Machine Learning‐Based Risk Stratification for Metabolic Dysfunction Severity Among Diabetic Patients With Established MASLD: Distinguishing Normal‐Weight From Overweight Individuals | Synapse
April 17, 2026Open Access
Machine Learning‐Based Risk Stratification for Metabolic Dysfunction Severity Among Diabetic Patients With Established MASLD: Distinguishing Normal‐Weight From Overweight Individuals
Key Points
This research aims to utilize machine learning for assessing metabolic dysfunction severity in diabetic patients with established MASLD.
Applied gradient boosting as a predictive model.
Focused on patients with established MASLD and varying BMI.
Conducted risk stratification to differentiate between normal-weight and overweight individuals.
Identified gradient boosting as the optimal model for predictive accuracy.
Demonstrated effective risk assessment tailored for metabolic dysfunction among diabetic patients.
Provided insights for healthcare professionals in managing MASLD based on patient BMI.
Abstract
Gradient boosting is the optimal predictive model, which can assist healthcare professionals in risk assessment and management for diabetic MASLD patients with normal BMI.