Table 1 Patient characteristics of the cancer cases in the three Chinese institutions

From: Diagnostic and interpretive gains from reasoning over conclusions with a large reasoning model in radiology

Characteristic

Institution 1 (n = 300)

Institution 2 (n = 300)

Institution 3 (n = 300)

p value

Breast cancer

150

150

150

 

 Age

55 ± 20

60 ± 17

62 ± 16

0.02

 Sex

   

-

  Female

150 (100.0)

150 (100.0)

150 (100.0)

 

 Histological type

   

0.52

  CIS

25 (16.7)

31 (20.7)

24 (16.0)

 

  NST

108 (72.0)

95 (63.3)

104 (69.3)

 

  Special types

17 (11.3)

24 (16.0)

22 (14.7)

 

 Modality

   

-

  MG

50 (33.3)

50 (33.3)

50 (33.3)

 

  CT

50 (33.3)

50 (33.3)

50 (33.3)

 

  MRI

50 (33.3)

50 (33.3)

50 (33.3)

 

Lung cancer

50

50

50

 

 Age

61 ± 18

62 ± 16

64 ± 15

0.33

 Sex

   

-

  Male

25 (50.0)

25 (50.0)

25 (50.0)

 

  Female

25 (50.0)

25 (50.0)

25 (50.0)

 

 Histological type

   

0.22

  NSCLC

43 (86.0)

46 (92.0)

40 (80.0)

 

  SCLC

7 (14.0)

4 (8.0)

10 (20.0)

 

 Modality

   

-

  CT

50 (100.0)

50 (100.0)

50 (100.0)

 

Colorectal cancer

100

100

100

 

 Age

63 ± 16

60 ± 12

63 ± 14

0.21

 Sex

   

-

  Male

50 (50.0)

50 (50.0)

50 (50.0)

 

  Female

50 (50.0)

50 (50.0)

50 (50.0)

 

 Location of lesion

   

0.11

  Colon

26 (26.0)

38 (38.0)

20 (20.0)

 

  Rectum

58 (58.0)

40 (40.0)

48 (48.0)

 

  Junction

16 (16.0)

22 (22.0)

32 (32.0)

 

 Modality

   

-

  CT

50 (50.0)

50 (50.0)

50 (50.0)

 

  MRI

50 (50.0)

50 (50.0)

50 (50.0)

 
  1. Categorical data are presented as the number of patients, with percentages shown in parentheses. Age is expressed as mean ± standard deviation. Comparisons of categorical variables among the three institutions were performed using the χ2 test, while comparisons of continuous variables were conducted using the Kruskal-Wallis test.