A new nomogram to predict in-hospital mortality in patients with acute decompensated chronic heart failure and diabetes after 48 Hours of Intensive Care Unit

The study set out to develop an accurate and clinically valuable prognostic nomogram to assess the risk of in-hospital death in patients with acute decompensated chronic heart failure (ADCHF) and diabetes. We extracted clinical data of patients diagnosed with ADCHF and diabetes from the Medical Information Mart for Intensive Care III database. Risk variables were selected utilizing least absolute shrinkage and selection operator regression analysis, and were included in multivariate logistic regression and presented in nomogram. bootstrap was used for internal validation. The discriminative power and predictive accuracy of the nomogram were estimated using the area under the receiver operating characteristic curve (AUC), calibration curve and decision curve analysis (DCA). Among 867 patients with ADCHF and diabetes, In-hospital death occurred in 81 (9.3