Abstract
Background and Objectives: Urinary tract infection (UTI) is a common comorbidity in diabetic patients, making up one of the causes of sepsis. This study aims to develop a nomogram to predict the risk probability of sepsis in diabetic patients with UTI (DPUTIs). Materials and Methods: This is a retrospective observational study. Clinical data for DPUTIs were extracted from the Medical Information Mart for Intensive Care IV database. Eligible DPUTIs were randomly divided into training and validation cohorts in a 7:3 ratio. Independent prognostic factors for sepsis risk were determined using least absolute shrinkage and selection operator (LASSO) regression and multivariate logistic regression. A corresponding nomogram based on these factors was constructed to predict sepsis occurrence in DPUTIs. The discrimination of the nomogram was assessed by multiple indicators, including the area under the receiver operating characteristic curve (AUC), net reclassification improvement index (NRI), and integrated discrimination improvement (IDI). In addition, a calibration curve and decision curve analysis (DCA) were used to evaluate the performance of the nomogram. Results: A total of 1990 DPUTIs were included. Nine independent prognostic factors were identified as predictive factors for sepsis risk in DPUTIs. The prognostic factors included urine red blood cell classification (urine RBC cat), urine white blood cell classification (urine WBC cat), blood glucose, age, temperature, white blood cells (WBCs), sequential organ failure assessment (SOFA) score, lymphocytes, and hematocrit. The AUC, NRI, and IDI of the nomogram indicated robust discrimination. The calibration curve and Hosmer-Lemeshow test showed good calibration of the nomogram. The DCA curve demonstrated a better clinical utility of the nomogram. Conclusions: The nomogram established in this study helps clinicians predict the probability of sepsis in DPUTIs, providing evidence for optimizing the management of related risk factors.