Triglyceride-glucose indices predict all-cause mortality after stroke in NHANES 1999-2018

Abstract

Objective: The present study explores the prognostic relevance of triglyceride-glucose-based indices in assessing post-stroke survival among affected individuals.

Methods: This study utilized a multifaceted analytical approach to assess how triglyceride-glucose-based indicators relate to death risk in stroke patients. This study was analyzed using a multivariate Cox proportional risk regression model incorporating sampling weights, while a restricted cubic spline function was introduced to assess trends in non-linear associations between exposure variables and outcomes. In addition, interaction terms were set and stratified analyses were conducted to verify the robustness and heterogeneity of the model results.

Results: This research ultimately included 796 individuals diagnosed with stroke. When adjusting for a wide range of potential confounders, those in the top TyG-BMI quartile exhibited the most pronounced reduction in mortality risk compared to individuals in the lowest category, with a hazard ratio of 0.20 (95% CI: 0.08-0.50), highlighting its protective potential across TyG-BMI. In contrast, individuals falling within the fourth quartile of the TyG-WHtR index demonstrated the strongest positive correlation with the risk of all-cause mortality (Hazard Ratio = 4.61, 95% CI: 1.77-12.00). Moreover, analysis using restricted cubic splines indicated a significant non-linear association between TyG-BMI levels and mortality outcomes (p < 0.05). No statistical interactions were observed between mortality outcomes and demographic or clinical variables including age, sex, smoking, asthma, coronary artery disease, diabetes, or hypertension across any TyG-related indices (p > 0.05).

Conclusion: The study outcomes suggest that stroke patients with reduced TyG-BMI and elevated TyG-WHtR levels tend to face increased mortality risks. Nonetheless, addressing obesity may be crucial in exploring potential causal pathways.

Keywords: NHANES; TyG-related index; mortality; retrospective cohort analysis; stroke.

Figure 1

The flow diagram shows participant selection from NHANES 1999–2000 to 2017–2018, outlining inclusion and exclusion criteria.

Figure 2

(A–D) Associations of TyG and its composite indices with post-stroke mortality across different models. Model 1: This model did not include any adjustments. Model 2: Adjustments were made for age, race, gender, education level, and family PIR. Model 3: Further adjustments based on 2a Model 2 included LDL-cholesterol, drinking status, smoking status, hypertension, diabetes, asthma and coronary heart disease.

Figure 3

(A–D) Restricted cubic spline curve for the association between TyG-related indicators and the mortality rate of stroke patients.

Figure 4

Associations between TyG-based indices and stroke-related mortality across various subgroups. To assess the associations between stroke-related mortality and the four TyG-derived metrics—TyG (A), TyG-BMI (B), TyG-WC (C), and TyG-WHtR (D)—stratified subgroup evaluations were performed. These models were adjusted for a comprehensive set of covariates, including demographic factors (age, sex, race, education, income level), physical measures (BMI, height, waist size, LDL-C), lifestyle behaviors (smoking and alcohol use), and chronic conditions (hypertension, diabetes, coronary disease, and asthma).