Skip to main content

Table 1 C-index for in-hospital 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

25

0.8603 [0.8330; 0.8886]

21

0.8576 [0.8284; 0.8878]

2

RF

9

0.8370 [0.7985; 0.8773]

12

0.8501 [0.8237; 0.8773]

3

ANN

10

0.8487 [0.8190; 0.8795]

2

0.9200 [0.9025; 0.9379]

4

DT

6

0.7957 [0.7390; 0.8567]

5

0.7691 [0.6674; 0.8864]

5

SVM

8

0.8491 [0.8048; 0.8958]

6

0.8737 [0.8551; 0.8927]

6

XGBoost

6

0.8953 [0.8526; 0.9401]

4

0.9295 [0.9094; 0.9500]

7

NB

1

0.8750 [0.8601; 0.8901]

2

0.8539 [0.8251; 0.8837]

8

KNN

1

0.7560 [0.7217; 0.7919]

1

0.9500 [0.9302; 0.9702]

9

Other

3

0.8416 [0.7825; 0.9051]

  

10

Overall

69

0.8491 [0.8337; 0.8649]

53

0.8633 [0.8467; 0.8802]