Nomogram model of mortality risk in patients with chronic obstructive pulmonary disease in intensive care unit: based on MIMIC-IV database and external validation study.

Objective: Chronic obstructive pulmonary disease (COPD) is a common respiratory disease with high incidence and mortality rates. This study aims to identify independent risk factors affecting the mortality risk of COPD patients and construct and validate a nomogram model to provide treatment guidance for COPD patients. Methods: Data from COPD patients in the intensive care unit (ICU) were obtained from the Medical Information Mart for Intensive Care-IV (MIMIC-IV) and the eICU Collaborative Research Database (eICU-CRD). The MIMIC-IV dataset was randomly divided into training and testing sets in a 7:3 ratio for model development and evaluation. External validation was performed using the eICU-CRD dataset. Independent prognostic factors were determined using multivariable Cox regression analysis and incorporated into the nomogram. The performance and clinical applicability of the prediction model were evaluated using the concordance index, receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA). Results: The MIMIC-IV dataset included 2036 COPD patients, and the eICU-CRD dataset included 13,053 COPD patients. The constructed nomogram model included 7 variables: age, weight, APSIII score, ventilation duration, potassium ion, anion gap, and international normalized ratio. Among these factors, ventilator time was a protective factor, while the remaining six factors were independent risk factors. The nomogram demonstrated good accuracy with C-index values of 0.862, 0.874, and 0.722 in the training set, testing set, and external validation set, respectively. The ROC curve indicated good predictive performance of the nomogram model, and the calibration curve and DCA further confirmed the reliability and clinical utility. Conclusion: This study established a simple and effective nomogram model consisting of 7 variables for evaluating the short-term mortality risk of COPD patients. It provides better recommendations for clinical decision-making and improves the short-term survival rate of COPD patients.