Objective：To develop a predictive model for significant liver fibrosis based on serological markers in the population with non - alcoholic fatty liver disease（NAFLD）. Methods：A total of 2 543 NAFLD patients from the he National Health and Nutrition Examination Survey（NHANES）database in the United States were selected. These patients were randomly divided into a training set and an internal validation set in a 7∶3 ratio. Chi-square tests，univariate analysis，and binary logistic regression analysis（stepwise）were performed on both sets using SPSS 26.0，followed by model evaluation and validation in R 4.3.1. Results：Age，gender，hip circumference，ferritin，aspartate aminotransferase（AST），gamma-glutamyl transferase（GGT），and cardiometabolic index（CMI）were identified as independent risk factor for significant liver fibrosis in NAFLD patients，respectively the predictive model aCHANGE demonstrated good performance in both the training and validation sets，with an area under the curve（AUC）of the receiver operating characteristic（ROC）curve of 0.775 in both sets. The calibration curves and decision curve analysis（DCA）also showed good results. Conclusion：The aCHANGE model is useful for predicting the risk of significant liver fibrosis in NAFLD patients.