Using machine learning models to predict the quality of plant-based foods

Tachie, Christabel Y.E.; Aryee, Alberta N. A.

doi:10.1016/j.crfs.2023.100544

Cited by 7 publications

(6 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This may be attributed to the data distribution, with MUFA achieving the best scores across all the models. As variables whose distribution is closer to normal, MUFA had the highest R 2 values compared to the other FA classes (Tables 1 and 3), with corresponding lower MSE, RMSE, and MAE rates [29,53].…”

Section: Resultsmentioning

confidence: 94%

“…The selection of ML algorithms depends on the research problem, the number of variables, and the model that best suits it [25]. For example, ML algorithms have been used to authenticate food using specific markers analyzed in nutritional studies to predict the association between obesity and demographics (age, body mass index, gender) [26], to distinguish between products based on their species, geographical origin [27], and production method [28], and to predict the quality of plant-based foods [29].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Approaches for Predicting Fatty Acid Classes in Popular US Snacks Using NHANES Data

Tachie,

Obiri-Ananey,

Tawiah

et al. 2023

Nutrients

Self Cite

View full text Add to dashboard Cite

In the US, people frequently snack between meals, consuming calorie-dense foods including baked goods (cakes), sweets, and desserts (ice cream) high in lipids, salt, and sugar. Monounsaturated fatty acid (MUFA) and polyunsaturated fatty acid (PUFA) are reasonably healthy; however, excessive consumption of food high in saturated fatty acid (SFA) has been related to an elevated risk of cardiovascular diseases. The National Health and Nutrition Survey (NHANES) uses a 24 h recall to collect information on people’s food habits in the US. The complexity of the NHANES data necessitates using machine learning (ML) methods, a branch of data science that uses algorithms to collect large, unstructured, and structured data sets and identify correlations between the data variables. This study focused on determining the ability of ML regression models including artificial neural networks (ANNs), decision trees (DTs), k-nearest neighbors (KNNs), and support vector machines (SVMs) to assess the variability in total fat content concerning the classes (SFA, MUFA, and PUFA) of US-consumed snacks between 2017 and 2018. KNNs and DTs predicted SFA, MUFA, and PUFA with mean squared error (MSE) of 0.707, 0.489, 0.612, and 1.172, 0.846, 0.738, respectively. SVMs failed to predict the fatty acids accurately; however, ANNs performed satisfactorily. Using ensemble methods, DTs (10.635, 5.120, 7.075) showed higher error values for MSE than linear regression (LiR) (9.086, 3.698, 5.820) for SFA, MUFA, and PUFA prediction, respectively. R2 score ranged between −0.541 to 0.983 and 0.390 to 0.751 for models one and two, respectively. Extreme gradient boost (XGR), Light gradient boost (LightGBM), and random forest (RF) performed better than LiR, with RF having the lowest score for MSE in predicting all the fatty acid classes.

show abstract

Section: Resultsmentioning

confidence: 94%

Section: Introductionmentioning

confidence: 99%

Machine Learning Approaches for Predicting Fatty Acid Classes in Popular US Snacks Using NHANES Data

Tachie,

Obiri-Ananey,

Tawiah

et al. 2023

Nutrients

Self Cite

View full text Add to dashboard Cite

show abstract

“…Advances in high-throughput phenotyping and non-destructive phenotyping, including hyperspectral imaging, Fourier transform near-infrared imaging, and micro-computed tomography imaging, offer efficient means of assessing nutritional components in chickpea ( Hacisalihoglu and Armstrong, 2023 ). Emerging approaches like artificial intelligence and machine learning tools that use convolutional and deep neural networks could predict nutritional quality and the role of novel genes/pathways associated with various nutritional and anti-nutritional components in chickpea ( Tachie et al., 2023 ). By integrating these innovative breeding tools into chickpea breeding programs, researchers can accelerate the development of nutritionally enhanced varieties, contributing to efforts to combat hunger and improve food security worldwide.…”

Section: Innovative Breeding Tools For Improving Nutritional Componentsmentioning

confidence: 99%

Unlocking the nutritional potential of chickpea: strategies for biofortification and enhanced multinutrient quality

Jha,

Nayyar,

Thudi

et al. 2024

Front. Plant Sci.

