Table 1 General characteristics of final data set (i.e., study population). “A case study performed in 2019-20 to develop a Machine Learning-algorithm to estimate the incidence of Diabetes Mellitus in France”

Age in years, mean (±SD)

47.8, ±13.2

47.8, ±13.2

57.0, ±8.2

Gender, men % (n)

46.9 (20946)

46.9 (20896)

61.7 (50)

 Never smoked

43.2 (19296)

43.2 (19271)

30.9 (25)

 Former smoker

33.1 (14772)

33.1 (14741)

38.3 (31)

 Current smoker

18.6 (8320)

18.6 (8307)

16.0 (13)

 Missing

5.1 (2271)

5.1 (2259)

14.8 (12)

Body mass index, kg/m² (mean, ±SD), (n)

25.0, ±4.4 (43668)

25.0, ±4.4 (43588)

31.8, ±6.0 (80)

Treated hypertension, yes, % (n)

11.3 (5031)

11.2 (4996)

43.2 (35)

Treated dyslipidemia, yes, % (n)

8.1 (3635)

8.1 (3609)

32.1 (26)

Mother/father diagnosed with diabetes, yes, % (n)

15.1 (6764)

15.1 (6730)

42.0 (34)

 No education - primary education

3.1 (1374)

3.1 (1366)

9.9 (8)

 Lower secondary education

6.9 (3060)

6.8 (3042)

22.2 (18)

 Upper secondary education

33.5 (14942)

33.4 (14911)

38.3 (31)

 Lower tertiary education

33.0 (14728)

33.0 (14714)

17.3 (14)

 Upper tertiary education

21.7 (9709)

21.8 (9699)

12.3 (10)

 Missing or other category

1.9 (846)

1.9 (846)

0 (.)

 Metropolitan France

87.9 (39249)

87.9 (39177)

88.9 (72)

 FOT^b

0.9 (381)

0.9 (379)

2.5 (2)

 Europe

4.2 (1861)

4.2 (1859)

2.5 (2)

 North Africa

2.8 (1260)

2.8 (1257)

3.7 (3)

 Sub-Saharan Africa

1.1 (503)

1.1 (502)

1.2 (1)

 Asia

0.7 (326)

0.7 (326)

. (.)

 Others

1.0 (433)

1.0 (433)

. (.)

 Missing or don’t want to answer

1.4 (646)

1.4 (645)

1.2 (1)

 Employed

65.2 (29123)

65.3 (29093)

37.0 (30)

 Unemployed

6.1 (2721)

6.1 (2712)

11.1 (9)

 Retired

21.8 (9753)

21.8 (9720)

40.7 (33)

 Student

1.5 (653)

1.5 (653)

0 (.)

 Unemployed due to disability

0.9 (390)

0.9 (385)

6.2 (5)

 No professional activity

1.4 (603)

1.4 (602)

1.2 (1)

 Missing or other category

3.2 (1416)

3.2 (1413)

3.7 (3)