A Novel Nomogram for Predicting the Risk of Acute Heart Failure in ICU Patients with COPD

Abstract

Abstract Background This study developed a novel nomogram to predict the incidence of acute heart failure (AHF) in patients of chronic obstructive pulmonary disease (COPD) and evaluated the predictive value of the nomogram. Methods 3730 patients of chronic obstructive pulmonary disease from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database were analysed. The patients were randomly divided into two groups in a seven-to-three ratio to form a training cohort (n = 2611) and a validation cohort (n = 1119). Least absolute shrinkage and selection operator (LASSO) regression analyses were used to identify associated risk variables. A nomogram was established to predict the rate of acute heart failure in patients of chronic obstructive pulmonary disease. The new model was assessed in terms of the concordance index (C-index), the area under the curve (AUC) of receiver operating characteristic (ROC) analysis, calibration curve, and decision curve analysis (DCA). Results Least absolute shrinkage and selection operator regression analysis identified ten potential predictors of acute heart failure. Multivariate logistic regression analysis was used to evaluate the effects of these predictors and create a final model. The concordance index values were 0.820. The areas under the curves for the training and validation sets were 0.8195 and 0.8035, respectively. Conclusion The age, body mass index (BMI), urine output, carbon dioxide partial pressure (pCO2), bicarbonate, partial thromboplastin time (PTT), total Bilirubin (TBIL), urea, chloride and ventilation status were identified as predictors. Our nomogram is a reliable convenient approach for predicting acute heart failure in patients with chronic obstructive pulmonary disease.