Skip to main content

Table 4 Performance comparisons of nine severity score models for predicting in-hospital mortality estimated using MIMIC-III test set

From: OASIS +: leveraging machine learning to improve the prognostic accuracy of OASIS severity score for predicting in-hospital mortality

Method

ACC (%)

Sn

Sp

MCC

AUC

Threshold

APSIII

89.4

0.16

0.98

0.24

0.78

0.27

LODS

89.0

0.17

0.97

0.23

0.75

0.30

MLODS

89.3

0.12

0.98

0.19

0.74

0.24

OASIS

69.4

0.70

0.69

0.25

0.77

0.49

QSOFA

39.1

0.81

0.34

0.10

0.59

0.67

SAPS

71.6

0.62

0.73

0.23

0.74

0.48

SAPSII

88.0

0.29

0.95

0.28

0.80

0.35

SIRS

20.4

0.94

0.12

0.06

0.61

1.00

SOFA

88.6

0.17

0.97

0.21

0.72

0.27

Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us