Development of a prognostic nomogram among chronic obstructive pulmonary disease patients based on laboratory tests and chest radiography

Background: Chronic obstructive pulmonary disease (COPD) patients requiring admission to the intensive care unit (ICU) typically have poor prognosis. In this study, the objective was to construct a prognostic nomogram to estimate the 28-day mortality for COPD patients in ICU. Methods: Data of 853 patients from the MIMIC-IV database and MIMIC-CXR-JPG database were extracted. To construct the prognostic nomogram, a multivariate Cox regression analysis was conducted using predictive factors identified based on the least absolute shrinkage and selection operator (LASSO) regression analysis. The performance of the nomogram was assessed by evaluating its discrimination and calibration using the area under the receiver operating characteristic curve (AUC), concordance index (C-index), and calibration curves. Results: The prognostic nomogram included age, SpO₂, mean blood pressure and creatinine. The C-index was 0.76 (95% CI 0.71 to 0.81) and AUCs for predicting 7-day, 14-day, and 28-day survival were 0.77 (95% CI 0.70 to 0.84), 0.75 (95% CI 0.68 to 0.81) and 0.72 (95% CI 0.62 to 0.82), respectively. The calibration curves demonstrated good concordance between the predicted outcomes and actual observations. Conclusion: A prognostic nomogram for COPD patients in ICU was developed with reasonable performance