Table 2 Distribution of BC risk factors related to oestrogen metabolism (Group 2) in the KBCP dataset.

From: Predicting breast cancer risk using interacting genetic and demographic factors and machine learning

Feature names

Cases (N = 445)

Controls (N = 250)

All subjects (N = 695)

Description

p-value

Oral contraceptive use

0

300 (67%)

124 (49%)

424 (61%)

If subject has used oral contraceptives: 0: No; 1: Yes

5e-6

1

145 (33%)

126 (51%)

271 (39%)

Oral contraceptive use duration

Mean (std)

48.27 (51.50)

40.86 (38.91)

44.82 (46.22)

Duration of oral contraceptive use in months.

0.08

Menopausal status

0

127 (29%)

109 (44%)

236 (34%)

If menopause has occurred: 0: No; 1: Yes

8e-5

1

318 (71%)

141 (56%)

459 (66%)

Breast- feeding

0

107 (24%)

39 (16%)

146 (21%)

Whether the subject has breast-fed: 0: No; 1: Yes

0.01

1

338 (76%)

211 (84%)

549 (79%)

Pregnancy

0

85 (19%)

31 (12%)

116 (17%)

Whether the subject has had a full-term pregnancy: 0: No; 1: Yes

0.03

1

360 (81%)

219 (88%)

579 (83%)

Hormonal replacement therapy, oestrogen duration

Mean (std)

53.94 (58.03)

39.85 (47.86)

48.25 (54.59)

Duration of oestrogen use in months.

0.6

Menstrual cycle length

Mean (std)

26.94 (2.27)

27.26 (2.65)

27.06 (2.42)

Length of menstrual cycle in days.

0.09

First pregnancy length

Mean (std)

39.20 (3.37)

39.18 (3.88)

39.19 (3.58)

Length of 1st pregnancy in weeks.

0.12

Second pregnancy length

Mean (std)

39.66 (1.95)

38.99 (4.64)

39.39 (3.31)

Length of 2nd pregnancy in weeks.

0.03

Third pregnancy length

Mean (std)

38.97 (3.93)

38.64 (5.70)

38.85 (4.66)

Length of 3rd pregnancy in weeks.

0.12

Body mass index (BMI)

Mean (std)

26.49 (4.60)

26.04 (4.29)

26.33 (4.50)

Body mass index.

0.2

  1. The P-values denote the differences in the Group 2 features between the BC cases and controls using the chi-squared test for categorical variables and the t-test for continuous variables. The difference is statistically significant when the p-value < 0.05 (highlighted p-values). P-values were not adjusted for multiple testing. std: standard deviation.