Table 1 Sociodemographic characteristics of the sample according to negative (non-death) and positive (death) class (n = 9412)

From: Predicting all-cause mortality with machine learning among Brazilians aged 50 and over: results from The Brazilian Longitudinal Study of Ageing (ELSI-Brazil)

Variables

No death (n = 8442)

Death (n = 970)

Age

61.7

60.9–62.5

70.0

68.7–71.3

Sex

Male

45.4

42.3–48.4

52.9

48.8–57.0

Female

54.6

51.6–57.7

47.1

43.0–51.2

Skin color

White

42.7

37.2–48.4

42.5

36.8–48.5

Black

9.8

8.0–12.0

8.6

6.2–11.9

Brown

44.7

40.3–49.1

44.7

39.6–49.8

Yellow

1.0

0.7–1.3

1.9

1.1–3.5

Indigenous

1.8

1.3–2.6

2.3

1.1–4.4

Marital Status

Single

11.3

9.9–12.9

13.4

10.7–16.7

Married/stable union

65.0

62.1–67.9

48.0

62.1–67.9

Divorced or separated

10.1

9.2–11.0

12.3

9.7–15.5

Widowed

13.6

11.7–15.6

26.2

23.3–29.4

Education

Less than 8 years

60.2

57.0–63.3

75.5

71.5–79.2

8 to 10 years

13.0

11.6–14.6

10.9

8.6–13.8

11 years or more

26.8

24.4–29.2

13.6

10.9–16.8

Back to article page