Developing and validating a Diagnostic Model for Predicting Pneumonia Risk Following Traumatic Spinal Cord Injury
Objective The aim of this study was to analyze the risk factors for pneumonia in patients with traumatic spinal cord injury(TSCI)and construct and validate a predictive model for assessing the risk of pneu-monia occurrence in TSCI patients.Methods This single-center retrospective clinical study included TSCI patients admitted to the First Affiliated Hospital of Guangxi Medical University between January 1,2016,and December 31,2020.Patient histories,clinical characteristics,laboratory test results,and imaging results are all recorded.Logistic regression analysis was employed to identify risk factors for pneumonia in TSCI patients.A predictive model was constructed based on these risk factors and validated using the receiver operating char-acteristic(ROC)curve,decision curve analysis(DCA),and calibration curve.Results A total of 469 TSCI patients were initially included,and after excluding cases with incomplete data,459 patients were finally ana-lyzed and randomly divided into a training set(322 cases)and a validation set(137 cases)at a 7∶3 ratio.A-mong the 459 patients,221(48.15％)developed pneumonia.Final logistic regression analysis showed that complete spinal cord injury,fever,abnormal white blood cell count(WBC)and abnormal serum albumin levels were independent risk factors for pneumonia in TSCI patients.The area under the curve(AUC)for the train-ing set was 0.819,and for the validation set,it was 0.774.Conclusion The developed prediction model demonstrated good predictive performance.Complete spinal cord injury,fever,WBC and serum albumin(ALB)levels may serve as predictive factors for pneumonia following TSCI.
万方数据
维普
