Table 2 The data set is divided into training set and validation set

From: Machine learning-based MRI radiomics predict IL18 expression and overall survival of low-grade glioma patients

Variables

Total (n = 139)

Train (n = 98)

Validation (n = 41)

p

IL18, n (%)

   

1

 Low

90 (65)

63 (64)

27 (66)

 

 High

49 (35)

35 (36)

14 (34)

 

Age, n (%)

   

0.734

 ~40

59 (42)

43 (44)

16 (39)

 

 41~

80 (58)

55 (56)

25 (61)

 

Gender, n (%)

  

0.869

 Female

71 (51)

51 (52)

20 (49)

 

 Male

68 (49)

47 (48)

21 (51)

 

Histologic_grade, n (%)

 

0.836

 G2

71 (51)

49 (50)

22 (54)

 

 G3

68 (49)

49 (50)

19 (46)

 

Radiotherapy, n (%)

  

1

 NO

46 (33)

32 (33)

14 (34)

 

 YES

93 (67)

66 (67)

27 (66)

 

Histological_type, n (%)

 

0.53

 Astrocytoma

46 (33)

35 (36)

11 (27)

 

 Oligoastrocytoma

34 (24)

22 (22)

12 (29)

 

 Oligodendroglioma

59 (42)

41 (42)

18 (44)

 

Chr_1p_19q_codeletion, n (%)

 

0.476

 Codel

38 (27)

29 (30)

9 (22)

 

 Non-Codel

101 (73)

69 (70)

32 (78)

 

IDH_status, n (%)

  

1

 Mutant

109 (78)

77 (79)

32 (78)

 

 WT

30 (22)

21 (21)

9 (22)

 

MGMT_promoter_status, n (%)

 

0.725

 Methylated

111 (80)

77 (79)

34 (83)

 

 Unmethylated

28 (20)

21 (21)

7 (17)

 

Chemotherapy, n (%)

  

1

 NO

45 (32)

32 (33)

13 (32)

 

 YES

94 (68)

66 (67)

28 (68)

 

OS, n (%)

   

0.504

 Alive

102 (73)

74 (76)

28 (68)

 

 Dead

37 (27)

24 (24)

13 (32)

 

OS. time, Median (Q1, Q3)

21.7 (14.97, 40.7)

20.27 (14.39, 38.57)

30.27 (17.77, 48.97)

0.036