eNutrition - The next dimension for eHealth?

Use of Digital Tools for the Assessment of Food Consumption in Brazil: A Scoping Review

This is a scoping review on mapping the use of digital tools to assess food consumption in Brazil. Searches were carried out in nine electronic databases (Medline, Lilacs, Scopus, Embase, Web of Science, Science Direct, Ovid, Free Medical Journal and Crossref) to select studies published from October 2020 to December 2023. This review identified forty-eight digital tools in the 94 publications analyzed, the most frequent being web-based technologies (60%) and mobile devices (40%). Among these studies, 55% (n = 52) adopted a population-based approach, while 45% (n = 42) focused on specific regions. The predominant study design observed was cross-sectional (n = 63). A notable trend observed was the increasing frequency of validation studies in recent years. Although the use of digital tools in the assessment of food consumption in Brazil has grown in recent years, studies did not describe the process of creating and validating the tools, which would contribute to the improvement of data quality. Investments that allow the expansion of the use of the internet and mobile devices; the improvement of digital literacy; and the development of open-access tools, especially in the North and Northeast regions, are challenges that require a concerted effort towards providing equal opportunities, fostering encouragement, and delving deeper into the potential of digital tools within studies pertaining to food consumption in Brazil.

Clustering Analysis and Machine Learning algorithms in the prediction of dietary patterns: Cross-sectional results of the Brazilian Longitudinal Study of Adult Health (ELSA-Brasil)

BACKGROUND

Machine learning investigates how computers can automatically learn. This study aimed to predict dietary patterns and compare algorithm performance in making predictions of dietary patterns.

METHODS

We analyzed the data of public employees (n=12,667) participating in the Brazilian Longitudinal Study of Adult Health (ELSA-Brasil). The K-means clustering algorithm and six other classifiers (support vector machines, naïve Bayes, K-nearest neighbors, decision tree, random forest, and xgboost) were used to predict the dietary patterns.

RESULTS

K-means clustering identified two dietary patterns. Cluster 1, labeled the Western pattern, was characterized by a higher energy intake and consumption of refined cereals, beans and other legumes, tubers, pasta, processed and red meats, high-fat milk and dairy products, and sugary beverages; Cluster 2, labeled the Prudent pattern, was characterized by higher intakes of fruit, vegetables, whole cereals, white meats, and milk and reduced-fat milk derivatives. The most important predictors were age, sex, per capita income, education level, and physical activity. The accuracy of the models varied from moderate to good (69-72%).

CONCLUSIONS

The algorithms' performance in dietary pattern prediction was similar, and the models presented may provide support in screener tasks and guide health professionals in the analysis of dietary data. This article is protected by copyright. All rights reserved.

The Age of Artificial Intelligence: Use of Digital Technology in Clinical Nutrition

PURPOSE OF REVIEW

Computing advances over the decades have catalyzed the pervasive integration of digital technology in the medical industry, now followed by similar applications for clinical nutrition. This review discusses the implementation of such technologies for nutrition, ranging from the use of mobile apps and wearable technologies to the development of decision support tools for parenteral nutrition and use of telehealth for remote assessment of nutrition.

RECENT FINDINGS

Mobile applications and wearable technologies have provided opportunities for real-time collection of granular nutrition-related data. Machine learning has allowed for more complex analyses of the increasing volume of data collected. The combination of these tools has also translated into practical clinical applications, such as decision support tools, risk prediction, and diet optimization.

SUMMARY

The state of digital technology for clinical nutrition is still young, although there is much promise for growth and disruption in the future.