Submit to Special Issue Submit Abstract to Special Issue Review for Nutrients Propose a Special Issue

Journal Browser

Artificial Intelligence Applications to Public Health Nutrition

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
Published Papers

A special issue of Nutrients (ISSN 2072-6643). This special issue belongs to the section "Nutrition and Public Health".

Deadline for manuscript submissions: 15 July 2024 | Viewed by 9599

Share This Special Issue

Special Issue Editor

Dr. Ruopeng An

E-Mail Website
Guest Editor

Brown School, Washington University, Campus Box 1196, One Brookings Drive, St. Louis, MO 63130, USA
Interests: applications of artificial intelligence and big data analytics in public health; environmental and policy influences on dietary behavior, physical activity, and obesity; social and economic determinants of health
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Data are now available to researchers and practitioners in a way and quantity that has never existed before, presenting unprecedented opportunities for advancing population health research and practices through state-of-the-art data analytics. On the other hand, dealing with extensive, complex, unconventional data (e.g., free text, image, video, and audio) requires revolutionary analytic tools only made available during the past decade. Artificial Intelligence (AI), characterized by machine and deep learning, has become increasingly recognized as an indispensable tool in health management and promotion, with relevant applications expanding from disease outbreak prediction to medical imaging and patient communication to behavioral modification.

Public health nutrition aims to promote overall nutritional health among a population rather than considering one person’s health at a time. In the dawn of the AI era, we dare to ask big questions, such as: How can we apply machine and deep learning technologies to promote a healthy diet at the population level? What barriers and opportunities exist in adopting and adapting AI tools to address global and local nutrition challenges? Could we showcase, through inspirational case studies and pioneering work, the applications of AI to public health nutrition that hold the potential to move the needle?

Arguably, the above questions are far beyond what our Special Issue could address. Still, we would be thrilled if it could help us to move one step closer to our goal of leveraging the power of AI to improve dietary behaviors and nutrition outcomes at the population level. This Special Issue calls for interdisciplinary, empirical research that applies machine or deep learning technologies to address issues in public health nutrition. Priorities will be given to studies that could transform current practices, scale up to serve a large population, and adapt to other settings or geographical regions. The Special Issue emphasizes AI applications; studies on AI theories or tooling without real-world applications and studies without an explicit focus on public health nutrition will not be considered.

Dr. Ruopeng An
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Nutrients is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2900 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

artificial intelligence
machine learning
deep learning
artificial neural network
data science
nutrition
diet
population health
public health

Published Papers (6 papers)

Download All Papers

Editorial

Jump to: Research

2 pages, 182 KiB

Open AccessEditorial

Artificial Intelligence Applications to Public Health Nutrition

by Ruopeng An and Xiaoxin Wang

Nutrients 2023, 15(19), 4285; https://0-doi-org.brum.beds.ac.uk/10.3390/nu15194285 - 08 Oct 2023

Viewed by 1830

Abstract

Public health nutrition occupies a paramount position in the overarching domains of health promotion and disease prevention, setting itself apart from nutritional investigations concentrated at the individual level [...] Full article

(This article belongs to the Special Issue Artificial Intelligence Applications to Public Health Nutrition)

Research

Jump to: Editorial

13 pages, 1166 KiB

Open AccessArticle

The Effectiveness of Artificial Intelligence in Assisting Mothers with Assessing Infant Stool Consistency in a Breastfeeding Cohort Study in China

by Jieshu Wu, Linjing Dong, Yating Sun, Xianfeng Zhao, Junai Gan and Zhixu Wang

Nutrients 2024, 16(6), 855; https://0-doi-org.brum.beds.ac.uk/10.3390/nu16060855 - 15 Mar 2024