View full text Add to dashboard Cite

Chickpea (Cicer arietinum L.) is a vital grain legume, offering an excellent balance of protein, carbohydrates, fats, fiber, essential micronutrients, and vitamins that can contribute to addressing the global population’s increasing food and nutritional demands. Chickpea protein offers a balanced source of amino acids with high bioavailability. Moreover, due to its balanced nutrients and affordable price, chickpea is an excellent alternative to animal protein, offering a formidable tool for combating hidden hunger and malnutrition, particularly prevalent in low-income countries. This review examines chickpea’s nutritional profile, encompassing protein, amino acids, carbohydrates, fatty acids, micronutrients, vitamins, antioxidant properties, and bioactive compounds of significance in health and pharmaceutical domains. Emphasis is placed on incorporating chickpeas into diets for their myriad health benefits and nutritional richness, aimed at enhancing human protein and micronutrient nutrition. We discuss advances in plant breeding and genomics that have facilitated the discovery of diverse genotypes and key genomic variants/regions/quantitative trait loci contributing to enhanced macro- and micronutrient contents and other quality parameters. Furthermore, we explore the potential of innovative breeding tools such as CRISPR/Cas9 in enhancing chickpea’s nutritional profile. Envisioning chickpea as a nutritionally smart crop, we endeavor to safeguard food security, combat hunger and malnutrition, and promote dietary diversity within sustainable agrifood systems.

show abstract

“…However, the acceptance of reduced meat consumption and meat replacement with alternative proteins is still generally low in western countries [34][35][36][37]. Consumers need to recognize the importance of adopting plant-based food products to support campaigns advocating reduced meat consumption by animal rights/welfare organizations and address increased greenhouse gas emissions detrimental to the environment caused by livestock farming [38].Perspectives on consumer practices related to the use of plant-based substitutes in obtaining meat analogs are crucial/important, first of all, because nutritional analogs with improved nutritional status and high biological value can be produced. This aligns with the promotion of a healthy lifestyle, the preservation of animal life, and the enhancement of environmental sustainability in the context of a sustainable circular bioeconomy [39].…”

Section: Introductionmentioning

confidence: 99%

Use of Vegetable-Derived Proteins for New Food Products

Mazur,

Bulgaru,

Celac

et al. 2024

J. Eng. Sci.

View full text Add to dashboard Cite

Nowadays there is a high concern with newly-identified protein sources to substitute all kinds of proteins derived from animals. The food industry faces a challenge to produce quality food products that can feed more than nine billion people by 2050, upholding the principles of a sustainable and environmentally affordable way. This idea can be supported by the use of legumes that stand out with appreciable protein content, rich in essential amino acids that increase the foaming and emulsifying properties as well as the dietary fiber content. In recent years, in order to solve environmental and social problems and to diversify food products to cover different nutritional types, proteins of plant origin are used to replace those of animal origin. The present work described a review about emerging alternative proteins for nutrition which focuses on its properties and characteristics.The work analyzes the influence of alternative proteins sources on the food products'sustainability.

show abstract

Using machine learning models to predict the quality of plant-based foods

Cited by 7 publications

References 14 publications

Machine Learning Approaches for Predicting Fatty Acid Classes in Popular US Snacks Using NHANES Data

Machine Learning Approaches for Predicting Fatty Acid Classes in Popular US Snacks Using NHANES Data

Unlocking the nutritional potential of chickpea: strategies for biofortification and enhanced multinutrient quality

Use of Vegetable-Derived Proteins for New Food Products

Contact Info

Product

Resources

About