Predicting the Macronutrient Composition of Mixed Meals From Dietary Biomarkers in Blood

Predicting the Macronutrient Composition of Mixed Meals From Dietary Biomarkers in Blood
复制标题

根据血液中的膳食生物标志物预测混合餐的常量营养素成分

DOI:
10.1109/jbhi.2021.3134193
复制
发表时间:
2022
影响因子:
7.7
通讯作者:
Gutierrez-Osuna, Ricardo
Gutierrez-Osuna, Ricardo
中科院分区:
工程技术1区
文献类型:
--
作者:
Das, Anurag;Mortazavi, Bobak;Sajjadi, Seyedhooman;Chaspari, Theodora;Ruebush, Laura E.;Deutz, Nicolaas E.;Cote, Gerard L.;Gutierrez-Osuna, Ricardo

文献摘要

参考文献

相似文献

饮食监测是从2型糖尿病到心血管疾病等许多疾病的重要干预组成部分。然而,目前的饮食监测方法是繁琐的,往往不准确。在先前的工作中,我们表明连续葡萄糖监测仪(CGMs)可用于预测膳食宏量营养素(例如,碳水化合物、蛋白质、脂肪)。在这项研究中,我们检查了血液中的一些额外的饮食生物标志物,与单独使用CGMs相比,它们能够改善常量营养素预测。为此,我们进行了一项营养研究,其中(n= 10)参与者食用了9种不同的混合膳食,其中含有不同但已知的大量营养素,我们分析了33种饮食生物标志物(包括氨基酸,胰岛素,甘油三酯和葡萄糖)在餐后不同时间的浓度。然后,我们建立了机器学习模型来预测(1)单个生物标志物和(2)它们的组合中的常量营养素含量。我们发现,额外的血液生物标志物提供了补充信息,更重要的是,三种常量营养素的归一化均方根误差(NRMSE)较低(碳水化合物:22.9%;蛋白质:23.4%;脂肪:32.3%)(碳水化合物:28.9%,t(18)1.64,p0.060;蛋白质:46.4%,t(18)5.38,p0.001;脂肪:40.0%,t(18)2.09,p0.025)。我们的主要结论是,增加CGMs来测量这些额外的饮食生物标志物可以提高常量营养素预测性能,并可能最终导致自动化方法的发展,以监测营养摄入。这项工作对生物医学研究具有重要意义,因为它为长期存在的饮食监测问题提供了潜在的解决方案,促进了对一些疾病的新干预措施。
Diet monitoring is an essential intervention component for a number of diseases, from type 2 diabetes to cardiovascular diseases. However, current methods for diet monitoring are burdensome and often inaccurate. In prior work, we showed that continuous glucose monitors (CGMs) may be used to predict meal macronutrients (e.g., carbohydrates, protein, fat) by analyzing the shape of the post-prandial glucose response. In this study, we examine a number of additional dietary biomarkers in blood by their ability to improve macronutrient prediction, compared to using CGMs alone. For this purpose, we conducted a nutritional study where (n= 10) participants consumed nine different mixed meals with varied but known macronutrient amounts, and we analyzed the concentration of 33 dietary biomarkers (including amino acids, insulin, triglycerides, and glucose) at various times post-prandially. Then, we built machine learning models to predict macronutrient amounts from (1) individual biomarkers and (2) their combinations. We find that the additional blood biomarkers provide complementary information, and more importantly, achieve lower normalized root mean squared error (NRMSE) for the three macronutrients (carbohydrates: 22.9%; protein: 23.4%; fat: 32.3%) than CGMs alone (carbohydrates: 28.9%,t(18)1.64, p0.060; protein: 46.4%,t(18)5.38, p0.001; fat: 40.0%,t(18)2.09, p0.025). Our main conclusion is that augmenting CGMs to measure these additional dietary biomarkers improves macronutrient prediction performance, and may ultimately lead to the development of automated methods to monitor nutritional intake. This work is significant to biomedical research as it provides a potential solution to the long-standing problem of diet monitoring, facilitating new interventions for a number of diseases.
基于声谱图的营养摄入音频分类
DOI: --
发表时间: 2014
期刊: Australian National Health Informatics Conference
影响因子: --
作者:
H. Kalantarian;N. Alshurafa;M. Pourhomayoun;Shruti Sarin;Tuan Le;M. Sarrafzadeh
通讯作者: M. Sarrafzadeh
感应叉子:饮食行为检测器具和移动说服游戏
DOI: 10.1145/2468356.2468634
发表时间: 2013
期刊: CHI '13 Extended Abstracts on Human Factors in Computing Systems
影响因子: --
作者:
Azusa Kadomura;Cheng;Yen;K. Tsukada;I. Siio;Hao
通讯作者: Hao
DOI: --
发表时间: 2017
期刊: Mobile Health - Sensors, Analytic Methods, and Applications
影响因子: --
作者:
Edison Thomaz;Irfan Essa;G. Abowd
通讯作者: G. Abowd
DOI: 10.1093/jn/133.3.921s
发表时间: 2003-03-01
影响因子: 4.2
作者:
Bingham, SA
通讯作者: Bingham, SA
预测正常受试者食用不同能量、蛋白质、脂肪、碳水化合物和血糖指数的混合膳食后的葡萄糖和胰岛素反应。
DOI: 10.1093/jn/126.11.2807
发表时间: 1996
期刊: The Journal of nutrition
影响因子: --
作者:
T. Wolever;Claudia Bolognesi
通讯作者: Claudia Bolognesi