Skip to main content

Table 2 Performance of machine learning models in identifying patients with preeclampsia (Independent dataset)

From: A cost-effective machine learning-based method for preeclampsia risk assessment and driver genes discovery

Base

classifier

Feature

selection

Feature number

Accuracy (%)

Precision (%)

Recall (%)

F1-measure (%)

MLP

LASSO

497

94.30

94.95

94.35

94.65

SVM

LASSO

497

94.28

95.33

93.36

94.58

RFC

LASSO

497

92.76

93.62

92.76

93.18

XGBoost

LASSO

497

91.23

92.71

90.71

91.70

Ensemble model

LASSO

497

94.62

95.83

94.56

94.95