Machine learning prediction of the degree of food processing

Artificial intelligence-based prediction of the rheological properties of hydrocolloids for plant-based meat analogues

BACKGROUND

Methylcellulose has been applied as a primary binding agent to control the quality attributes of plant-based meat analogues. H owever, a great deal of effort has been made to search for hydrocolloids to replace methylcellulose because of increasing awareness of clean labels. In this study, a machine learning framework was proposed in order to describe and predict the flow behavior of six hydrocolloid solutions, and the predicted viscosities were correlated with the textural features of their corresponding plant-based meat analogues.

RESULTS

Different shear-thinning and Newtonian behaviors were observed depending on the type of hydrocolloid and the shear rate. Methylcellulose exhibited an increasing viscosity pattern with increasing temperature, compared to the other hydrocolloids. The machine learning algorithms (random forest and multilayer perceptron models) showed a better viscosity fitting performance than the constitutive equations (power law and Cross models). In addition, three hyperparameters of the multilayer perceptron model (optimizer, learning rate, and the number of hidden layers) were tuned using the Bayesian optimization algorithm.

CONCLUSION

The optimized multilayer perceptron model exhibited superior performance in viscosity prediction (R2 = 0.9944-0.9961/RMSE = 0.0545-0.0708). Furthermore, the machine learning-predicted viscosities overall showed similar patterns to the textural parameters of the meat analogues. © 2024 Society of Chemical Industry.

GroceryDB: Prevalence of Processed Food in Grocery Stores

The offering of grocery stores is a strong driver of consumer decisions, shaping their diet and long-term health. While highly processed food like packaged products, processed meat, and sweetened soft drinks have been increasingly associated with unhealthy diet, information on the degree of processing characterizing an item in a store is not straightforward to obtain, limiting the ability of individuals to make informed choices. Here we introduce GroceryDB, a database with over 50,000 food items sold by Walmart, Target, and Wholefoods, unveiling how big data can be harnessed to empower consumers and policymakers with systematic access to the degree of processing of the foods they select, and the potential alternatives in the surrounding food environment. The wealth of data collected on ingredient lists and nutrition facts allows a large scale analysis of ingredient patterns and degree of processing stratified by store, food category, and price range. We find that the nutritional choices of the consumers, translated as the degree of food processing, strongly depend on the food categories and grocery stores. Moreover, the data allows us to quantify the individual contribution of over 1,000 ingredients to ultra-processing. GroceryDB and the associated http://TrueFood.Tech/ website make this information accessible, guiding consumers toward less processed food choices while assisting policymakers in reforming the food supply.

Associations of parental preconception and maternal pregnancy urinary phthalate biomarker and bisphenol-a concentrations with child eating behaviors

BACKGROUND

Eating behaviors are controlled by the neuroendocrine system. Whether endocrine disrupting chemicals have the potential to affect eating behaviors has not been widely studied in humans. We investigated whether maternal and paternal preconception and maternal pregnancy urinary phthalate biomarker and bisphenol-A (BPA) concentrations were associated with children's eating behaviors.

METHODS

We used data from mother-father-child triads in the Preconception Environmental exposure And Childhood health Effects (PEACE) Study, an ongoing prospective cohort study of children aged 6-13 years whose parent(s) previously enrolled in a fertility clinic-based prospective preconception study. We quantified urinary concentrations of 11 phthalate metabolites and BPA in parents' urine samples collected preconceptionally and during pregnancy. Parents rated children's eating behavior using the Child Eating Behavior Questionnaire (CEBQ). Using multivariable linear regression, accounting for correlation among twins, we estimated covariate-adjusted associations of urinary phthalate biomarkers and BPA concentrations with CEBQ subscale scores.

