Skip to main content

Table 7 Algorithm sensitivity across the testing sample depression group stratified by potential confounding factors

From: Using heart rate profiles during sleep as a biomarker of depression

  Stratification Sensitivity (%)a n χ 2(df) p
Body Mass Index Normal 61.9 21 10.5 (2) .005
Overweight 83.3 36
Obese 96.7 30
Psychotropic Medication Use Yes 87.0 69 4.1 (1) <.050
No 66.7 18
Depression Severity Mild 83.9 31 0.2 (2) .927
Moderate 80.6 31
Severe 84.0 25
Psychiatric Comorbidity Yes 75.9 29 1.5 (1) .229
No 86.2 58
Cardiovascular Disease or Related Risk Factor Yes 83.9 31 0.0 (1) .838
No 82.1 56
Cardiovascular Medication Use Yes 82.6 23 0.0 (1) .982
No 82.8 64
Smoking Status Non-Smoker 82.5 63 0.0 (1) .930
Current Smoker 83.3 24
AHI <  5 79.7 69 2.2 (1) .141
≥ 5 94.4 18
Sleep Onset Latency (min) ≤ 15 82.2 45 0.0 (1) .891
>  15 83.3 42
REM Onset Latency (min) ≤ 164 80.0 40 0.7 (1) .390
>  164 87.2 39
%REM ≤ 13 90.9 44 4.1 (1) <.050
>  13 74.4 43
  1. aThe algorithm’s ability to accurately detect cases of depression (i.e. true positive rate)
  2. AHI Apnea-Hypopnea Index, REM Rapid eye movement