Table 3.
Performances of RF and LR on the three test sets
| Test Set | Tool | AUC | Accuracy [IC95%] | Sens | Spec | PPV | NPV | F-m | MCC |
|---|---|---|---|---|---|---|---|---|---|
| # 1 | RF | .8988 | .8314 [.8381-.8246] | .8354 | .8274 | .8298 | .8331 | .8326 | .6629 |
| LR | .8770 | .8118 [.8188-.8047] | .8410 | .7825 | .7957 | .8301 | .8177 | .6246 | |
| # 2 | RF | .90 | .8310 [.8377-.8242] | .8370 | .8250 | .8282 | .8340 | .8325 | .6621 |
| LR | .8752 | .8121 [.8190-8049] | .8464 | .7775 | .7931 | .8340 | .8189 | .6255 | |
| # 3 | RF | .9035 | .8344 [.8422-8262] | .8406 | .8280 | .8311 | .8377 | .8358 | .6687 |
| LR | .8833 | .8168 [.8250-.8083] | .8459 | .7875 | .8003 | .8355 | .8225 | .6346 |
Performances of the Random Forest (RF) and Logistic Regression (LR) on the three test sets. Area under the curve (AUC), accuracy with 95% confidence interval, sensitivity (Sens), specificity (Spec), Positive Predictive Value (PPV), Negative Predictive Value (NPV), F-measure (F-m) and Matthews correlation coefficient (MCC) are reported for each method.