Abstract
BACKGROUND: Cardiovascular disease (CVD) continues to be a leading cause of disease burden and mortality worldwide. Identifying reliable biomarkers for CVD risk assessment is essential. This study investigates the association between the C-reactive protein-triglyceride-glucose (CTI) index and CVD, evaluating its potential value in CVD classification. METHODS: This study included 14,899 participants aged 20 years and older from the 1999-2020 National Health and Nutrition Examination Survey. Regression analysis and restricted cubic splines (RCS) were used to examine the relationship between the CTI and CVD, along with its five specific outcomes. An interaction test assessed the impact of different subgroups on the association between CTI and CVD. Furthermore, the potential of CTI to assess CVD risk was evaluated through receiver operating characteristic (ROC) curves, decision curve analysis, and SHAP analysis, with machine learning models, including XGBoost, LASSO, random forest, support vector machine, and Naive Bayes, used for evaluation. RESULTS: For each 1-unit higher CTI, the odds of having CVD were 18% higher (OR = 1.18, 95% CI: 1.10-1.28, P < 0.01). Specific associations include congestive heart failure (29%) (OR = 1.29, 95% CI: 1.14-1.47, P < 0.001), heart attack (29%) (OR = 1.29, 95% CI: 1.15-1.44, P < 0.001), coronary heart disease (20%) (OR = 1.20, 95% CI: 1.07-1.35, P < 0.01), angina (21%) (OR = 1.21, 95% CI: 1.06-1.36, P < 0.01), and stroke (13%) (OR = 1.13, 95% CI: 1.01-1.27, P < 0.05). Age influences the association between CTI and CVD, with individuals under 60 years being more affected. Machine-learning models achieved AUC > 0.70, indicating moderate discriminatory ability; these findings suggest promising potential for risk stratification. SHAP analysis indicated that CTI showed larger SHAP contributions to CVD classification than CRP and TyG within our models. CONCLUSION: Higher CTI levels were associated with higher odds of prevalent CVD, indicating that CTI may serve as a marker of CVD status and aid cross-sectional discrimination of prevalent CVD. Prospective longitudinal studies are needed to establish temporality and to evaluate whether CTI adds predictive value in longitudinal risk assessment.