Systematically analysis of decompensated cirrhotic patients with spontaneous bacterial peritonitis to identify diagnostic and prognostic indexes

Abstract Background Spontaneous bacterial peritonitis (SBP) is a common complication in patients with cirrhosis. The diagnosis of SBP is still mostly based on ascites cultures and absolute ascites polymorphonuclear (PMN) cell count, which restricts the widely application in clinical settings. This study aimed to identify reliable and easy-to-use biomarkers for both diagnosis and prognosis of cirrhotic patients with SBP. Methods We conducted a retrospective study including 413 cirrhotic patients from March 2013 to July 2022 in the First Affiliated Hospital of Guangxi Medical University. Patients’ clinical characteristics and laboratory indices were collected and analyzed. Two machine learning methods (Xgboost and LASSO algorithms) and a logistic regression analysis were adopted to screen and validate the indices associated with the risk of SBP. A predictive model was constructed and validated using the estimated area under curve (AUC). The indices related to the survival of cirrhotic patients were also analyzed. Results A total of 413 cirrhotic patients were enrolled in the study, of whom 329 were decompensated and 84 were compensated. 52 patients complicated and patients with SBP had a poorer Child–Pugh score (P