Skip to main content

TABLE 6 Performance of optimized ML methods

From: Improvement of APACHE II score system for disease severity based on XGBoost algorithm

Abbreviation Accuracy
[95% Cl]
Precision
[95% Cl]
Recall
[95% Cl]
F1
[95% Cl]
SVM* 0.774 ± 0.003
[0.770, 0.779]
0.826 ± 0.004
[0.820, 0.832]
0.774 ± 0.003
[0.770, 0.779]
0.794 ± 0.003
[0.790, 0.798]
LR* 0.739 ± 0.004
[0.734, 0.744]
0.840 ± 0.004
[0.834, 0.846]
0.739 ± 0.004
[0.734, 0.744]
0.770 ± 0.003
[0.766, 0.775]
NB* 0.840 ± 0.005
[0.833, 0.847]
0.814 ± 0.007
[0.805, 0.824]
0.840 ± 0.005
[0.833, 0.847]
0.822 ± 0.006
[0.815, 0.830]
ANN* 0.863 ± 0.004
[0.856, 0.869]
0.841 ± 0.009
[0.829, 0.853]
0.863 ± 0.005
[0.856, 0.869]
0.832 ± 0.007
[0.823, 0.841]
RF* 0.857 ± 0.003
[0.853, 0.862]
0.859 ± 0.003
[0.854, 0.863]
0.859 ± 0.003
[0.855, 0.864]
0.860 ± 0.004
[0.855, 0.865]
XGBoost* 0.867 ± 0.004
[0.860, 0.872]
0.846 ± 0.007
[0.836, 0.856]
0.867 ± 0.004
[0.860, 0.872]
0.841 ± 0.006
[0.832, 0.850]
  1. * The data set used for model building contains 19 feature variables