Table 1 Baseline characteristic between train dataset and test dataset

From: Identifying the predictive effectiveness of a genetic risk score for incident hypertension using machine learning methods among populations in rural China

Variables

Total population (n = 4592)

Train dataset (n = 3214)

Test dataset (n = 1378)

t / χ2

P value

Age, mean ± sd

49.04 ± 11.52

48.92 ± 11.51

49.34 ± 11.55

āˆ’1.156

0.248

Women, n (%)

2896 (63.07)

2037 (63.38)

859 (62.34)

0.450

0.502

Education, n (%)

Ā Ā Ā 

1.954

0.377

Ā Ā Ā Ā Primary and below

2112 (45.99)

1493 (46.45)

619 (44.92)

Ā Ā 

Ā Ā Ā Ā Junior

1962 (42.73)

1371 (42.66)

591 (42.89)

Ā Ā 

Ā Ā Ā Ā Senior and above

518 (11.28)

350 (10.89)

168 (12.19)

Ā Ā 

Marital status, n (%)

Ā Ā Ā 

1.137

0.286

Ā Ā Ā Ā Married/cohabit

4262 (92.85)

2991 (93.12)

1271 (92.24)

Ā Ā 

Ā Ā Ā Ā Widowed/divorced/separated/spinsterhood

328 (7.15)

221 (6.88)

107 (7.76)

Ā Ā 

Per capita monthly income, n (%)

Ā Ā Ā 

1.321

0.517

Ā Ā Ā Ā <1000 (RMB)

4174 (91.10)

2931 (91.31)

1243 (90.60)

Ā Ā 

Ā Ā Ā Ā 1000~ (RMB)

308 (6.72)

214 (6.67)

94 (6.85)

Ā Ā 

Ā Ā Ā Ā 3000~ (RMB)

100 (2.18)

65 (2.02)

35 (2.55)

Ā Ā 

Smoking, n (%)

1226 (26.70)

853 (26.54)

373 (27.07)

0.137

0.711

Drinking, n (%)

588 (12.80)

404 (12.57)

184 (13.35)

0.529

0.467

High fat diet, n (%)

132 (2.92)

90 (2.84)

42 (3.10)

0.227

0.634

High salt diet, n (%)

2826 (62.41)

1979 (62.49)

847 (62.23)

0.026

0.871

Less fruits and vegetables intake, n (%)

2784 (60.61)

1964 (61.08)

820 (59.51)

1.004

0.316

Physical activity, n (%)

Ā Ā Ā 

1.901

0.387

Ā Ā Ā Ā Low

2250 (49.00)

1567 (48.76)

683 (49.56)

Ā Ā 

Ā Ā Ā Ā Moderate

1024 (22.30)

706 (21.97)

318 (23.08)

Ā Ā 

Ā Ā Ā Ā High

1318 (28.70)

941 (29.28)

377 (27.36)

Ā Ā 

Family history of hypertension, n (%)

1394 (30.36)

959 (29.84)

435 (31.57)

1.364

0.243

TC, mean ± sd (mmol/L)

4.41 ± 0.90

4.41 ± 0.89

4.42 ± 0.93

āˆ’0.293

0.770

TG, mean ± sd (mmol/L)

1.57 ± 1.11

1.57 ± 1.11

1.56 ± 1.11

0.104

0.917

HDL-C, mean ± sd (mmol/L)

1.18 ± 0.27

1.17 ± 0.26

1.18 ± 0.28

āˆ’0.496

0.620

LDL-C, mean ± sd (mmol/L)

2.55 ± 0.73

2.55 ± 0.73

2.54 ± 0.74

0.370

0.711

BMI, mean ± sd (kg/m2)

24.15 ± 3.33

24.16 ± 3.32

24.12 ± 3.34

0.407

0.684

SBP, mean ± sd (mmHg)

116.06 ± 11.44

115.95 ± 11.34

116.32 ± 11.65

āˆ’1.019

0.308

DBP, mean ± sd (mmHg)

73.62 ± 7.59

73.60 ± 7.52

73.67 ± 7.75

āˆ’0.297

0.766

Pulse pressure, mean ± sd (mmHg)

42.43 ± 8.07

42.34 ± 8.08

42.65 ± 8.05

āˆ’1.163

0.245

  1. Pulse pressure was calculated as SBP-DBP. The incidence of hypertension was 18.90% with a 3-year follow-up period.
  2. TC cholesterol, TG triglyceride, HDL-C high density lipoprotein cholesterol, LDL-C low density lipoprotein cholesterol, BMI body mass index, SBP systolic Blood Pressure, DBP diastolic Blood Pressure