Table 3. Comparative performance of optimal machine learning predictors and Cox benchmark for cardiovascular mortality.
| Index | C-index (95% CI) | Optimal model | Cox regression benchmark | ||
|---|---|---|---|---|---|
| P value | HR | 95% CI | |||
| TyG-BMI | 0.840 (0.802–0.875) | RSF | 0.194 | 0.999 | 0.996–1.001 |
| TyG-WHtR | 0.817 (0.763–0.867) | CoxNet | 0.964 | 1.003 | 0.869–1.158 |
| TyG | 0.815 (0.770–0.857) | CoxPH | 0.484 | 0.929 | 0.757–1.141 |
| TyG-WC | 0.794 (0.744–0.834) | SurvivalSVM | 0.407 | 1.000 | 0.999–1.000 |
CI, confidence interval; CoxNet, LASSO-Cox regression; CoxPH, Cox proportional hazards; HR, hazard ratio; RSF, random survival forest; survivalSVM, support vector machine for survival analysis; TyG, triglyceride-glucose; TyG-BMI, triglyceride-glucose-body mass index; TyG-WC, triglyceride-glucose-waist circumference; TyG-WHtR, triglyceride-glucose-waist-to-height ratio.