Table 9 Areas under the ROC curves for the three models
From: Application of three statistical models for predicting the risk of diabetes
Predictive model | Accuracy | AUC | SE | 95%Cl | P | AIC |
|---|---|---|---|---|---|---|
Logistic Regression model | 90.8 | 0.711 | 0.0137 | 0.697–0.724 | < 0.0001 | 293.178 |
BP Neural network model | 91.2 | 0.780 | 0.0128 | 0.767–0.792 | < 0.0001 | 281.895 |
Decision tree model | 90.7 | 0.698 | 0.0136 | 0.684–0.712 | < 0.0001 | 343.877 |