S2430 Development and Validation of a Composite MASLD Risk Index (MCRI) in Patients With Type 2 Diabetes Mellitus: A Step Beyond FIB-4

Introduction: FIB-4 is widely used to assess fibrosis risk in patients with Type 2 Diabetes Mellitus (T2DM), but it relies on limited input variables and may misclassify risk. We aimed to develop and validate a novel MASLD Composite Risk Index (MCRI) that incorporates broader clinical and metabolic parameters to improve fibrosis risk stratification. Methods: We retrospectively analyzed 1,149 adult patients with T2DM seen in outpatient clinics. Elevated fibrosis risk was defined as FIB-4 >1.3. Eight variables (age, sex, race, BMI, A1c, aspartate aminotransferase [AST], alanine aminotransferase, and platelets) were used to construct the MCRI using LASSO-penalized logistic regression. The model was trained to predict high FIB-4 as a surrogate for significant fibrosis. Performance was assessed using AUC, calibration plots, and comparison against the binary FIB-4 threshold. Results: MCRI retained 6 features after penalization (age, race, BMI, A1c, AST, and platelets). It achieved an AUC of 0.82, significantly outperforming the FIB-4 threshold alone (AUC = 0.51). Calibration analysis showed strong agreement between predicted and observed risk probabilities. The MCRI also maintained discriminatory power across sex and race subgroups, suggesting robust generalizability. Conclusion: The MCRI is a promising risk stratification tool that improves upon FIB-4 by integrating metabolic and demographic information. Its superior performance and strong calibration suggest it may better identify T2DM patients at risk for advanced fibrosis, and support referral and imaging decisions in MASLD screening strategies.