Classification and prediction of the effects of nutritional intake on diabetes mellitus using artificial neural network sensitivity analysis: 7th Korea National Health and Nutrition Examination Survey.

IF 2 4区 医学 Q3 NUTRITION & DIETETICS
Nutrition Research and Practice Pub Date : 2023-12-01 Epub Date: 2023-10-04 DOI:10.4162/nrp.2023.17.6.1255
Kyungjin Chang, Songmin Yoo, Simyeol Lee
{"title":"Classification and prediction of the effects of nutritional intake on diabetes mellitus using artificial neural network sensitivity analysis: 7th Korea National Health and Nutrition Examination Survey.","authors":"Kyungjin Chang, Songmin Yoo, Simyeol Lee","doi":"10.4162/nrp.2023.17.6.1255","DOIUrl":null,"url":null,"abstract":"<p><strong>Background/objectives: </strong>This study aimed to predict the association between nutritional intake and diabetes mellitus (DM) by developing an artificial neural network (ANN) model for older adults.</p><p><strong>Subjects/methods: </strong>Participants aged over 65 years from the 7th (2016-2018) Korea National Health and Nutrition Examination Survey were included. The diagnostic criteria of DM were set as output variables, while various nutritional intakes were set as input variables. An ANN model comprising one input layer with 16 nodes, one hidden layer with 12 nodes, and one output layer with one node was implemented in the MATLAB<sup>®</sup> programming language. A sensitivity analysis was conducted to determine the relative importance of the input variables in predicting the output.</p><p><strong>Results: </strong>Our DM-predicting neural network model exhibited relatively high accuracy (81.3%) with 11 nutrient inputs, namely, thiamin, carbohydrates, potassium, energy, cholesterol, sugar, vitamin A, riboflavin, protein, vitamin C, and fat.</p><p><strong>Conclusions: </strong>In this study, the neural network sensitivity analysis method based on nutrient intake demonstrated a relatively accurate classification and prediction of DM in the older population.</p>","PeriodicalId":19232,"journal":{"name":"Nutrition Research and Practice","volume":"17 6","pages":"1255-1266"},"PeriodicalIF":2.0000,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10694415/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Nutrition Research and Practice","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.4162/nrp.2023.17.6.1255","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2023/10/4 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"NUTRITION & DIETETICS","Score":null,"Total":0}
引用次数: 0

Abstract

Background/objectives: This study aimed to predict the association between nutritional intake and diabetes mellitus (DM) by developing an artificial neural network (ANN) model for older adults.

Subjects/methods: Participants aged over 65 years from the 7th (2016-2018) Korea National Health and Nutrition Examination Survey were included. The diagnostic criteria of DM were set as output variables, while various nutritional intakes were set as input variables. An ANN model comprising one input layer with 16 nodes, one hidden layer with 12 nodes, and one output layer with one node was implemented in the MATLAB® programming language. A sensitivity analysis was conducted to determine the relative importance of the input variables in predicting the output.

Results: Our DM-predicting neural network model exhibited relatively high accuracy (81.3%) with 11 nutrient inputs, namely, thiamin, carbohydrates, potassium, energy, cholesterol, sugar, vitamin A, riboflavin, protein, vitamin C, and fat.

Conclusions: In this study, the neural network sensitivity analysis method based on nutrient intake demonstrated a relatively accurate classification and prediction of DM in the older population.

利用人工神经网络敏感性分析对营养摄入对糖尿病的影响进行分类和预测:第 7 次韩国国民健康和营养调查。
背景/目的:本研究旨在通过为老年人开发人工神经网络(ANN)模型来预测营养摄入与糖尿病(DM)之间的关联:纳入第 7 次(2016-2018 年)韩国国民健康与营养调查中 65 岁以上的参与者。DM的诊断标准被设定为输出变量,而各种营养摄入量被设定为输入变量。用 MATLAB® 编程语言实现了一个 ANN 模型,该模型由一个包含 16 个节点的输入层、一个包含 12 个节点的隐藏层和一个包含 1 个节点的输出层组成。进行了敏感性分析,以确定输入变量在预测输出时的相对重要性:我们的 DM 预测神经网络模型在 11 个营养素输入变量(硫胺素、碳水化合物、钾、能量、胆固醇、糖、维生素 A、核黄素、蛋白质、维生素 C 和脂肪)中表现出相对较高的准确率(81.3%):在这项研究中,基于营养素摄入量的神经网络敏感性分析方法对老年人群中的 DM 进行了相对准确的分类和预测。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Nutrition Research and Practice
Nutrition Research and Practice NUTRITION & DIETETICS-
CiteScore
3.50
自引率
4.20%
发文量
62
审稿时长
6-12 weeks
期刊介绍: Nutrition Research and Practice (NRP) is an official journal, jointly published by the Korean Nutrition Society and the Korean Society of Community Nutrition since 2007. The journal had been published quarterly at the initial stage and has been published bimonthly since 2010. NRP aims to stimulate research and practice across diverse areas of human nutrition. The Journal publishes peer-reviewed original manuscripts on nutrition biochemistry and metabolism, community nutrition, nutrition and disease management, nutritional epidemiology, nutrition education, foodservice management in the following categories: Original Research Articles, Notes, Communications, and Reviews. Reviews will be received by the invitation of the editors only. Statements made and opinions expressed in the manuscripts published in this Journal represent the views of authors and do not necessarily reflect the opinion of the Societies.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信