Skip to main content

Table 4 Performance of prediction models on MIMIC III

From: Utilizing imbalanced electronic health records to predict acute kidney injury by ensemble learning and time series model

Model

AUC

Sensitivity

F1-score

AP

 

24h

48h

24h

48h

24h

48h

24h

48h

ETSM

0.95

0.95

0.95

0.98

0.96

0.98

0.98

0.98

AdaBoost

0.89

0.93

0.93

0.97

0.93

0.96

0.98

0.98

Random Forest

0.78

0.78

0.91

0.97

0.86

0.91

0.93

0.97

Naive Bayes

0.67

0.65

0.61

0.66

0.68

0.73

0.82

0.86

k-Nearest Neighbor

0.72

0.82

0.64

0.83

0.76

0.88

0.83

0.93