Using Demographic Factors and Comorbidities to Develop a Predictive Model for ICU Mortality in Patients with Acute Exacerbation COPD.

Abstract

Recognizing factors associated with mortality in patients admitted to the ICU with acute exacerbation of chronic obstructive pulmonary disease could reduce healthcare costs and improve end-of-life care. Previous studies have identified possible predictive variables, but analysis is lacking on the combined effect of demographic factors and comorbidities. Using the MIMIC-III database, this study examined factors associated with mortality in a model incorporating comorbidities, comorbidity indices, and demographic factors. After determining associations between predictive variables and mortality through univariate and multivariate binomial logistic regression, three predictive models were developed: (1) univariate GLM-derived logistic, (2) Mean Gini-derived logistic (MGDL), and (3) random forest. The MGDL model best predicted mortality with an AUROC of 0.778. Variables with the greatest relative importance in determining mortality included the Charlson Comorbidity Index, Elixhauser Index, male, and arrhythmia. The results support the potential of using the MGDL model and need for further work in exploring demographic factors.