NHANES Dietary Data for Renal Impairment in Diabetes Analyzed by Machine Learning

9,764 diabetic participants from the National Health and Nutrition Examination Survey (NHANES) 1999–2020 were analyzed for associations between dietary oxidative balance and renal impairment. The study applied multiple machine learning models, with random forest achieving the best performance, and identified vitamin E, β-carotene, and magnesium as key dietary factors. This dataset, authored by Xincan Chen and shared under CC-BY-4.0, supports the findings of the associated research paper.

Use Cases

• Training machine learning models to predict renal impairment based on dietary oxidative balance scores.
• Investigating the association between specific antioxidant nutrients (e.g., vitamin E, β-carotene) and kidney health in diabetic populations.
• Conducting feature importance analysis to identify key dietary contributors to UACR-defined renal impairment.
• Reproducing or extending the study's analytical pipeline on NHANES data for similar health outcomes.

Strengths

• Includes data from 9,764 diabetic participants, providing a substantial sample size for analysis.
• Leverages the authoritative and nationally representative NHANES survey from 1999–2020.
• Analysis is supported by multiple machine learning models and in vitro experimental validation mentioned in the description.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count for the underlying dataset is unknown, which may limit suitability assessment.
• The 556.5 KB file size suggests the dataset is a supplementary document, not the raw NHANES data, limiting direct analysis scope.

Provenance

Source

National Health and Nutrition Examination Survey (NHANES)

Collection Method

Secondary analysis of survey data, applying machine learning models and functional analysis.

Time Range

1999–2020

Freshness

Last updated 2026-05-04 04:24:15; freshness should be verified.

Geography

United States