Viewed by 798

Abstract

Breastfeeding is widely recognized as the gold standard for infant nutrition, benefitting infants’ gastrointestinal tracts. Stool analysis helps in understanding pediatric gastrointestinal health, but the effectiveness of automated fecal consistency evaluation by parents of breastfeeding infants has not been investigated. Photographs of one-month-old infants’ feces on diapers were taken via a smartphone app and independently categorized by Artificial Intelligence (AI), parents, and researchers. The accuracy of the evaluations of the AI and the parents was assessed and compared. The factors contributing to assessment bias and app user characteristics were also explored. A total of 98 mother–infant pairs contributed 905 fecal images, 94.0% of which were identified as loose feces. AI and standard scores agreed in 95.8% of cases, demonstrating good agreement (intraclass correlation coefficient (ICC) = 0.782, Kendall’s coefficient of concordance W (Kendall’s W) = 0.840, Kendall’s tau = 0.690), whereas only 66.9% of parental scores agreed with standard scores, demonstrating low agreement (ICC = 0.070, Kendall’s W = 0.523, Kendall’s tau = 0.058). The more often a mother had one or more of the following characteristics, unemployment, education level of junior college or below, cesarean section, and risk for postpartum depression (PPD), the more her appraisal tended to be inaccurate (p < 0.05). Each point increase in the Edinburgh Postnatal Depression Scale (EPDS) score increased the deviation by 0.023 points (p < 0.05), which was significant only in employed or cesarean section mothers (p < 0.05). An AI-based stool evaluation service has the potential to assist mothers in assessing infant stool consistency by providing an accurate, automated, and objective assessment, thereby helping to monitor and ensure the well-being of infants. Full article

(This article belongs to the Special Issue Artificial Intelligence Applications to Public Health Nutrition)

► Show Figures

Graphical abstract

12 pages, 1346 KiB

Open AccessArticle

Sentiment Analysis of Tweets on Menu Labeling Regulations in the US

by Yuyi Yang, Nan Lin, Quinlan Batcheller, Qianzi Zhou, Jami Anderson and Ruopeng An

Nutrients 2023, 15(19), 4269; https://0-doi-org.brum.beds.ac.uk/10.3390/nu15194269 - 06 Oct 2023

Viewed by 1283

Abstract

Menu labeling regulations in the United States mandate chain restaurants to display calorie information for standard menu items, intending to facilitate healthy dietary choices and address obesity concerns. For this study, we utilized machine learning techniques to conduct a novel sentiment analysis of public opinions regarding menu labeling regulations, drawing on Twitter data from 2008 to 2022. Tweets were collected through a systematic search strategy and annotated as positive, negative, neutral, or news. Our temporal analysis revealed that tweeting peaked around major policy announcements, with a majority categorized as neutral or news-related. The prevalence of news tweets declined after 2017, as neutral views became more common over time. Deep neural network models like RoBERTa achieved strong performance (92% accuracy) in classifying sentiments. Key predictors of tweet sentiments identified by the random forest model included the author’s followers and tweeting activity. Despite limitations such as Twitter’s demographic biases, our analysis provides unique insights into the evolution of perceptions on the regulations since their inception, including the recent rise in negative sentiment. It underscores social media’s utility for continuously monitoring public attitudes to inform health policy development, execution, and refinement. Full article

(This article belongs to the Special Issue Artificial Intelligence Applications to Public Health Nutrition)

► Show Figures

Figure 1

11 pages, 1744 KiB

Open AccessArticle

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

by Guanlan Hu, Nadia Flexner, María Victoria Tiscornia and Mary R. L’Abbé

Nutrients 2023, 15(19), 4167; https://0-doi-org.brum.beds.ac.uk/10.3390/nu15194167 - 27 Sep 2023

Cited by 2 | Viewed by 2155

Abstract

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. Full article

(This article belongs to the Special Issue Artificial Intelligence Applications to Public Health Nutrition)

► Show Figures

Figure 1

15 pages, 2301 KiB

Open AccessArticle

Machine Learning-Based Prediction of Complications and Prolonged Hospitalization with the GLIM Criteria Combinations Containing Calf Circumference in Elderly Asian Patients

by Shan-Shan Ren, Kai-Wen Zhang, Bo-Wen Chen, Chun Yang, Rong Xiao, Peng-Gao Li and Ming-Wei Zhu

Nutrients 2023, 15(19), 4146; https://0-doi-org.brum.beds.ac.uk/10.3390/nu15194146 - 26 Sep 2023

