Abstract
OBJECTIVE: To construct and validate a nomogram prediction model for the risk of cefoperazone sodium/sulbactam sodium (CPZ/SAM)-related coagulation disorders in hospitalized patients. METHODS: Patients treated with CPZ/SAM from January 2022 to December 2024 were enrolled and divided into a coagulation disorder group and a control group based on the occurrence of coagulation disorders. Clinical data were collected to identify risk factors and construct a nomogram model, which was validated using the Hosmer-Lemeshow goodness-of-fit test, receiver operating characteristic (ROC) curve, decision curve analysis (DCA), and clinical impact curve. RESULTS: A total of 439 patients were included, with 86 cases (19.59%) in the coagulation disorder group and 353 cases in the control group. Multivariate analysis identified malnutrition, recent bleeding history, prolonged treatment duration with CPZ/SAM, combination use with carbapenems, and elevated serum creatinine as independent risk factors. The constructed nomogram had an AUC of 0.845, demonstrating good calibration ability (χ²=2.312, P=0.891), providing moderate net benefit in predicting the incidence of coagulation disorders, with consistent agreement between predicted and actual probabilities. CONCLUSION: The nomogram model effectively identifies high-risk patients, indicating that attention should be paid to the risk of coagulation disorders in patients with the above risk factors during CPZ/SAM treatment.