A Machine Learning Approach to Predict the Added-Sugar Content of Packaged Foods

An eco-friendly approach for analysing sugars, minerals, and colour in brown sugar using digital image processing and machine learning

Brown sugar is a natural sweetener obtained by thermal processing, with interesting nutritional characteristics. However, it has significant sensory variability, which directly affects product quality and consumer choice. Therefore, developing rapid methods for its quality control is desirable. This work proposes a fast, environmentally friendly, and accurate method for the simultaneous analysis of sucrose, reducing sugars, minerals and ICUMSA colour in brown sugar, using an innovative strategy that combines digital image processing acquired by smartphone cell with machine learning. Data extracted from the digital images, as well as experimentally determined contents of the physicochemical characteristics and elemental profile were the variables adopted for building predictive regression models by applying the kNN algorithm. The models achieved the highest predictive capacity for the Ca, ICUMSA colour, Fe and Zn, with coefficients of determination (R2) ≥ 92.33 %. Lower R2 values were observed for sucrose (81.16 %), reducing sugars (85.67 %), Mn (83.36 %) and Mg (86.97 %). Low data dispersion was found for all the predictive models generated (RMSE < 0.235). The AGREE Metric assessed the green profile and determined that the proposed approach is superior in relation to conventional methods because it avoids the use of solvents and toxic reagents, consumes minimal energy, produces no toxic waste, and is safer for analysts. The combination of digital image processing (DIP) and the kNN algorithm provides a fast, non-invasive and sustainable analytical approach. It streamlines and improves quality control of brown sugar, enabling the production of sweeteners that meet consumer demands and industry standards.

Shallow and deep learning classifiers in medical image analysis

An increasingly strong connection between artificial intelligence and medicine has enabled the development of predictive models capable of supporting physicians' decision-making. Artificial intelligence encompasses much more than machine learning, which nevertheless is its most cited and used sub-branch in the last decade. Since most clinical problems can be modeled through machine learning classifiers, it is essential to discuss their main elements. This review aims to give primary educational insights on the most accessible and widely employed classifiers in radiology field, distinguishing between "shallow" learning (i.e., traditional machine learning) algorithms, including support vector machines, random forest and XGBoost, and "deep" learning architectures including convolutional neural networks and vision transformers. In addition, the paper outlines the key steps for classifiers training and highlights the differences between the most common algorithms and architectures. Although the choice of an algorithm depends on the task and dataset dealing with, general guidelines for classifier selection are proposed in relation to task analysis, dataset size, explainability requirements, and available computing resources. Considering the enormous interest in these innovative models and architectures, the problem of machine learning algorithms interpretability is finally discussed, providing a future perspective on trustworthy artificial intelligence.Relevance statement The growing synergy between artificial intelligence and medicine fosters predictive models aiding physicians. Machine learning classifiers, from shallow learning to deep learning, are offering crucial insights for the development of clinical decision support systems in healthcare. Explainability is a key feature of models that leads systems toward integration into clinical practice. Key points • Training a shallow classifier requires extracting disease-related features from region of interests (e.g., radiomics).• Deep classifiers implement automatic feature extraction and classification.• The classifier selection is based on data and computational resources availability, task, and explanation needs.

Machine learning accurately predicts food exchange list and the exchangeable portion

Introduction

Food Exchange Lists (FELs) are a user-friendly tool developed to help individuals aid healthy eating habits and follow a specific diet plan. Given the rapidly increasing number of new products or access to new foods, one of the biggest challenges for FELs is being outdated. Supervised machine learning algorithms could be a tool that facilitates this process and allows for updated FELs-the present study aimed to generate an algorithm to predict food classification and calculate the equivalent portion.

Methods

Data mining techniques were used to generate the algorithm, which consists of processing and analyzing the information to find patterns, trends, or repetitive rules that explain the behavior of the data in a food database after performing this task. It was decided to approach the problem from a vector formulation (through 9 nutrient dimensions) that led to proposals for classifiers such as Spherical K-Means (SKM), and by developing this idea, it was possible to smooth the limits of the classifier with the help of a Multilayer Perceptron (MLP) which were compared with two other algorithms of machine learning, these being Random Forest and XGBoost.

Results

The algorithm proposed in this study could classify and calculate the equivalent portion of a single or a list of foods. The algorithm allows the categorization of more than one thousand foods with a confidence level of 97% at the first three places. Also, the algorithm indicates which foods exceed the limits established in sodium, sugar, and/or fat content and show their equivalents.

