Scholarlink

<p>Tracking food intake is key to using nutrition to prevent or manage common diseases including type 2 diabetes (T2D) and obesity. Several datasets are publicly available to promote research in diet monitoring, but generally contain data from a limited set of sensors (e.g., accelerometry, food images), which limits their application to specific use cases such as activity recognition or image recognition. Also lacking are publicly available datasets with food macronutrients and their associated continuous glucose measurements; datasets containing such rich information are proprietary. To address this gap, we present CGMacros, a dataset containing multimodal information from an activity tracker, two continuous glucose monitors (CGM), food macronutrients, and food photographs, as well as anonymized participant demographics, anthropometric measurements and health parameters from blood analyses and gut microbiome profiles. CGMacros contains data for 45 participants (15 healthy, 16 pre-diabetes, 14 T2D) who consumed meals with varying and known macronutrient compositions in a free-living setting for ten consecutive days. To our knowledge, this is the first database of its kind to be made publicly available. CGMacros, and larger publicly available datasets that we hope may follow, are essential to democratize academic research in personalized nutrition and algorithmic approaches to automated diet monitoring.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

CGMacros: a pilot scientific dataset for personalized nutrition and diet monitoring

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年9月25日

查看全文
  • Anurag Das,
  • David Kerr,
  • Namino Glantz,
  • Wendy Bevier,
  • Rony Santiago,
  • Ricardo Gutierrez-Osuna,
  • Bobak J. Mortazavi

摘要

Tracking food intake is key to using nutrition to prevent or manage common diseases including type 2 diabetes (T2D) and obesity. Several datasets are publicly available to promote research in diet monitoring, but generally contain data from a limited set of sensors (e.g., accelerometry, food images), which limits their application to specific use cases such as activity recognition or image recognition. Also lacking are publicly available datasets with food macronutrients and their associated continuous glucose measurements; datasets containing such rich information are proprietary. To address this gap, we present CGMacros, a dataset containing multimodal information from an activity tracker, two continuous glucose monitors (CGM), food macronutrients, and food photographs, as well as anonymized participant demographics, anthropometric measurements and health parameters from blood analyses and gut microbiome profiles. CGMacros contains data for 45 participants (15 healthy, 16 pre-diabetes, 14 T2D) who consumed meals with varying and known macronutrient compositions in a free-living setting for ten consecutive days. To our knowledge, this is the first database of its kind to be made publicly available. CGMacros, and larger publicly available datasets that we hope may follow, are essential to democratize academic research in personalized nutrition and algorithmic approaches to automated diet monitoring.