Establishment of a Predictive Model for Acute Respiratory Distress Syndrome in Patients with Bacterial Pneumonia

Background: Community -acquired pneumonia (CAP) is a global health concern due to its high rates of morbidity and mortality. Bacterial pathogens are common causes of CAP. It is one of the most common causes of acute respiratory distress syndrome (ARDS), a common severe respiratory system manifestation threatening human health. This study aimed to establish a predictive model for ARDS in patients with bacterial pneumonia, which was conducive to early identification of the occurrence and effective prevention of ARDS. Methods: We collected the clinical data of hospitalized patients with bacterial pneumonia in Affiliated Huzhou Hospital of Zhejiang University School of Medicine from January 2022 to November 2022. The independent risk factors for ARDS in patients with bacterial pneumonia were determined by univariate and multivariate binary logistic regression analyses. The nomogram was constructed to display the predictive model, and the receiver -operating characteristic curve was plotted to evaluate the predictive value of ARDS. Results: This study included 254 patients with bacterial pneumonia, of which 114 developed ARDS. The multivariate logistic regression analysis revealed age [odds ratio (OR) = 1.041, P = 0.003], heart rate (OR = 1.020, P = 0.028), lymphocyte count (OR = 0.555, P = 0.033), white blood cell count (OR = 1.062, P = 0.033), bilateral lung lesions (OR = 7.352, P = 0.011) and pleural effusion (OR = 2.512, P = 0.002) as the independent risk factors for ARDS. The predictive model was constructed based on the six independent factors, which was valuable in predicting ARDS with area under the curve of 0.794. Conclusion: The predictive model was beneficial to evaluate the disease progression in patients with bacterial pneumonia and identify ARDS. Further, our nomogram might help doctors predict the incidence of ARDS and conduct treatment as early as possible.