skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Nutrient Estimation from 24-Hour Food Recalls Using Machine Learning and Database Mapping: A Case Study with Lactose
The Automated Self-Administered 24-Hour Dietary Assessment Tool (ASA24) is a free dietary recall system that outputs fewer nutrients than the Nutrition Data System for Research (NDSR). NDSR uses the Nutrition Coordinating Center (NCC) Food and Nutrient Database, both of which require a license. Manual lookup of ASA24 foods into NDSR is time-consuming but currently the only way to acquire NCC-exclusive nutrients. Using lactose as an example, we evaluated machine learning and database matching methods to estimate this NCC-exclusive nutrient from ASA24 reports. ASA24-reported foods were manually looked up into NDSR to obtain lactose estimates and split into training (n = 378) and test (n = 189) datasets. Nine machine learning models were developed to predict lactose from the nutrients common between ASA24 and the NCC database. Database matching algorithms were developed to match NCC foods to an ASA24 food using only nutrients (“Nutrient-Only”) or the nutrient and food descriptions (“Nutrient + Text”). For both methods, the lactose values were compared to the manual curation. Among machine learning models, the XGB-Regressor model performed best on held-out test data (R2 = 0.33). For the database matching method, Nutrient + Text matching yielded the best lactose estimates (R2 = 0.76), a vast improvement over the status quo of no estimate. These results suggest that computational methods can successfully estimate an NCC-exclusive nutrient for foods reported in ASA24.  more » « less
Award ID(s):
1934568
PAR ID:
10182416
Author(s) / Creator(s):
; ; ; ; ; ;
Date Published:
Journal Name:
Nutrients
Volume:
11
Issue:
12
ISSN:
2072-6643
Page Range / eLocation ID:
3045
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; ; ; ; ; ; et al (, Current Environmental Health Reports)
    Abstract Purpose of ReviewAquatic foods are increasingly being recognized as a diverse, bioavailable source of nutrients, highlighting the importance of fisheries and aquaculture for human nutrition. However, studies focusing on the nutrient supply of aquatic foods often differ in the nutrients they examine, potentially biasing their contribution to nutrition security and leading to ineffective policies or management decisions. Recent FindingsWe create a decision framework to effectively select nutrients in aquatic food research based on three key domains: human physiological importance, nutritional needs of the target population (demand), and nutrient availability in aquatic foods compared to other accessible dietary sources (supply). We highlight 41 nutrients that are physiologically important, exemplify the importance of aquatic foods relative to other food groups in the food system in terms of concentration per 100 g and apparent consumption, and provide future research pathways that we consider of high importance for aquatic food nutrition. SummaryOverall, our study provides a framework to select focal nutrients in aquatic food research and ensures a methodical approach to quantifying the importance of aquatic foods for nutrition security and public health. 
    more » « less
  2. ; ; ; ; ; (, Advanced Materials Technologies)
    Abstract Nutrition measurement has broad applications in science, ranging from dietary assessment, to food monitoring, personalized health, and more. Despite its importance, there are currently no tools that offer continuous cotracking of nutrients direct from food. In this study, the multiscale engineering of silk biopolymer‐interlayer sensors is reported for comonitoring of nutrients. By manipulating various nano‐ to mesostructural properties of such biosensors, sensors are obtained with programmable sensitivity and selectivity to salts, sugars, and oils/fats. Notably, this approach requires no specialized nanomaterials or delicate biomolecules. Programmable biosensors are further formatted for wireless readout and characteristics of these passive, wireless nutrient monitors are studied in vitro. As a proof of concept, the discrimination and comonitoring of salt, sugar, and fat content direct from real, complex foods such as milk, meat, soup, and tea drinks are demonstrated. It is anticipated that such sensors can be utilized in emerging dietary tools for applications across food tracking and human health. In addition, such strategies are expected in structural engineering of sensors to be adaptable to existing or emerging selective or partially selective sensors. 
