Skip to main content

Table 4 C-index for 1 year or more mortality

From: The predictive value of machine learning for mortality risk in patients with acute coronary syndromes: a systematic review and meta-analysis

No

Model

Training cohort

Validation cohort

Number of models

C-index (95% CI)

Number of models

C-index (95% CI)

1

LR

23

0.8266 [0.8070; 0.8466]

11

0.8110 [0.7974; 0.8249]

2

RF

7

0.8623 [0.8284; 0.8975]

8

0.8127 [0.7898; 0.8362]

3

ANN

5

0.8172 [0.7804; 0.8557]

6

0.8454 [0.7989; 0.8946]

4

DT

8

0.8281 [0.7865; 0.8719]

3

0.7868 [0.7383; 0.8384]

5

SVM

7

0.8195 [0.7814; 0.8594]

6

0.7972 [0.7491; 0.8484]

6

XGBoost

3

0.8619 [0.8051; 0.9226]

2

0.8075 [0.7776; 0.8385]

7

NB

2

0.8930 [0.8621; 0.9249]

  

8

AdaBoost

1

0.9100 [0.9001; 0.9201]

3

0.8905 [0.8248; 0.9615]

9

KNN

1

0.7840 [0.7498; 0.8198]

  

10

Other

1

0.9240 [0.9190; 0.9290]

2

0.8869 [0.8581; 0.9166]

11

Overall

58

0.8352 [0.8214; 0.8493]

41

0.8197 [0.8042; 0.8354]