Background The triglyceride-glucose (TyG) index is regarded as an independent predictor of cardiovascular (CV) consequences and a reliable surrogate measure of insulin resistance (IR). However, the predictive significance of the TyG index in patients with type 2 diabetes mellitus (T2DM) and ischemic cardiomyopathy (ICM) remains unknown. Methods This study included 1514 consecutive subjects with ICM and T2DM. The tertile of the TyG index values was used to categorize these patients into three groups. Major adverse cardiac and cerebral events (MACCEs) were also noted. The TyG index was calculated using the [fasting triglycerides (mg/dL) × fasting plasma glucose (mg/dL)/2] equation. Results After adjusting for age, BMI, and other potential confounders, the scores of multivariate Cox proportional hazards regression models for chest pain [9.056 (4.370 to 18.767), p<0.001], acute myocardial infarction [4.437 (1.420 to 13.869), p=0.010], heart failure [7.334 (3.424 to 15.708), p <0.001], cardiogenic shock [3.707 (1.207 to 11.384), p =0.022], malignant arrhythmia [5.309 (2.367 to 11.908), p <0.001], cerebral infarction [3.127 (1.596 to 6.128), p <0.001], gastrointestinal bleeding [4.326 (1.612 to 11.613), p =0.004], all-cause death [4.502 (3.478 to 5.827), p <0.001] and cumulative incidence of MACCEs [4.856 (3.842 to 6.136), p <0.001] increased significantly with an increase in TyG index levels (all p <0.05). Time-dependent ROC analysis revealed that the area under the TyG index curve (AUC) reached 0.653 in the 3rd year, 0.688 in the 5th year, and 0.764 in the 10th year. The predictive efficiency of this model on MACCEs improved [net reclassification improvement (NRI): 0.361 (0.253 to 0.454); C-index: 0.678 (0.658 to 0.698); integrated discrimination improvement (IDI): 0.138 (0.098 to 0.175), all p <0.05] following the incorporation of the TyG index into the base risk model. Conclusion TyG index could be useful in predicting MACCEs and initiating preventive measures in subjects with ICM and T2DM.

BackgroundIschemic Heart Disease (IHD) is the leading cause of death from cardiovascular disease. Currently, most studies have focused on factors influencing IDH or mortality risk, while few predictive models have been used for mortality risk in IHD patients. In this study, we constructed an effective nomogram prediction model to predict the risk of death in IHD patients by machine learning.MethodsWe conducted a retrospective study of 1,663 patients with IHD. The data were divided into training and validation sets in a 3:1 ratio. The least absolute shrinkage and selection operator (LASSO) regression method was used to screen the variables to test the accuracy of the risk prediction model. Data from the training and validation sets were used to calculate receiver operating characteristic (ROC) curves, C-index, calibration plots, and dynamic component analysis (DCA), respectively.ResultsUsing LASSO regression, we selected six representative features, age, uric acid, serum total bilirubin, albumin, alkaline phosphatase, and left ventricular ejection fraction, from 31 variables to predict the risk of death at 1, 3, and 5 years in patients with IHD, and constructed the nomogram model. In the reliability of the validated model, the C-index at 1, 3, and 5 years was 0.705 (0.658–0.751), 0.705 (0.671–0.739), and 0.694 (0.656–0.733) for the training set, respectively; the C-index at 1, 3, and 5 years based on the validation set was 0.720 (0.654–0.786), 0.708 (0.650–0.765), and 0.683 (0.613–0.754), respectively. Both the calibration plot and the DCA curve are well-behaved.ConclusionAge, uric acid, total serum bilirubin, serum albumin, alkaline phosphatase, and left ventricular ejection fraction were significantly associated with the risk of death in patients with IHD. We constructed a simple nomogram model to predict the risk of death at 1, 3, and 5 years for patients with IHD. Clinicians can use this simple model to assess the prognosis of patients at the time of admission to make better clinical decisions in tertiary prevention of the disease.