RESULTS

This analysis included 195 children (30 sets of twins), 160 mothers and 97 fathers; children were predominantly non-Hispanic white (84%) and 53% were male. Paternal and maternal preconception monobenzyl phthalate (MBzP) concentrations and maternal preconception mono-n-butyl phthalate (MnBP) were positively associated with emotional overeating, food responsiveness, and desire to drink scores in children (β's= 0.11 [95% CI: 0.01, 0.20]-0.21 [95% CI: 0.10, 0.31] per loge unit increase in phthalate biomarker concentration). Paternal preconception BPA concentrations were inversely associated with scores on food approaching scales. Maternal pregnancy MnBP, mono-isobutyl phthalate (MiBP) and MBzP concentrations were associated with increased emotional undereating scores. Maternal pregnancy monocarboxy-isononyl phthalate concentrations were related to decreased food avoiding subscale scores.

CONCLUSIONS

In this cohort, higher maternal and paternal preconception urinary concentrations of some phthalate biomarkers were associated with increased food approaching behavior scores and decreased food avoiding behavior scores, which could lead to increased adiposity in children.

Ultra-Processed Foods-Dietary Foe or Potential Ally?

The prevalence of non-communicable diseases (NCDs) has steadily increased in the United States. Health experts attribute the increasing prevalence of NCDs, in part, to the consumption of ultra-processed foods (UPFs) based on epidemiological observations. However, no definitive evidence of causality has been established. Consequently, there is an ongoing debate over whether adverse health outcomes may be due to the low nutrient density per kilocalorie, the processing techniques used during the production of UPFs, taste preference-driven overconsumption of calories, or unidentified factors. Recognizing that "the science is not settled," we propose an investigative process in this narrative review to move the field beyond current controversies and potentially identify the basis of causality. Since many consumers depend on UPFs due to their shelf stability, affordability, availability, ease of use, and safety from pathogens, we also suggest a paradigm for guiding both the formulation of UPFs by food designers and the selection of UPFs by consumers.

Ultra-processed Food and Obesity: What Is the Evidence?

PURPOSE OF REVIEW

Obesity is a growing global healthcare concern. A proposed driver is the recent increase in ultra-processed food (UPF) intake. However, disagreement surrounds the concept of UPF, the strength of evidence, and suggested mechanisms. Therefore, this review aimed to critically appraise the evidence on UPF and obesity.

RECENT FINDINGS

Observational studies demonstrate positive associations between UPF intake, weight gain, and overweight/obesity, more clearly in adults than children/adolescents. This is supported by high-quality clinical data. Several mechanisms are proposed, but current understanding is inconclusive. Greater UPF consumption has been a key driver of obesity. There is a need to change the obesogenic environment to support individuals to reduce their UPF intake. The UPF concept is a novel approach that is not explained with existing nutrient- and food-based frameworks. Critical analysis of methodologies provides confidence, but future observational and experimental research outputs with greater methodological rigor will strengthen findings, which are outlined.

Integrative deep learning framework predicts lipidomics-based investigation of preservatives on meat nutritional biomarkers and metabolic pathways

Preservatives are added as antimicrobial agents to extend the shelf life of meat. Adding preservatives to meat products can affect their flavor and nutrition. This review clarifies the effects of preservatives on metabolic pathways and network molecular transformations in meat products based on lipidomics, metabolomics and proteomics analyses. Preservatives change the nutrient content of meat products via altering ionic strength and pH to influence enzyme activity. Ionic strength in salt triggers muscle triglyceride hydrolysis by causing phosphorylation and lipid droplet splitting in adipose tissue hormone-sensitive lipase and triglyceride lipase. DisoLipPred exploiting deep recurrent networks and transfer learning can predict the lipid binding trend of each amino acid in the disordered region of input protein sequences, which could provide omics analyses of biomarkers metabolic pathways in meat products. While conventional meat quality assessment tools are unable to elucidate the intrinsic mechanisms and pathways of variables in the influences of preservatives on the quality of meat products, the promising application of omics techniques in food analysis and discovery through multimodal learning prediction algorithms of neural networks (e.g., deep neural network, convolutional neural network, artificial neural network) will drive the meat industry to develop new strategies for food spoilage prevention and control.

