Triglyceride-glucose index and mortality in congestive heart failure with diabetes: A machine learning predictive model

Lin YuHaizhu ChenJiwen ZhangWei Han^*

• Guangzhou University of Chinese Medicine Foshan Clinical Medical School, Foshan, China

The triglyceride-glucose (TyG) index operates as a marker for insulin resistance.Research exploring the link from the TyG index to unfavorable outcomes in patients with congestive heart failure(CHF) and diabetes mellitus(DM) is limited. This investigation was designed to investigate the correlation linking the TyG index and mortality risk among individuals with CHF and DM.We obtained clinical data for patients with CHF and DM from the MIMIC-IV (3.1) database. The optimal cutoff value for the TyG index was identified using X-tile software, and patients were classified into three groups. The primary outcome was 28-day hospital mortality, while the secondary outcome was 28-day ICU mortality. We utilized restricted cubic spline (RCS), COX regression analysis, and Kaplan-Meier survival curves to explore the link between the TyG index and negative outcomes. Analyses of subgroups categorized by age, gender, chronic pulmonary disease, atrial fibrillation, hypertension, and mechanical ventilation were conducted to determine the strength of the study's conclusions. Feature selection was conducted through LASSO regression, and predictive modeling was performed using machine learning algorithms.This study encompassed 1046 patients with CHF and DM. Utilizing a fully adjusted COX regression model, a substantial link was identified between the TyG index and both 28-day hospital mortality (HR = 1.32, 95% CI: 1.10-1.58, P = 0.003) and 28-day ICU mortality (HR = 1.29, 95% CI: 1.08-1.54, P = 0.004). Using restricted cubic spline analysis, a linear link between the TyG index and mortality rates was found. Higher TyG values indicate a greater risk of adverse 3 health outcomes. The predictive performance was evaluated using seven machine learning algorithms, with the Random Survival Forest (RSF) algorithm achieving the best performance (AUC 0.817).In patients with CHF and DM, TyG exhibited a linear correlation with both 28-day hospital mortality and 28-day ICU mortality. Elevated TyG values were significantly linked to a heightened risk of adverse events.