (i.e., elastic net, k-Nearest Neighbors, and XGBoost) for multiclass classification and regression tasks.
Pretrained language model representations utilized by the XGBoost multiclass classification algorithm reached overall accuracy scores of 0.98 and 0.96 in predicting food TRA major and subcategories, outperforming bag-of-words methods. For FSANZ score prediction, our proposed method reached a similar prediction accuracy (R2: 0.87 and MSE: 14.4) compared with bag-of-words methods (R2: 0.72-0.84; MSE: 30.3-17.6), whereas structured nutrition facts machine learning model performed the best (R2: 0.98; MSE: 2.5). The pretrained language model had a higher generalizable ability on the external test datasets than bag-of-words methods.
Our automation achieved high accuracy in classifying food categories and predicting nutrition quality scores using text information found on food labels. This approach is effective and generalizable in a dynamic food environment, where large amounts of food label data can be obtained from websites.

Japan is one of the countries with the highest life expectancy in the world, and maintaining good health is the key component to extend healthy life expectancy. According to World Health Organization, self-care is the ability to promote health, prevent disease, and maintain health. Food labels play an important role in healthy dietary habits for self-care. Food labels comprise nutrition claims and health claims. In Japan, the nutrition component exhibits the contents of energy, protein, fat, carbohydrates, and salt equivalent, which are mandatory, and saturated fat and dietary fiber, which are recommended. On the other hand, the health portion exhibits health maintenance and health promotion by nutrients/ingredients in foods. Under the Food Labeling Act, foods allowed to display health claims, are specified as \"Foods with Health Claims\" in Japan. The Consumer Affairs Agency reported that most consumers could not utilize food labels, even though the nutrition label serves as a parameter for a healthier food choice. In this regard, front-of-pack labels (FOPLs), are a beneficial tool which encourages people to choose healthier foods, and conduct self-care. However, FOPLs is still unfamiliar in Japan, so we have to investigate which nutrients and which type of FOPLs are the best for Japanese people. In addition to FOPL promotion, education is important to get consumers using food labels for extending their healthy life expectancy.