Table 1 Characteristics of the datasets used in this study

From: Advancing sleep health equity through deep learning on large-scale nocturnal respiratory signals

Dataset

Nights

Age (%)

Male (%)

AHI (%)

Hypertension (%)

LD+ (%)

PD (%)

  

< 45

[45, 55)

[55, 65)

> =65

 

< 5

[5, 15)

[15, 30)

> =30

   

SHHS1*

5736

5.9

17.6

30.6

45.9

47.8

17.3

38.3

27.3

17.1

30.7

42.7

/

SHHS2*

2638

0.1

11.6

28.9

59.4

46.2

17.4

37.1

27.0

18.5

44.2

6.7

0.5

MrOS1*

2848

0.0

0.0

0.0

100.0

100.0

9.3

33.6

32.1

25.0

49.8

5.1

1.1

MrOS2*

999

0.0

0.0

0.0

100.0

100.0

10.0

31.4

31.5

27.0

52.9

/

1.6

MESA*

2015

0.0

0.1

36.7

63.2

46.3

10.4

30.5

29.5

29.6

/

/

/

SOF*

446

0.0

0.0

0.0

100.0

0.0

18.6

38.6

28.5

14.3

59.9

12.1

/

ClinSuZhou*

458

55.5

17.5

12.9

13.8

80.3

27.1

17.2

16.8

38.9

24.7

0.4

11.1

ClinHuaiAn#

424

56.1

21.9

14.9

6.8

86.8

11.3

16.3

16.5

55.9

27.1

/

/

ClinRadar#

221

62.0

19.5

11.8

6.3

81.4

24.9

19.0

18.6

37.6

21.3

0.9

6.3

  1. *Internal Dataset, #External Dataset.
  2. +LD Lung diseases, including COPD chronic bronchitis, asthma, and emphysema. PD Parkinson’s Disease.