Skip to main content

Table 1 Characteristics of participants in this study

From: Machine learning for predicting diabetes risk in western China adults

Category

Features

Health (n = 3774084)

Diabetes (n = 301347)

p value

Questionnaire

Sex, n(%)

  

 < 0.001

 Male

1778128 (47.11%)

141120 (46.83%)

 

 Female

1995956 (52.89%)

160227 (53.17%)

 

 Age(year)

49.33 ± 15.58

61.77 ± 11.13

 < 0.001

Ethnicity, n(%)

  

 < 0.001

 Uyghur

2015933 (53.42%)

133687 (44.36%)

 

 Han

1106565 (29.32%)

128512 (42.65%)

 

 Kazak

369059 (9.78%)

12591 (4.18%)

 

 Hui

177841 (4.71%)

21256 (7.05%)

 

 Khalkha

36773 (0.97%)

1025 (0.34%)

 

 Mongol

34752 (0.92%)

1479 (0.49%)

 

 Tajik

6655 (0.70%)

105 (0.03%)

 

 Other

26506 (0.18%)

2692 (0.89%)

 

EH, n(%)

  

 < 0.001

 Balanced diet

3647207 (96.64%)

289846 (96.18%)

 

 Meat based

54428 (1.44%)

4466 (1.48%)

 

 Vegetarian based

72449 (1.92%)

7035 (2.33%)

 

SS,n(%)

  

 < 0.001

 Never smoked

3352894 (88.84%)

271177 (89.99%)

 

 Smoking

396921 (10.52%)

26578 (8.82%)

 

 Quit smoking

24269 (0.64%)

3592 (1.19%)

 

HTN,n(%)

  

 < 0.001

 No

2977467 (78.89%)

109105 (36.21%)

 

 Yes

796617 (21.11%)

192242 (63.79%)

 

CAD,n(%)

  

 < 0.001

 No

3609085 (95.63%)

252633 (83.83%)

 

 Yes

164999 (4.37%)

48714 (16.17%)

 

PDM,n(%)

  

 < 0.001

 No

3742806 (99.17%)

294209 (97.63%)

 

 Yes

31278 (0.83%)

7138 (2.37%)

 

Routine examination

WC (cm)

86.36 ± 11.46

91.39 ± 11.46

 < 0.001

BMI (kg/m2)

25.08 ± 3.89

26.65 ± 3.76

 < 0.001

Laboratory test

HGB, g/L

140.96 ± 16.65

143.11 ± 15.5

 < 0.001

The WBC, × 109/L

6.29 ± 1.47

6.6 ± 1.5

 < 0.001

PLT, × 109/L

235.08 ± 57.5

227.88 ± 57.92

 < 0.001

FBG, mmol/L

5.19 ± 0.69

5.81 ± 0.68

 < 0.001

ECG,n(%)

0.21 ± 0.41

0.3 ± 0.46

 < 0.001

Normal

2982273 (79.02%)

212044 (70.37%)

 

Abnormal

791811 (20.98%)

89303 (29.63%)

 

TC, mmol/L

4.41 ± 0.96

4.68 ± 1.01

 < 0.001

TG, mmol/L

1.26 ± 0.54

1.49 ± 0.56

 < 0.001

LDLC, mmol/L

2.48 ± 0.8

2.62 ± 0.86

 < 0.001

HDLC, mmol/L

1.36 ± 0.36

1.32 ± 0.36

 < 0.001

  1. For continuous variables, the data are expressed as the mean ± standard deviation, and for categorical variables, the data are expressed as counts (percentage)
  2. DM diabetes mellitus, EF exercise frequency, EH eating habits, SS smoking status, HTN hypertension, CAD coronary heart disease, PHTN parental hypertension, PDM parental diabetes mellitus, PCHD parental coronary heart disease, MS marital status, WC waist circumference, BMI body mass index, SBP systolic blood pressure, DBP diastolic blood pressure, HGB hemoglobin, WBC white blood cell, PLT platelet, FBG fasting blood glucose, ECG electrocardiogram, TC total cholesterol, TG triglyceride, LDLC low-density lipoprotein cholesterol, HDLC high-density lipoprotein cholesterol