Development and Validation of a Machine Learning–Based Prediction Model for Cardiovascular Disease in Patients with Metabolic Dysfunction–Associated Fatty Liver Disease

The findings confirm that traditional cardiovascular risk assessment approaches are insufficient for MAFLD patients, as liver-specific markers-particularly hepatic fibrosis (NFS) and liver synthetic function (albumin)-dominated cardiovascular risk prediction over conventional risk factors (hypertension, diabetes, smoking). This paradigm shift underscores the necessity of integrated liver-heart assessment in MAFLD and supports routine hepatic fibrosis evaluation for cardiovascular risk stratification. The model demonstrates immediate clinical applicability through existing electronic health records, enabling early identification of high-risk patients for targeted preventive interventions.