Table 6 Comparison with existing models
From: Machine learning for predicting diabetes risk in western China adults
Author | Feature | Method | AUC |
|---|---|---|---|
Gao et al. [30] | Age, Sex, WC, Systolic pressure and PDM | LR | 0.635 |
Yang et al. [8] | BMI, FGB, Waist-toheight ratio, Age, Mean systolic pressure, Urine glucose | XGBoost | 0.881 |
Zhou et al. [31] | Age, Sex, Systolic pressure, BMI, WC, PDM | LR | 0.748 |
Ravaut et al. [16] | demographics, routine diagnosis codes and history, laboratory values, geographical information prescription history, information on the specialty of each doctor encounter, and hospitalizations | XGBoost | 80.26 |
This study | Sex, Age, Ethnicity, EH, SS, HTN, CAD, PDM, WC, BMI, WBC, PLT, FBG, ECG, TC, TG, LDLC, HDLC | XGBoost | 0.9122 |