The accuracy of prediction result based different selected set of features by XGBoost algorithm. Abbreviations: Duration, Duration of diabetes; BMI, Body Mass Index; FPG, Fasting plasma glucose; FINS, Fasting Insulin; HbA1c, Glycated hemoglobin A1c; C–P, c-peptide; Cr, Serum creatinine; UALB/Ucr, Urine albumin creatinine ratio; UA, Serum uric acid; Ca, Calcium; P, Phosphorus; OC, Osteocalcin; CTX, C-terminal telopeptide of type I collagen; PINP, N-terminal propeptide of type I procollagen; LDL-C, low-density lipoprotein cholesterol; HDL-C, High-density lipoprotein cholesterol; SBP, Systolic blood pressure; DBP, Diastolic blood pressure; ALP, Alkaline phosphatase; TG, Triglyceride; TC, Totalcholesterol; Alb, Albumin; ALT, Alanine aminotransferase; AST, Aspartate aminotransferase; GGT, γ-glutamyltransferase; 25-OH-VD, 25-hydroxyvitamin vitaminD; PTH, Parathyroid hormone; BMD1, Bone Mineral Density at the lumbar spines (L1-L4); BMD2, Bone Mineral Density at the distal radius; BMD3, Bone Mineral Density at the femoral neck; BMD4, Bone Mineral Density at the Ward's triangle; BMD5, Bone Mineral Density at the greater trochanter; BMD6, Bone Mineral Density at the total hip.