Skip to main content

Table 6 Accuracy for 30-day 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

Accuracy (95% CI)

Number of models

ACC (95% CI)

1

LR

4

0.7893 [0.6364; 0.8891]

3

0.8095 [0.7946; 0.8236]

2

RF

1

0.8429 [0.8289; 0.8560]

5

0.8533 [0.7843; 0.9029]

3

ANN

1

0.7669 [0.7623; 0.7714]

  

4

DT

3

0.8209 [0.6871; 0.9054]

  

5

SVM

  

3

0.8014 [0.7862; 0.8157]

6

NB

3

0.8845 [0.8104; 0.9321]

  

7

AdaBoost

1

0.8088 [0.7937; 0.8230]

  

8

BN

2

0.9212 [0.9068; 0.9335]

  

9

Other

2

0.6536 [0.5015; 0.7797]

  

10

Overall

17

0.8257 [0.7694; 0.8707]

11

0.8282 [0.7922; 0.8591]