Table 2. Comparative performance of optimal machine learning predictors and Cox benchmark for all-cause mortality.
| Index | C-index (95% CI) | Optimal model | Cox regression benchmark | ||
|---|---|---|---|---|---|
| P value | HR | 95% CI | |||
| TyG | 0.771 (0.741–0.801) | GBSA | 0.234 | 0.926 | 0.816–1.051 |
| TyG-BMI | 0.753 (0.721–0.787) | CoxPH | 0.005 | 0.998 | 0.997–0.999 |
| TyG-WHtR | 0.739 (0.703–0.777) | RSF | 0.150 | 0.937 | 0.857–1.024 |
| TyG-WC | 0.725 (0.688–0.761) | SurvivalSVM | 0.082 | 1.000 | 0.999–1.000 |
CI, confidence interval; CoxPH, Cox proportional hazards; GBSA, gradient boosting survival analysis; 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.