〔Abstract〕 Objective To investigate hepatocellular carcinoma(HCC) risk factors in hepatitis B e antigen(HBeAg)-negative cirrhotics,and to develop and validate a predictive model using these indicators.Methods A total of 649 hospitalized patients with HBeAg-negative hepatitis B cirrhosis and HBeAg-negative primary HCC were enrolled.Patients were randomly divided into a modeling group(n=298) and a validation group(n=351) at a 7:3 ratio.Logistic regression analysis was used to screen for independent predictors of HCC occurrence.A predictive model was constructed and validated using receiver operating characteristic(ROC) curves.The clinical net benefit of the prediction model was assessed via decision curve analysis.Results Univariate analysis showed significant statistical differences between the modeling and validation groups in serum alanine aminotransferase(ALT),aspartate aminotransferase(AST),triglycerides(TG),gamma-glutamyl transferase(GGT),red blood cell count(RBC),hemoglobin(Hb),platelet count(PLT),international normalized ratio(INR),alpha-fetoprotein(AFP),serum calcium(Ca2+),serum cholinesterase(CHE),and HBV DNA levels.Multivariate logistic regression analysis identified AST,GGT,Hb,PLT,Ca2+,CHE,and HBV DNA as independent influencing factors for HCC occurrence(P