Discussion

Accurate and robust FELs could improve implementation and adherence to the recommended diet. Compared with manual categorization and calculation, machine learning approaches have several advantages. Machine learning reduces the time needed for manual food categorization and equivalent portion calculation of many food products. Since it is possible to access food composition databases of various populations, our algorithm could be adapted and applied in other databases, offering an even greater diversity of regional products and foods. In conclusion, machine learning is a promising method for automation in generating FELs. This study provides evidence of a large-scale, accurate real-time processing algorithm that can be useful for designing meal plans tailored to the foods consumed by the population. Our model allowed us not only to distinguish and classify foods within a group or subgroup but also to perform the calculation of an equivalent food. As a neural network, this model could be trained with other food bases and thus improve its predictive capacity. Although the performance of the SKM model was lower compared to other types of classifiers, our model allows selecting an equivalent food not from a group previously classified by machine learning but with a fully interpretable algorithm such as cosine similarity for comparing food.

Natural language processing and machine learning approaches for food categorization and nutrition quality prediction compared with traditional methods

BACKGROUND

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.

OBJECTIVES

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.

METHODS

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.

RESULTS

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.

CONCLUSIONS

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.

Enabling Informed Decision Making in the Absence of Detailed Nutrition Labels: A Model to Estimate the Added Sugar Content of Foods

Obesity and diabetes have emerged as an increasing threat to public health, and the consumption of added sugar can contribute to their development. Though nutritional content information can positively influence consumption behavior, added sugar is not currently required to be disclosed in all countries. However, a growing proportion of the world's population has access to mobile devices, which allow for the development of digital solutions to support health-related decisions and behaviors. To test whether advances in computational science can be leveraged to develop an accurate and scalable model to estimate the added sugar content of foods based on their nutrient profile, we collected comprehensive nutritional information, including information on added sugar content, for 69,769 foods. Eighty percent of this data was used to train a gradient boosted tree model to estimate added sugar content, while 20% of it was held out to assess the predictive accuracy of the model. The performance of the resulting model showed 93.25% explained variance per default portion size (84.32% per 100 kcal). The mean absolute error of the estimate was 0.84 g per default portion size (0.81 g per 100 kcal). This model can therefore be used to deliver accurate estimates of added sugar through digital devices in countries where the information is not disclosed on packaged foods, thus enabling consumers to be aware of the added sugar content of a wide variety of foods.

Development of the Food Label Information Program: A Comprehensive Canadian Branded Food Composition Database

Objectives

Traditional methods for creating food composition databases struggle to cope with the large number of products and the rapid pace of turnover in the food supply. This paper introduces Food Label Information Program (FLIP), a big data approach to the evaluation of the Canadian food supply and presents the latest methods used in the development of this database.

Methods

The Food Label Information Program (FLIP) is a database of Canadian food and beverage package labels by brand name. The latest iteration of the FLIP, FLIP 2020, was developed using website “scraping” to collect food labeling information (e.g., nutritional composition, price, product images, ingredients, brand, etc.) on all foods and beverages available on seven major Canadian e-grocery retailer websites between May 2020 and February 2021.

Results

The University of Toronto's Food Label Information Program (FLIP) 2020 was developed in three phases: Phase 1, database development and enhancements; Phase 2, data capture and management of food products and nutrition information; Phase 3, data processing and food categorizing. A total of 74,445 products available on websites of seven retailers and 2 location-specific duplicate retailers were collected for FLIP 2020. Of 57,006 food and beverage products available on seven retailers, nutritional composition data were available for about 60% of the products and ingredients were available for about 45%. Data for energy, protein, carbohydrate, fat, sugar, sodium and saturated fat were present for 54–65% of the products, while fiber information was available for 37%. Food products were classified under multiple categorization systems, including Health Canada's Table of Reference Amounts, Health Canada's sodium categories for guiding benchmark sodium levels, sugar-focused categories and categories specific to various global nutrient profiling models.

Conclusions

FLIP is a powerful tool for evaluating and monitoring the Canadian food supply environment. The comprehensive sampling and granularity of collection provides power for revealing analyses of the relationship between nutritional quality and marketing of branded foods, timely observation of product reformulation and other changes to the Canadian food supply.