Toward Advancing Precision Environmental Health: Developing a Customized Exposure Burden Score to PFAS Mixtures to Enable Equitable Comparisons Across Population Subgroups, Using Mixture Item Response Theory

Quantifying a person's cumulative exposure burden to per- and polyfluoroalkyl substances (PFAS) mixtures is important for risk assessment, biomonitoring, and reporting of results to participants. However, different people may be exposed to different sets of PFASs due to heterogeneity in the exposure sources and patterns. Applying a single measurement model for the entire population (e.g., by summing concentrations of all PFAS analytes) assumes that each PFAS analyte is equally informative to PFAS exposure burden for all individuals. This assumption may not hold if PFAS exposure sources systematically differ within the population. However, the sociodemographic, dietary, and behavioral characteristics that underlie systematic exposure differences may not be known, or may be due to a combination of these factors. Therefore, we used mixture item response theory, an unsupervised psychometrics and data science method, to develop a customized PFAS exposure burden scoring algorithm. This scoring algorithm ensures that PFAS burden scores can be equitably compared across population subgroups. We applied our methods to PFAS biomonitoring data from the United States National Health and Nutrition Examination Survey (2013-2018). Using mixture item response theory, we found that participants with higher household incomes had higher PFAS burden scores. Asian Americans had significantly higher PFAS burden compared with non-Hispanic Whites and other race/ethnicity groups. However, some disparities were masked when using summed PFAS concentrations as the exposure metric. This work demonstrates that our summary PFAS burden metric, accounting for sources of exposure variation, may be a more fair and informative estimate of PFAS exposure.

Perspective: A Research Roadmap about Ultra-Processed Foods and Human Health for the United States Food System: Proceedings from an Interdisciplinary, Multi-Stakeholder Workshop

Our objective was to convene interdisciplinary experts from government, academia, and industry to develop a Research Roadmap to identify research priorities about processed food intake and risk for obesity and cardiometabolic diseases (CMD) among United States populations. We convened attendees at various career stages with diverse viewpoints in the field. We held a "Food Processing Primer" to build foundational knowledge of how and why foods are processed, followed by presentations about how processed foods may affect energy intake, obesity, and CMD risk. Breakout groups discussed potential mechanistic and confounding explanations for associations between processed foods and obesity and CMD risk. Facilitators created research questions (RQs) based on key themes from discussions. Different breakout groups convened to discuss what is known and unknown for each RQ and to develop sub-RQs to address gaps. Workshop attendees focused on ultra-processed foods (UPFs; Nova Group 4) because the preponderance of evidence is based on this classification system. Yet, heterogeneity and subjectivity in UPF classification was a challenge for RQ development. The 6 RQs were: 1) What objective methods or measures could further categorize UPFs, considering food processing, formulation, and the interaction of the two? 2) How can exposure assessment of UPF intake be improved? 3) Does UPF intake influence risk for obesity or CMDs, independent of diet quality? 4) What, if any, attributes of UPFs influence ingestive behavior and contribute to excess energy intake? 5) What, if any, attributes of UPFs contribute to clinically meaningful metabolic responses? 6) What, if any, external environmental factors lead people to consume high amounts of UPFs? Uncertainty and complexity around UPF intake warrant further complementary and interdisciplinary causal, mechanistic, and methodological research related to obesity and CMD risk to understand the utility of applying classification by degree of processing to foods in the United States.

Accelerating the Classification of NOVA Food Processing Levels Using a Fine-Tuned Language Model: A Multi-Country Study

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.

The Role of Agricultural Systems in Teaching Kitchens: An Integrative Review and Thoughts for the Future

Diet-related chronic disease is a public health epidemic in the United States. Concurrently, conventional agricultural and food production methods deplete the nutritional content of many foods, sever connections between people and the origin of their food, and play a significant role in climate change. Paradoxically, despite an abundance of available food in the US, many households are unable to afford or attain a healthful diet. The linkages between agriculture, health, and nutrition are undeniable, yet conventional agriculture and healthcare systems tend to operate in silos, compounding these pressing challenges. Operating teaching kitchens in collaboration with local agriculture, including farms, community gardens, vertical farms, and urban agriculture, has the potential to catalyze a movement that emphasizes the role of the food system in promoting human and planetary health, building resilient communities, and encouraging cross-disciplinary collaboration. This paper reviews the current state of agricultural systems, food is medicine, consumer behavior, and the roles within these sectors. This is followed by a series of case studies that fill the gaps between TKs and agriculture. The authors summarize opportunities to combine the knowledge and resources of teaching kitchens and agriculture programs, as well as challenges that may arise along the way.

