Development and Validation of a Nomogram to Predict Recompensation in Patients With HBV‐Related Acute‐on‐Chronic Liver Failure: A Multicenter Retrospective Study

Limited studies have investigated the predictors of hepatic recompensation in patients with hepatitis B virus (HBV)-related acute-on-chronic liver failure (ACLF). Establishing a clinically applicable predictive model for recompensation in ACLF patients is of critical importance. A total of 304 HBV-ACLF patients were included in the study, 169 patients as training cohort and 135 patients as validation cohort. In the training cohort, 72 patients (42.6%) achieved recompensation within the first year following an ACLF episode, whereas 87 patients (64.4%) in the validation cohort achieved recompensation during the same period. Age, alpha-fetoprotein, total bilirubin, white blood cell count, hepatic encephalopathy, and gastrointestinal bleeding were selected for inclusion in the model. The nomogram demonstrated excellent discriminative ability, with an area under the curve (AUC) of 0.842 (95% CI: 0.784-0.900) in the training cohort and 0.855 (95% CI: 0.785-0.926) in the validation cohort. Calibration curves showed strong agreement between predicted and observed recompensation rates. DCA further confirmed the model's clinical utility for decision-making. This model demonstrated superior predictive performance compared to the MELD score, MELD-Na score, and MELD 3.0 score. The developed nomogram provides an accurate and clinically applicable tool for predicting recompensation likelihood, enhancing personalized management of HBV-ACLF patients.