Use and Understanding of Nutrition Labels: Impact of Diet Attachment

Precise nutritional labelling of sliced packaged dry-cured ham using multi-energy X-ray absorptiometry

New consumer demands have increased the need for improved food processing and new value-added products that meet the latest quality standards. Changes in eating habits may lead to a preference for lower sodium products, making accurate labelling and nutritional claims important for the industry. The aim of this work was to study the application of Multi-energy X-ray absorptiometry (MEXA) for the determination of nutritional information in sliced packaged dry-cured ham for the industry. The effect of the acquisition conditions, the analysis approach, fat content and measured area of slices, as well as the potential of this technology for the inclusion of a verified 'salt reduced' nutritional claim, were analyzed in two industrial case studies. Two hundred and ten packets of sliced dry-cured ham were scanned using MEXA equipment. Two regions of interest were selected to study the effect of thickness on the model's precision. Salt content could be predicted with a RMSEP of 0.346% and 0.403% when acquisition conditions were 80 keV and 110 keV respectively. When used by the industry, the classification performance for a 'salt reduced' labelling claim depends on the mean salt content and heterogeneity of the company's production and on the threshold value selected for class definition. However, to support consumers personalized nutrition through precise labelling, implementation of MEXA technology together with labelling system is necessary.

How Much Do Front-Of-Pack Labels Correlate with Food Environmental Impacts?

Nutrient profiling and front-of-pack labeling (FOPL) have been developed to categorize food products as more or less healthy based on their nutrient content and to easily communicate this information to consumers. The goal is to change individual food choices toward a healthier diet. Since global climate change has recently become an urgent matter, this paper also aims to investigate the correlations between different food health scales, including some FOPLs currently adopted by one or more countries, and several sustainability indicators. For this purpose, a food sustainability composite index has been developed to summarize environmental indicators and compare food scales. Results indicate, as expected, that well-known healthy and sustainable diets are strongly correlated with both environmental indicators and the composite index, while FOPLs based on portions or on 100 g show moderate and weak correlation values, respectively. Within-category analysis has not found any associations that explain these results. Hence, 100 g standard, on which FOPLs are usually developed, seems not to be the ideal basis for developing a label that aspires to communicate healthiness and sustainability in a unique format, as required by the need for simple messaging. On the contrary, FOPLs based on portions appear to be more likely to achieve this goal.

Status of nutrition labeling knowledge, attitude, and practice (KAP) of residents in the community and structural equation modeling analysis

Objective

Unhealthy foods were a major contributor to the occurrence of chronic non-communicable diseases. The promotion of nutrition labeling in the community can effectively help residents to choose healthy foods, which plays an important role in the prevention of chronic diseases. However, the public awareness of this measure is not clear. Our study used a structural equation model based on the KAP theory to analyze the interaction mechanisms among knowledge, attitude, and practice and aimed to evaluate the relationships among nutrition knowledge, attitude, and practice of residents, which can provide the basis of policy formulation for nutrition education and behavior intervention.

Methods

We carried out a cross-sectional study from May 2022 to July 2022 in the "Community Health Service Center", and each "Community Service Station" in Yinchuan use a self-designed questionnaire and convenience sampling to evaluate resident nutrition labeling KAP status. This study adopted the structural equation modeling approach to analyze a survey of Chinese individuals through the cognitive processing model, interrelated nutrition knowledge, nutrition label knowledge, attitude, and practice.

Results

According to the principle of sample size estimation, a total of 636 individuals were investigated, with the ratio of male to female being 1:1.2. The average score of community residents' nutrition knowledge was 7.48 ± 3.24, and the passing rate was 19.4%. Most residents had a positive attitude toward nutrition labeling, but the awareness rate was only 32.7% and the utilization rate was 38.5%. Univariate analysis showed that women had higher knowledge scores than men (p < 0.05), and young people had higher scores than older adults (p < 0.05), and the difference was significant. Based on the KAP structural equation model (SEM), residents' nutrition knowledge will directly affect their attitude toward nutrition labeling. Attitude played a greater role as an indirect effect between knowledge and behavior, while trust limits residents' practice of nutrition labeling and then affects their practice. It could be explained that nutrition knowledge was the prerequisite for label reading behavior, and attitude was the intermediary effect.

Conclusion

The nutrition knowledge and nutrition labeling knowledge of respondents hardly directly support the practice of nutrition labeling, but it can influence the use behavior by forming a positive attitude. The KAP model is suitable for explaining residents' use of nutrition labeling in the region. Future research should focus on better understanding the motivations of residents to use nutrition labeling and the opportunity to use nutrition labeling in real-life shopping settings.

Predicting Unreported Micronutrients from Food Labels: A Machine Learning Approach (Preprint)

BACKGROUND

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.

OBJECTIVE

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.

METHODS

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.

RESULTS

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).

CONCLUSIONS

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.