Construction and Validation Study of a Model for Predicting the Risk of Pulmonary Complications in Elderly Patients with Multiple Rib Fractures.

OBJECTIVE: Given the high incidence of pulmonary complications and poor prognosis in patients with multiple rib fractures, we have developed a risk prediction model for pulmonary complications in patients with MRF. In order to identify the high-risk groups prone to pulmonary complications as early as possible, we will intervene in advance and provide targeted interventions to improve patients' quality of life and disease prognosis.

METHODS: The prospective cohort study design scheme was used to collect data information based on the hospital's electronic medical record system. The constructed cohort included 314 cases, and the validation cohort included 119 patients with MRF. The risk prediction model for pulmonary complications in patients with MRF was established using the backward screening method and multivariate logistic regression analysis. The predictive quality and clinical utility of the model were assessed using AUC, sensitivity, specificity, calibration curves, and clinical decision curves.

RESULTS: Seven predictors were finally included after multivariate logistic regression analysis: age, smoking history, diabetes mellitus, presence of other fracture combinations, serum albumin, treatment modality, and presence of underlying lung disease. The construction of the cohort yielded an AUC of 0.928 (95% CI 0899-0.956; P < .001) for the present model, with a sensitivity of 81.2% and a specificity of 76.8%, while the external validation cohort yielded an AUC of 0.942 (95% CI 0.900-0.983; P < .001), with a sensitivity of 76.7% and a specificity of 78.4%, and the H-L chi-squared tests all showed P > .05.

CONCLUSIONS: The column-line diagram model of pulmonary complications in patients with MRF constructed in this study showed good discriminative and calibration performance in both internal and external validation, which is helpful for clinicians to identify individuals at high risk of pulmonary complications as early as possible, and thus can be recommended for clinical use.