TyG Index and Melanoma: NHANES 1999–2018 and Hospital Patient Data

21,360 participants from the 1999–2018 National Health and Nutrition Examination Survey (NHANES) were analyzed for associations between the triglyceride-glucose (TyG) index and melanoma prevalence and mortality. An external validation set includes 475 patients with primary non-metastatic acral melanoma from three tertiary hospitals. The dataset, authored by Yao Liang and last updated in March 2026, was used to build predictive models with seven machine learning algorithms.

Use Cases

• Investigating U-shaped associations between metabolic indices and all-cause mortality based on the TyG index.
• Building predictive models for melanoma risk using machine learning algorithms like ridge regression.
• Conducting subgroup analyses to verify the robustness of associations across demographic factors.
• Interpreting model predictions for melanoma risk using SHAP values to identify key features like race and age.

Strengths

• Includes data from a large, nationally representative survey (21,360 NHANES participants).
• Provides an external validation cohort of 475 hospital patients with acral melanoma.
• Analysis employed multiple statistical and machine learning methods, including weighted regression and SHAP interpretation.

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 15.7 KB file size suggests the dataset is likely a summary or analysis document, not the raw underlying data.

Provenance

Source

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

Collection Method

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

Time Range

1999–2018 for NHANES data.

Freshness

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

Geography

United States (NHANES); hospital locations are unspecified.