Skip to main content

Table 4 Counts of how many models were statistically not different to the best model for each dataset, sorted by AUC-ROC of the best model

From: Evaluation of the dependence of radiomic features on the machine learning model

Dataset

AUC-ROC of best model

Number of stat. eq. models

Song2020

0.98

9

Li2020

0.89

34

Toivonen2019

0.87

45

Arita2018

0.83

18

Ramella2018

0.81

23

Lu2019

0.76

27

Hosny2018B

0.73

26

Hosny2018C

0.69

14

Keek2020

0.69

56

Carvalho2018

0.67

52

Sasaki2019

0.67

61

Park2020

0.65

48

Hosny2018A

0.64

53

Veeraraghavan2020

0.64

42