RESUMO
BACKGROUND: To explore the risk factors and prognostic factors related to the acute-on-chronic liver failure (ACLF) occurrence and adverse outcome after withdrawal of nucleos(t)ide analogs (NAs) in chronic hepatitis B (CHB) patients. METHODS: Hospitalized CHB patients with relapse after NAs withdrawal at our medical center were retrospectively included in the present study from January 2011 to May 2018. Logistic regression, Cox regression analysis, Kaplan-Meier log-rank test, and area under the receiver operating characteristic curves (AUROC) were used. RESULTS: A total of 389 CHB patients (including 46 ACLF patients) were included. Their median age was 48.0 years; 315 patients were male and 74 were female. The age ≥30 years and HBVDNA ≤1000 copies at admission in logistic regression were the independent risk factors for ACLF after NAs withdrawal in CHB patients. In patients who developed ACLF, only the model of end-stage liver disease combining serum natrium concentration (MELD-Na) score and relapse after Lamivudine (LAM) cessation in the Cox multivariate regression analysis were independent predictors for 12-week mortality. The artificial liver support system (ALSS) showed no improvement in the 12-week survival of ACLF patients. We further defined 22.35 as the optimal cutoff value of MELD-Na score to predict 12-week mortality for ACLF patients, with the AUROC of 0.817, a sensitivity of 76.5%, and a specificity of 75.9%. CONCLUSION: The age ≥30 years and HBVDNA ≤1000 copies at admission strongly correlate with occurrence of ACLF, and higher MELD-Na score and relapse after LAM withdrawal are closely related with 12-week mortality among patients with ACLF after NAs withdrawal.