Experiential Culinary, Nutrition and Food Systems Education Improves Knowledge and Confidence in Future Health Professionals

The food system plays a crucial role in the relationship between environmental, population and individual health. While leading healthcare and environmental organizations call for urgent action to address climate-planetary-human health crises, it is often challenging for healthcare organizations to respond at a systems level to these concerns. Additionally, there is little consensus and limited research exploring how future health professionals should be trained in order to work at both the individual and systems level to address or prevent the negative health impacts related to the current food system. The intervention of a 6-week, hands-on cooking and nutrition course for graduate health professional students which examines these intersections and equips students with clinically applicable skills was examined using matched pre- and post-course surveys and thematic analysis of reflective assignments. Results indicate improved knowledge and confidence in areas including understanding the food system, guiding patients through dietary change, working interprofessionally, and applying basic nutrition concepts to clinical practice.

An integrative analytical framework to identify healthy, impactful, and equitable foods: a case study on 100% orange juice

To identify healthy, impactful, and equitable foods, we combined health scores from six diverse nutrient profiling systems (NPS) into a meta-framework (meta-NPS) and paired this with dietary guideline adherence assessment via multilevel regression and poststratification. In a case-study format, a commonly debated beverage formulation - 100% orange juice (OJ) - was chosen to showcase the utility and depth of our framework, systematically scoring high across multiple food systems (i.e. a Meta-Score percentile = 93rd and Stability percentile = 75th) and leading to an expected increase of US dietary fruit guideline adherence by ∼10%. Moreover, the increased adherence varies across the 300 sociodemographic strata, with the benefit patterns being sensitive to absolute or relative quantification of the difference of adherence affected by OJ. In sum, the adaptable, integrative framework we established deepens the science of nutrient profiling and dietary guideline adherence assessment while shedding light on the nuances of defining equitable health effects.

Physician-Chef-Dietitian Partnerships for Evidence-Based Dietary Approaches to Tackling Chronic Disease: The Case for Culinary Medicine in Teaching Kitchens

Since the middle of the 20th century, the American food environment has become increasingly ultra-processed. As a result, the prevalence of chronic, diet-related disease in the United States has skyrocketed. Meanwhile, physicians are still poorly trained in nutrition. A recent innovation that aims to address this is "culinary medicine" programming taught by teams of physicians, chefs, and registered dietitian nutritionists. Culinary medicine is an evidence-based, interprofessional field of medicine that combines culinary arts, nutrition science, and medical education to prevent and treat diet-related disease. It employs hands-on learning through healthy cooking and is typically taught in a teaching kitchen, either in-person or virtually. It can be dosed either as a patient care intervention or as experiential nutrition education for students, medical trainees, and healthcare professionals. Culinary medicine programs are effective, financially feasible, and well-received. As a result, healthcare systems and medical education programs are increasingly incorporating culinary medicine, teaching kitchens, and interprofessional nutrition education into their patient care and training models.

Nutritional redundancy in the human diet and its application in phenotype association studies

Studying human dietary intake may help us identify effective measures to treat or prevent many chronic diseases whose natural histories are influenced by nutritional factors. Here, by examining five cohorts with dietary intake data collected on different time scales, we show that the food intake profile varies substantially across individuals and over time, while the nutritional intake profile appears fairly stable. We refer to this phenomenon as 'nutritional redundancy' and attribute it to the nested structure of the food-nutrient network. This network enables us to quantify the level of nutritional redundancy for each diet assessment of any individual. Interestingly, this nutritional redundancy measure does not strongly correlate with any classical healthy diet scores, but its performance in predicting healthy aging shows comparable strength. Moreover, after adjusting for age, we find that a high nutritional redundancy is associated with lower risks of cardiovascular disease and type 2 diabetes.