Development and validation of a nomogram for pneumonia risk in burn patients with inhalation injury: a multicenter retrospective cohort study.

Background: Burn patients with inhalation injury are at higher risk of developing pneumonia, and yet there is no reliable tool for the assessment of the risk for such patients at admission. This study aims to establish a predictive model for pneumonia risk for burn patients with inhalation injury based on clinical findings and laboratory tests.

Method: This retrospective study enrolled 546 burn patients with inhalation injury. They were grouped into a training cohort and a validation cohort. The least absolute shrinkage and selection operator (LASSO) regression analysis and binary logistic regression analysis were utilized to identify risk factors for pneumonia. Based on the factors, a nomogram for predicting pneumonia in burn patients with inhalation injury was constructed. Areas under the receiver operating characteristic curves (AUC), calibration plots, and decision curve analysis (DCA) were used to evaluate the efficiency of the nomogram in both the training and validation cohorts.

Results: The training cohort included 432 patients, and the validation cohort included 114 patients, with a total of 225 (41.2%) patients experiencing pneumonia. Inhalation injury, tracheal intubation/tracheostomy, low serum albumin, and high blood glucose were independent risk factors for pneumonia in burn patients with inhalation injury and they were further used to build the nomogram. The AUC of the nomogram in the training and validation cohorts were 0.938 (95% CI: 0.917-0.960) and 0.966 (95% CI: 0.931-1), respectively. The calibration curve for probability of pneumonia showed optimal agreement between the prediction by nomogram and the actual observation, and the DCA indicated that the constructed nomogram conferred high clinical net benefit.

Conclusion: This nomogram can accurately predict the risk of developing pneumonia for burn patients with inhalation injury, and help professionals to identify high-risk patients at an early stage as well as to make informed clinical decisions.