Skip to main content

Table 2 clinical characteristics of high-risk and low-risk groups in the training set

From: Predicting micropapillary or solid pattern of lung adenocarcinoma with CT-based radiomics, conventional radiographic and clinical features

Characteristic

high risk, N = 1221

low risk, N = 1241

p-value2

multivariate

age

62 (55, 67)

61 (55, 67)

> 0.9

 

gender

  

< 0.001

 

 Female

48 (39%)

75 (60%)

  

 Male

74 (61%)

49 (40%)

  

max diameter(mm)

39 (28, 54)

32 (22, 43)

< 0.001

0.008

smoking history

57 (47%)

32 (26%)

< 0.001

 

lung cancer family history

12 (9.8%)

12 (9.7%)

> 0.9

 

ProGRP

42 (36, 54)

44 (39, 58)

0.11

 

CEA

4 (2, 7)

3 (2, 5)

0.2

 

cyfra

2.25 (1.70, 3.48)

2.20 (1.68, 3.30)

0.7

 

NSE

13.50 (12.60, 15.80)

13.11 (12.10, 14.50)

0.062

 

SCCA

0.80 (0.60, 1.00)

0.70 (0.50, 0.90)

0.2

 

type

  

< 0.001

< 0.001

(pure-GGO)

 CTR < 0.5

1 (0.8%)

19 (15%)

  

 CTR > 0.5

1 (0.8%)

5 (4.0%)

  

 pure-GGO

0 (0%)

14 (11%)

  

 solid

120 (98%)

86 (69%)

  

lobular

36 (30%)

56 (45%)

0.011

0.013

spiculation

76 (62%)

73 (59%)

0.6

 

pleural traction

37 (30%)

26 (21%)

0.093

 

air bronchus

19 (16%)

35 (28%)

0.017

0.011

vessel

39 (32%)

65 (52%)

0.001

 

hollow

17 (14%)

16 (13%)

0.8

 

smooth edge

9 (7.4%)

4 (3.2%)

0.15

 

adjacent to pleural

15 (12%)

15 (12%)

> 0.9

 
  1. 1Median (IQR); n (%)
  2. 2Wilcoxon rank sum test; Pearson’s Chi-squared test; Fisher’s exact test