Fig. 4From: Machine-learning-based models to predict cardiovascular risk using oculomics and clinic variables in KNHANESROC and AUC of models use both oculomics and clinic variables as input variables. a-c The performance of our model using TyG-index=8.0, 8.75, or 8.93 as the cut-off point in the internal validation dataset is demonstrated. d-f The performance of our model using TyG-index=8.0, 8.75, or 8.93 as the cut-off point in the external validation dataset is demonstrated. AUC, Area under curve. TyG, Triglyceride-glucose index.ROC, Receiver operating characteristicBack to article page