A Novel Nomogram for Predicting the Risk of Acute Heart Failure in Intensive Care Unit Patients with COPD.

Abstract

Background: The objective of this study was to construct a prediction model to assess the onset of acute heart failure (AHF) in patients with chronic obstructive pulmonary disease (COPD) without a history of heart failure and to evaluate the predictive value of the nomogram.

Methods: This study involved 3730 patients with COPD and no history of heart failure. Clinical and laboratory data were collected from the Medical Information Mart for Intensive Care IV database. The patients were divided into a training set (2611 cases) and a validation set (1119 cases) in a 7:3 ratio. Least absolute shrinkage and selection operator (LASSO) regression was used to identify potential risk factors for AHF in patients with COPD. These factors were then subjected to multivariate logistic regression analysis to develop a prediction model for the risk of AHF. The model's differentiation, consistency, and clinical applicability were evaluated using receiver operating characteristic analysis, a calibration curve, and decision curve analysis (DCA), respectively.

Results: LASSO regression identified 10 potential predictors. The concordance index was 0.820. The areas under the curves for the training and validation sets were 0.8195 and 0.8035, respectively. The calibration curve demonstrated strong concordance between the nomogram's predictions and the actual outcomes. DCA confirmed the clinical applicability of the nomogram.

Conclusion: Our nomogram is a reliable and convenient tool for predicting acute heart failure in patients with COPD.