Table 1_Uncovering non-linear dietary predictors of cardiovascular disease risk in older a

Data from three NHANES cycles (2009–2014) and the MyPyramid Equivalents Database (MPED) was integrated by Jiefan Liu to investigate non-linear dietary predictors of cardiovascular disease risk in older adults with periodontitis. The dataset includes results from six machine learning models and an external validation study of 183 older adults. It was last updated on 2026-03-18.

Use Cases

• Training interpretable ML models (e.g., XGBoost) to predict CVD risk based on dietary trace elements and food intake.
• Applying SHAP/LIME analysis to identify key protective dietary factors like theobromine, lycopene, and meat consumption.
• Validating non-linear dietary risk models in a specific inflammatory population (older adults with periodontitis).
• Comparing model performance across different data sources (NHANES vs. MPED) for nutritional epidemiology.

Strengths

• Includes external validation on an independent cohort of 183 older adults with periodontitis.
• Reports high model performance with a validation AUC-ROC of 0.889 for the MPED model.
• Applies multiple interpretable ML techniques (XGBoost, SHAP, LIME) for feature analysis.
• Integrates data from established public health sources (NHANES, MPED).

Limitations

• Row count and column-level documentation are absent; field semantics must be inferred after download.
• The dataset is very small (33.6 KB), indicating limited scope, likely containing summary results rather than raw data.
• Data may reflect geographic and temporal bias inherent to the NHANES survey cycles used.

Provenance

Source

NHANES (2009–2014 cycles) and MyPyramid Equivalents Database (MPED), with external validation from a hospital-based cohort.

Collection Method

Cross-sectional analysis integrating survey and dietary database data, with feature selection using correlation coefficients and the BORUTA algorithm.

Time Range

2009–2014 (NHANES cycles)

Freshness

Last updated 2026-03-18 06:42:32; freshness should be verified.

Geography

United States (NHANES data); geography of external validation cohort is unspecified.