Development of a Predictive Model for Liver Fibrosis Risk in Diabetic Fatty Liver Patients Based on Ultrasound Elastography
Objective:To develop a nomogram prediction model based on ultrasound elastography for quantitatively assessing the risk of liver fibrosis progression in patients with type 2 diabetes mellitus (T2DM) and fatty liver. Methods:A retrospective analysis was conducted on the clinical data of 318 T2DM patients with fatty liver treated at our hospital. Liver stiffness measurements (LSM) were obtained using shear wave elastography (SWE) technology,and detailed clinical data and laboratory test results were collected. Multivariate Logistic regression analysis was employed to identify independent factors associated with liver fibrosis. Based on these factors,a nomogram prediction model was constructed and its accuracy and calibration were validated using Bootstrap resampling. Results:Body mass index (BMI),glycated hemoglobin (HbA1c),alanine aminotransferase (ALT),and platelet count (PLT) were identified as independent factors for liver fibrosis progression. The constructed nomogram prediction model demonstrated high accuracy in both discrimination and calibration,with an area under the receiver operating characteristic curve (AUC) of 0.882,indicating strong predictive capability. Conclusion:Combining ultrasound elastography with a nomogram model effectively assesses the risk of liver fibrosis progression in T2DM patients with fatty liver,aiding in the early identification of high-risk patients,providing personalized intervention measures,and improving long-term prognosis.
万方数据
维普
