An official website of the United States government
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
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
- 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
-
-
Many Small Island Developing States (SIDS) are experiencing a nutrition transition, wherein high prevalence of malnutrition co-occurs with growing rates of diet-related non-communicable diseases. Sustainably managed and accessible aquatic foods can serve as a rich and bioavailable source of nutrients, helping communities achieve healthy diets and meet key sustainable development goals (e.g., SDG 1 No Poverty, SDG 2 Zero Hunger, and SDG 14 Life Below Water). However, to properly harness aquatic food systems in nutrition interventions, we must first understand aquatic food’s role in nutrient intake and adequacy. Here, using a nationally representative survey from Kiribati, we quantify the contribution of aquatic foods to nutrient intake and adequacy, and examine the spatial variability in nutrient intake adequacies. We find aquatic foods are the main contributors of most nutrients we examined, providing > 75% of vitamin B12, retinol, and heme iron, > 50% of niacin and total vitamin A, and > 25% of protein, vitamin E, potassium, and total iron consumed. Consumption of aquatic foods contributes to meeting key nutrient adequacies (e.g., niacin) and provides complete adequacy for vitamin B12 and protein. However, despite high aquatic food consumption, we find high levels of nutrient inadequacies (11 of the 17 nutrients with dietary reference intakes). Overall, our study quantifies the nutritional importance of aquatic foods in an emblematic SIDS, emphasizing their vulnerability to declining aquatic resources. We also highlight the need for cross-scale context-specific targeted nutrition interventions, even when aquatic food consumption is high, to enable SIDS to meet key SDGs.more » « less
-
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
-
The preprocessing of infrared spectra can significantly improve predictive accuracy for protein, carbohydrate, lipid, or other nutrition components, yet optimal preprocessing selection is typically empirical, tedious, and dataset specific. This study introduces a Bayesian optimization-based framework designed for the automated selection of optimal spectral preprocessing pipelines within a chemometric modeling context. The framework was applied to mid-infrared spectra of milk to predict compositional parameters for fat, protein, lactose, and total solids. A total of 385 averaged spectra corresponding to 198 unique samples was split into a 70/30 ratio (training/test) using a group-aware Kennard-Stone algorithm, resulting in 269 averaged spectra (135 unique samples) for training and 116 spectra (58 unique samples) for testing. Six regression models: Elastic Net, Gradient Boosting Machines (GBM), Partial Least Squares (PLS), RidgeCV Regression, LassoLarsCV, and Support Vector Regression (SVR) were evaluated across three preprocessing conditions: (1) no preprocessing, (2) literature-derived custom preprocessing (e.g., MSC, SNV, and first and second derivatives), and (3) optimized preprocessing via the proposed Bayesian framework. Optimized preprocessing consistently outperformed other methods, with RidgeCV achieving the best performance for all components except lactose, where PLS slightly outperformed it. Improvements in predictive accuracy, particularly in terms of RMSEP were observed across all milk components. The best RMSEP results were achieved for protein (RMSEP = 0.054, R2=0.981) and lactose (RMSEP = 0.026, R2=0.917), followed by fat (RMSEP = 0.139, R2=0.926) and total solids (RMSEP = 0.154, R2=0.960). Literature-based pipelines demonstrated inconsistent effectiveness, highlighting the limitations of transferring preprocessing methods between datasets. The Bayesian optimization approach identified relatively simple yet highly effective preprocessing pipelines, typically involving few steps. By eliminating manual trial and error, this data-driven strategy offers a robust and generalizable solution that streamlines spectral modeling in dairy analysis and can be readily applied to other types of spectroscopic data across various domains.more » « less
-
Abstract Researchers and policymakers increasingly recognize the contribution of aquatic food systems, such as fisheries, to food security and nutrition. Yet governing fisheries for nutrition objectives is complicated by the multiple overlapping processes that shape availability and access to nutrients over time, including fishing sustainability, climate change, trade dynamics, and consumer preferences. Anticipating the impact of governance interventions to sustain or enhance nutritional benefits from fisheries entails accounting for these multiple interacting influences. We develop an analytical approach to link available data on aquatic foods production, nutrition, distribution, and potential climate impacts to evaluate the nutrition implications of fishery management and post-harvest allocation interventions. We demonstrate this approach using national and publicly available datasets for five case study countries: Peru, Chile, Indonesia, Sierra Leone, and Malawi. As examples, we evaluate the potential to enhance domestic supply of key nutrients to nutritionally-vulnerable populations by a) dynamically adjusting fishing effort in response to climate impacts on fish stocks, and b) retaining aquatic foods currently diverted via trade or foreign fishing. The results indicate substantial differences across countries in terms of anticipated climate change effects, with potential for substantially increased nutrition yield in Chile and Peru under adaptive management, vs. more modest yield increases in Indonesia. The impacts of post-harvest allocation policies related to foreign fishing, exports, fishing sector, and subnational trade also vary, with exports weighing heavily on nutrient availability in Sierra Leone. This methodological approach represents a step toward operationalizing calls to manage fisheries as part of national food and nutrient supplies, in light of climate change risks.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.3390/nu11123045
