Review
Open access
Sep 2026
Machine-learning-based prediction model of type 2 diabetes using liver enzymes: a cross-sectional study
ML models incorporating routinely measured liver enzymes improve T2D identification across US and Chinese datasets, indicating the potential utility of liver enzymes as accessible adjunctive indicators for diabetes risk stratification and improved T2D identification.
Ya-Ping Bi, Xiao-Jie Yuan, Yu-Feng Wang et al.
· Frontiers in Endocrinology · 0 citations