Table 2 Sample characteristics of the second dataset (Alzheimer’s Sleep Dataset)

From: Wearable sleep recording augmented by artificial intelligence for Alzheimer’s disease screening

 

Test dataset for sleep staging model & dataset for AD detection model

 

non-AD

AD

  

Total

Prodromal Disease stagea

n

30

35

12

Age

70·63 ± 7·10

74·63 ± 6·52

74·5 ± 6·29

% female

63·3

45·7

33·3

BMI

24·69 ± 3·84

23·52 ± 3·25

24·28 ± 3·36

AHI

8·07 ± 6·71

16·81 ± 13·54

21·2 ± 15·97

ESS

4·40 ± 3·04

4·74 ± 3·56

4·17 ± 3·51

MMSE

28·87 ± 0·88

20·00 ± 7·33

27·92 ± 1·04

PSQI

4·77 ± 3·24

3·86 ± 3·29

4·42 ± 3·59

  1. The Alzheimer’s Sleep Dataset consists of patients with AD and cognitively intact elderly. This dataset (Alzheimer’s Sleep Dataset) was pooled with a part of the Senior Sleep Dataset to obtain the test dataset (n = 102). This table only shows the characteristics of the Alzheimer’s Sleep Dataset.
  2. Data are reported as mean ± standard deviation unless otherwise indicated.
  3. AD Alzheimer’s disease, AHI apnea-hypopnea index, BMI body mass index, ESS Epworth Sleepiness Scale, MMSE Mini-Mental State Examination, OSA obstructive sleep apnea, PSQI Pittsburg sleep quality index.
  4. a12 of the AD patients had an MMSE score ≥ 27/30 and were labeled as being in the prodromal AD stage.
Back to article page