Skip to main content

Table 2 Descriptive statistics of selected variables for the training data set

From: Polytomous diagnosis of ovarian tumors as benign, borderline, primary invasive or metastatic: development and validation of standard and kernel-based risk prediction models

 

Benign

Border-line

Primary invasive

Meta-static

Variables

N = 563

N = 40

N = 121

N = 30

Continuous

    

Age, years (median)

42

52.5

58

59

Maximum diameter of mass, mm (median)

63

108

98

73

Maximum diameter of solid part, mm (median)

0

22

51

54

Ordinal

    

Number of papillations (mean)#

0.35

1.70

1.43

0.93

Binary

    

Ascites (%)

3.2

12.5

50.4

40.0

Entirely solid tumor (%)

6.6

7.5

32.2

56.7

Irregular internal cyst walls (%)

33.6

67.5

88.4

83.3

Personal history of ovarian cancer (%)

0.9

5.0

0.8

10.0

Bilateral tumors (%)

17.6

12.5

41.3

33.3

Papillary structures with blood flow (%)

6.8

47.5

43.0

23.3

Acoustic shadows (%)

13.0

2.5

0.0

3.3

Unilocular tumor without solid component (%)

40.3

2.5

0.0

0.0

  1. # Values are 0, 1, 2, 3, 4 (more than three).