Objective To explore the incidence of immune checkpoint inhibitors (ICIs)-related adverse events (irAEs) in patients with advanced hepatocellular carcinoma (HCC), and to develop and validate a risk prediction model.Methods A retrospective analysis was conducted on the clinical data of 186 HCC patients treated with ICIs between June 2018 and June 2023. The patients were divided into the irAE group and the control group based on whether they experienced an irAE. Logistic regression was employed to identify independent factors influencing the occurrence of irAEs in patients with advanced HCC and to construct a risk prediction model. Furthermore, the model was validated using the Bootstrap internal validation method and the area under the receiver operating characteristic curve (ROC).Results A total of 71 patients with advanced HCC who received ICIs developed irAEs. Univariate and multivariate Logistic regression analysis of the two groups revealed that age, Child-Pugh score, clinical stage, prognostic nutritional index (PNI), systemic immune inflammation index (SII), and treatment regimen were independent factors influencing the occurrence of irAEs in patients. Based on these findings, a nomogram model for predicting the risk of irAEs was constructed, with a mean absolute error of 0.02. The performance of this model was evaluated using ROC, resulting in an area under the curve (AUC) of 0.891 (95% CI: 0.845-0.937). The optimal cut-off value was 280, with a sensitivity of 83.10% and a specificity of 80.87%.Conclusion Age, Child-Pugh score, clinical stage, PNI, SII, and treatment regimen were independent factors influencing the occurrence of irAEs in HCC patients after ICIs treatment. The nomogram model constructed based on these factors could effectively predict the risk of irAEs in patients with advanced HCC, demonstrating significant clinical value.