Development of a machine learning-based model for prediction of diabetes risk in patients with metabolic dysfunction-associated steatotic liver disease (MASLD)

Key Points

• The model effectively identifies high diabetes risk in individuals with MASLD, enhancing early detection efforts.
• Using the LightGBM algorithm, accuracy and interpretability significantly improved, providing a robust predictive tool.
• Key predictors like Ualb and LAP reveal the essential role of renal and metabolic markers in diabetes risk assessment.
• This approach may enable more individualized interventions and informed clinical decision-making for at-risk populations.