Viewed by 1037

Abstract

Background and aims: Malnutrition is widely present and influences the prognosis of elderly inpatients, so it is helpful to be able to identify it with a convenient method. However, in the widely accepted criteria for malnutrition, the Global Leadership Initiative on Malnutrition (GLIM), a lot of metrics can be used to define the phenotypic and etiological criteria. To identify muscle mass reduction, anthropometric parameters such as calf circumference (CC) and hand grip strength (HGS) are preferable to other expensive methods in many situations because they are easy and inexpensive to measure, but their applicability needs to be verified in specific clinical scenarios. This study aims to verify the value of CC- and HGS-identified muscle loss in diagnosing malnutrition and predicting in-hospital complications (IHC) and prolonged length of hospital stay (PLOS) in elderly inpatients using machine learning methods. Methods: A sample of 7122 elderly inpatients who were enrolled in a previous multicenter cohort study in China were screened for eligibility for the current study and were then retrospectively diagnosed for malnutrition using 33 GLIM criteria that differ in their combinations of phenotypic and etiological criteria, in which CC or CC+HGS were used to identify muscle mass reduction. The diagnostic consistency with the subjective global assessment (SGA) criteria at admission was evaluated according to Kappa coefficients. The association and the predictive value of the GLIM-defined malnutrition with 30-day IHC and PLOS were evaluated with logistic regression and randomized forest models. Results: In total, 2526 inpatients (average age 74.63 ± 7.12 years) were enrolled in the current study. The prevalence of malnutrition identified by the 33 criteria combinations ranged from 3.3% to 27.2%. The main IHCs was infectious complications (2.5%). The Kappa coefficients ranged from 0.130 to 0.866. Logistic regression revealed that malnutrition was identified by 31 GLIM criteria combinations that were significantly associated with 30-day IHC, and 22 were significantly associated with PLOS. Random forest prediction revealed that GLIM 15 (unconscious weight loss + muscle mass reduction, combined with disease burden/inflammation) performs best in predicting IHC; GLIM 30 (unconscious weight loss + muscle mass reduction + BMI reduction, combined with disease burden/inflammation) performs best in predicting PLOS. Importantly, CC alone performs better than CC+HGS in the criteria combinations for predicting adverse clinical outcomes. Conclusion: Muscle mass reduction defined by a reduced CC performs well in the GLIM criteria combinations for diagnosing malnutrition and predicting IHC and PLOS in elderly Asian inpatients. The applicability of other anthropometric parameters in these applications needs to be further explored. Full article

(This article belongs to the Special Issue Artificial Intelligence Applications to Public Health Nutrition)

► Show Figures

Figure 1

13 pages, 524 KiB

Open AccessArticle

Predicting Cardiovascular Disease Mortality: Leveraging Machine Learning for Comprehensive Assessment of Health and Nutrition Variables

by Agustin Martin-Morales, Masaki Yamamoto, Mai Inoue, Thien Vu, Research Dawadi and Michihiro Araki

Nutrients 2023, 15(18), 3937; https://0-doi-org.brum.beds.ac.uk/10.3390/nu15183937 - 11 Sep 2023

Cited by 2 | Viewed by 1572

Abstract

Cardiovascular disease (CVD) is one of the primary causes of death around the world. This study aimed to identify risk factors associated with CVD mortality using data from the National Health and Nutrition Examination Survey (NHANES). We created three models focusing on dietary data, non-diet-related health data, and a combination of both. Machine learning (ML) models, particularly the random forest algorithm, demonstrated robust consistency across health, nutrition, and mixed categories in predicting death from CVD. Shapley additive explanation (SHAP) values showed age, systolic blood pressure, and several other health factors as crucial variables, while fiber, calcium, and vitamin E, among others, were significant nutritional variables. Our research emphasizes the importance of comprehensive health evaluation and dietary intake in predicting CVD mortality. The inclusion of nutrition variables improved the performance of our models, underscoring the utility of dietary intake in ML-based data analysis. Further investigation using large datasets with recurring dietary recalls is necessary to enhance the effectiveness and interpretability of such models. Full article

(This article belongs to the Special Issue Artificial Intelligence Applications to Public Health Nutrition)

► Show Figures