Skip to main content

Table 2 Baseline characteristics

From: Gut microbiome-based machine learning for diagnostic prediction of liver fibrosis and cirrhosis: a systematic review and meta-analysis

Author

Year

Sex

Age (year)

MT

ODM

ROC

TP

FP

FN

TN

Caussy

2019

9/29

65.1 ± 9.8

Random forest

/

/

22

7

4

39

Dong

2020

19/0

66.2 ± 6.8

Random forest

10-fold cross-validation

0.82

36

9

14

16

Chen

2020

20/5

51.24 ± 6.91

Random forest

10-fold cross-validation

/

20

5

5

46

Gyu Oh

2020

5/22

64.74 ± 9.80

Random forest

10-fold cross-validation

Italy 0.89China 0.88

23

8

4

19

Loomba

2017

2/13

63.4 ± 3

Random forest/ Support Vector Machines

Separation of training set and test set

/

13

4

1

68

Lang 1A

2020

20/24

58.9 (20.2–79.6)

Logistic model

Leave-One-Out Cross-Validation

/

8

9

1

55

Lang 1B

2020

16/13

51.9 (28.8–74.2)

Logistic model

Leave-One-Out Cross-Validation

0.71

21

5

8

39

Lang 2

2020

8/5

64.0 ± 7.0

Random forest

Separation of training set and test set

/

12

17

1

66

Lapidot

2020

46/22

65.9

Random forest

20-fold cross-validation

/

62

10

6

17

Lee

2020

27/37

58.7 ± 10.7

/

/

0.721

48

6

16

101

Schwimmer

2019

62/65

12 ± 10.7

Classification Regression Tree/Decision Tree

10-fold cross-validation

/

65

1

22

36

  1. Sex Male/Female, MT Model type, ROC External Verification (Roc), TN True negative, TP True positive, FN False negative, FP False positive, ODM Overfitting detection method