Objective: To develop a predictive model for significant liver fibrosis in NAFLD patients based on serological markers. Methods: A total of 2,543 NAFLD patients from the NHANES database in the United States were selected and 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, AST, GGT, and CMI were identified as independent risk factors for significant liver fibrosis in NAFLD patients. The aCHANGE model demonstrated good performance in both the training and validation sets, with an area under the ROC curve of 0.775 in the training set and 0.775 in the validation set, showing satisfactory results in calibration and Decision Curve Analysis (DCA). Conclusion: The aCHANGE model is useful for predicting the risk of significant liver fibrosis in NAFLD patients.