Dietary Pattern Extraction Using Natural Language Processing Techniques.

Insu Choi,Jihye Kim,Woo Chang Kim

doi:10.3389/fnut.2022.765794

Abstract

In this study, we observed the changes in dietary patterns among Korean adults in the previous decade. We evaluated dietary intake using 24-h recall data from the fourth (2007–2009) and seventh (2016–2018) Korea National Health and Nutrition Examination Survey. Machine learning-based methodologies were used to extract these dietary patterns. Particularly, we observed three dietary patterns from each survey similar to the traditional and Western dietary patterns in 2007–2009 and 2016–2018, respectively. Our results reveal a considerable increase in the number of Western dietary patterns compared with the previous decade. Thus, our study contributes to the use of novel methods using natural language processing (NLP) techniques for dietary pattern extraction to obtain more useful dietary information, unlike the traditional methodology.

Highlights

The vocabulary that emerged only once in the subsequent cleaning and normalization process through frequency analysis, was removed, because it does not affect the conduct of topic modeling and because it is seen as an outlier
Studies using the fifth Korea National Health and Nutrition Examination Survey (KNHANES) dataset reported the meat and alcohol patterns using a traditional method for dietary pattern extraction [12]
We proposed a novel natural language processing (NLP) for extracting dietary patterns

Summary

Introduction

Diets are affected by interactions between biological, social, economic, and cultural factors [1]. Dietary patterns have rapidly evolved in South Korea due to this country’s early westernization compared with most Asian countries [2]. The transition of dietary patterns should be monitored because it holds an important risk factor for developing chronic diseases. Traditional methods have been employed to show unique dietary patterns or observe changes in dietary patterns over time in Korean populations [3, 4]. Epidemiological studies on dietary pattern extraction using traditional methods have many limitations. Many subjective decisions are included in food grouping for extracting dietary patterns. Obtaining information on particular food items has become difficult due to their broad classification

Objectives

Methods

Results

Discussion

Conclusion