NHANES 1999–2018: TyG Index Association with Melanoma Prevalence and Mortality

A study dataset of 21,360 participants from the National Health and Nutrition Examination Survey (NHANES) 1999–2018 cycles, used to investigate the relationship between the triglyceride-glucose (TyG) index and melanoma. The analysis includes weighted logistic and Cox regression models, machine learning model performance metrics, and an external validation cohort of 475 patients from three tertiary hospitals. The dataset was authored by Yao Liang and last updated in March 2026.

Use Cases

• Training machine learning models for melanoma risk prediction based on metabolic and demographic factors.
• Analyzing the U-shaped association between the TyG index and all-cause mortality in a melanoma cohort.
• Conducting subgroup analyses to verify the robustness of associations across different population segments.
• Interpreting predictive models using SHAP values to identify key factors like race, age, and serum phosphorus.

Strengths

• Includes data from 21,360 participants from a major national health survey (NHANES).
• External validation cohort of 475 patients from three tertiary hospitals is described.
• Analysis employed seven machine learning algorithms, with the ridge regression model achieving an AUROC of 0.85.

Limitations

• Row count and column-level documentation for the underlying data are unknown.
• The 14.2 KB file size suggests the uploaded document is likely a summary paper, not the raw dataset.
• Data may reflect the geographic and demographic biases inherent to the NHANES survey.

Provenance

Source

National Health and Nutrition Examination Survey (NHANES) and three tertiary hospitals.

Collection Method

Cross-sectional survey data and hospital-based patient records.

Time Range

1999–2018 for NHANES data.

Freshness

Last updated 2026-03-18 05:35:02.

Geography

United States (NHANES); hospital locations are unspecified.