Skip to main content

Table 5 Results using 10-fold cross-validation for diabetes classification

From: A data-driven approach to predicting diabetes and cardiovascular disease with machine learning

Lab Year & Case Model AUC Precision Recall F1
No lab   Logistic Reg. 0.827 0.75 0.75 0.75
  1999-2014 SVM 0.849 0.77 0.77 0.77
  Diab. Case I Random Forest 0.855 0.78 0.78 0.78
   XGBoost 0.862 0.78 0.78 0.78
   Ensemble 0.859 0.78 0.78 0.78
   Logistic Reg. 0.732 0.67 0.67 0.67
  1999-2014 SVM 0.734 0.68 0.68 0.68
  Diab. Case II Random Forest 0.731 0.67 0.67 0.67
   XGBoost 0.734 0.67 0.67 0.67
   Ensemble 0.737 0.68 0.68 0.68
   Logistic Reg. 0.800 0.72 0.72 0.72
  2003-2014 SVM 0.822 0.75 0.75 0.75
  Diab. Case I Random Forest 0.841 0.77 0.76 0.76
   XGBoost 0.837 0.75 0.75 0.75
   Ensemble 0.834 0.75 0.75 0.75
   Logistic Reg. 0.718 0.66 0.66 0.66
  2003-2014 SVM 0.716 0.66 0.66 0.66
  Diab. Case II Random Forest 0.719 0.67 0.67 0.66
   XGBoost 0.725 0.67 0.67 0.67
   Ensemble 0.725 0.66 0.66 0.66
With lab   Logistic Reg. 0.866 0.79 0.79 0.79
  1999-2014 SVM 0.887 0.81 0.81 0.81
  Diab. Case I Random Forest 0.937 0.86 0.86 0.86
   XGBoost 0.957 0.89 0.89 0.89
   Ensemble 0.944 0.87 0.87 0.87
   Logistic Reg. 0.724 0.67 0.67 0.67
  1999-2014 SVM 0.737 0.68 0.68 0.68
  Diab. Case II Random Forest 0.738 0.68 0.68 0.68
   XGBoost 0.802 0.74 0.74 0.74
   Ensemble 0.783 0.71 0.71 0.71
   Logistic Reg. 0.877 0.80 0.80 0.80
  2003-2014 SVM 0.882 0.81 0.80 0.80
  Diab. Case I Random Forest 0.939 0.86 0.86 0.86
   XGBoost 0.962 0.89 0.89 0.89
   Ensemble 0.948 0.88 0.88 0.88
   Logistic Reg. 0.738 0.68 0.68 0.68
  2003-2014 SVM 0.737 0.68 0.68 0.68
  Diab. Case II Random Forest 0.740 0.68 0.68 0.67
   XGBoost 0.834 0.75 0.75 0.75
   Ensemble 0.798 0.72 0.72 0.72
  1. AUC - Area Under the Curve, \(Precision = \frac {TP}{TP + FP}, Recall = \frac {TP}{TP + FN}\) (where TP - True Positive, FP - False Positive, FN - False Negative), and F1 (score) = \(2\frac {precision*recall}{precision + recall}\). Bold face font signifies best performing model result