    more » « less
  3. ; ; ; ; (, Scientific Reports)
    Abstract Over 2 billion people are unable to access safe, nutritious and sufficient food year-round. While global fisheries are considered key in providing essential nutrients to hundreds of millions of people around the globe, the specific contribution of small-scale fisheries to the nutrient supply given other available food supplies is unknown. Here, we combined multiple global databases to quantify the importance of marine small-scale fisheries to national-level nutrient supply of coastal populations. We found that, on average across assessed nutrients (iron, zinc, calcium, DHA + EPA and vitamins A and B12), small-scale fisheries contributed about 32% of overall global seafood nutrient supply, 17% of the nutrient supply from animal-sourced foods and 10% of nutrient supply from all foods. These global averages, however, underrepresent some key roles of ocean-based foods. Combining nutrient supply estimates with global estimates of inadequate nutrient intake, we found that about half of coastal countries that have a mean inadequate intake of at least 50% across assessed nutrients (iron, zinc, calcium, DHA + EPA and vitamins A and B12) rely on small scale fisheries for at least 15% of mean nutrient supply, and many rely on small scale fisheries for more than 30% of mean nutrient supply. Catch from small-scale fisheries is particularly important for the supply of vitamin B12, calcium and DHA + EPA, representing up to 100% of supply in selected countries. Our study demonstrates the significance of small-scale fisheries for nutritionally vulnerable coastal populations, emphasizing how effective fisheries management can contribute to public health. 
    more » « less
  4. ; ; ; ; (, Frontiers in Sustainable Food Systems)
    Introduction The average American diet is high in red and processed meats which increases one's risk for chronic diseases and requires more land and water to produce and yields greater greenhouse gases (GHG) compared to other protein foods. Reduction of red and processed meat intake, such as seen with the Dietary Approaches to Stop Hypertension (DASH diet), could benefit human and environmental health. Objective The objective of this study is to predict the environmental sustainability of the DASH diet by evaluating the GHG, land use, and water withdrawals from protein foods within the self-selected diets of people who were encouraged to follow the DASH diet. Methods Dietary data was collected from 380 Midwesterners aged 35-70 years old with hypertension using the Automated Self-Administered 24-Hour (ASA 24) Recall System. DASH diet adherence was measured using a nutrient-based DASH score. GHG, land use, and water withdrawals were obtained using Carnegie Mellon University's Economic Input-Output Life Cycle Assessment ( eiolca.net ) using the Purchaser model (cradle-to-consumer). Multiple linear regressions were used to view associations between individual DASH nutrient scores and environmental impacts of total, animal, and plant protein foods. Results Diets that met DASH diet guidelines, as indicated by higher individual DASH nutrient scores, were associated with less GHG and land use from total and animal protein foods but more GHG and land use from plant-protein foods, with a few exceptions. The pattern was not clear for water withdrawals. Diets with the greatest adherence had around 25–50% lower GHG and land use from total protein foods than diets with the lowest adherence. Changes may be due to decreased consumption of total and animal protein foods, selection of animal protein foods with lower environmental impacts, and increased consumption of plant protein foods. Conclusion Adhering to the DASH diet can promote the consumption of less environmentally demanding protein foods resulting in lower GHG and land use from protein foods. However, claims regarding the sustainability of the entire dietary pattern cannot be determined based off the current study. Regardless, it is evident that environmental impacts should be considered alongside health impacts when selecting, promoting, or recommending a dietary pattern. 
    more » « less
  5. ; ; ; ; (, International Journal of Science Academic Research)
    Proteins are essential macronutrients that support the growth, development, and maintenance of tissues in children. Nutrient requirements vary with age, weight, and physiological needs, making age-specific dietary planning critical. Adequate protein intake promotes both physical growth and cognitive development, while diverse sources such as lean meats, dairy, legumes, and nuts help meet varying nutritional needs and encourage lifelong healthy eating habits. This study analyzed a nutritional dataset of 244 baby foods using artificial intelligence (AI) and machine learning to assess protein content, categorizing items into three groups based on protein content: low (0.0–5.9 g/day), moderate (6.0– 10.9 g/day), and high (11.0–15.0 g/day). The majority (n = 202) fell into the low-protein range, followed by 22 in the moderate range and 20 in the high range. Age-specific protein requirements, expressed in grams per kilogram of body weight (g/kg), were assessed for four age groups: 0– 6 months (1.52 g/kg; 12.6–15.8 g/day; 5.5–6.0 kg), 7–9 months (1.20 g/kg; 9.0–10.2 g/day; 7.5–8.5 kg), 10–12 months (1.00 g/kg; 8.5–9.5 g/day; 8.5–9.5 kg), and 1–3 years (1.05 g/kg; 12.6–15.8 g/day; 12.0–15.0 kg). Low-protein foods may be insufficient for infants with reduced breastmilk or formula intake, while high-protein foods often rich in meat, dairy, or fortified products can help meet upper-range requirements. These findings underscore the need for careful alignment of complementary food protein levels with age-specific nutritional guidelines to support optimal growth and development in early childhood. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email