Association between the high-sensitivity C-reactive protein-triglyceride-glucose index and metabolic dysfunction-associated steatotic liver disease across different glycemic states

Figure 2 Feature importance analysis using the Boruta algorithm across glycemic states. A-D: Boruta algorithm results showing feature importance (Z-scores) for metabolic dysfunction-associated steatotic liver disease identification across different glycemic states: Total population (A), normal glucose regulation (B), prediabetes mellitus (C), and diabetes mellitus (D). NGR: Normal glucose regulation; Pre-DM: Prediabetes mellitus; DM: Diabetes mellitus; BMI: Body mass index; BRI: Body roundness index; WC: Waist circumference; CTI: C-reactive protein-triglyceride-glucose index; WHR: Waist to hip ratio; TyG: Triglyceride-glucose index; TG: Triglycerides; HOMA-IR: Homeostatic model assessment of insulin resistance; FINS: Fasting insulin; ALT: Alanine aminotransferase; HC: Hip circumference; HDL: High-density lipoprotein; UA: Uric acid; HbA1c: Glycated haemoglobin; HTG: Hypertriglyceridemia; FPG: Fasting plasma glucose; hs-CRP: High-sensitivity C-reactive protein; DBP: Diastolic blood pressure; SBP: Systolic blood pressure; AST: Aspartate aminotransferase; FIB-4: Fibrosis-4 index; Cr: Serum creatinine; APRI: Aspartate aminotransferase to platelet ratio index; NFS: Non-alcoholic fatty liver disease fibrosis score; ALB: Albumin; TP: Total protein; TCHO: Total cholesterol; PLT: Platelet count; eGFR: Estimated glomerular filtration rate; DBIL: Direct bilirubin; LDL: Low-density lipoprotein; TBIL: Total bilirubin; BUN: Blood urea nitrogen; HTN: Hypertension.