TyG Index and Melanoma: NHANES 1999–2018 Data with External Hospital Cohort

21,360 participants from the 1999–2018 National Health and Nutrition Examination Survey (NHANES) were analyzed for links between the triglyceride-glucose index and melanoma prevalence and mortality. The study, authored by Yao Liang and last updated in March 2026, also includes a descriptive analysis of 475 primary non-metastatic acral melanoma patients from three tertiary hospitals. Machine learning models, including ridge regression, were used to build a predictive model with an AUROC of 0.85.

Use Cases

• Investigating the U-shaped association between the TyG index and all-cause mortality in melanoma patients based on the study's findings.
• Building predictive models for melanoma risk using machine learning algorithms, as demonstrated by the ridge regression model.
• Conducting subgroup analyses to verify the robustness of associations between metabolic indices and health outcomes.
• Interpreting predictive models for clinical risk factors using SHAP analysis, as performed on race, age, and serum phosphorus levels.

Strengths

• Includes data from a large, nationally representative survey (NHANES) with 21,360 participants.
• Analysis incorporates an external validation cohort of 475 hospital patients.
• Employs multiple analytical methods, including weighted regression, restricted cubic splines, and seven machine learning algorithms.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count for the primary dataset is unknown, which may limit suitability assessment.
• The 11.6 KB file size suggests the uploaded document is likely a summary or paper, not the raw underlying data.

Provenance

Source

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

Collection Method

Cross-sectional survey data analysis and external hospital-based descriptive analysis.

Time Range

1999–2018 for NHANES data.

Freshness

Last updated 2026-03-18 05:35:04; freshness should be verified.

Geography

United States (NHANES); hospital locations are unknown.