Skip to main content
. 2021 Nov 1;17(11):2197–2204. doi: 10.5664/jcsm.9424

Table 5.

Logistic regression analysis using 3 models.

Odds Ratio or Coef. P 95% CI
ICU Admission
 Model 1* 1.46 .03 1.03–2.07
 Model 2** 1.08 .69 0.75–1.56
 Model 3***,† 0.86 .46 0.58–1.28
Length of hospital stay
 Model 1 2.09 (coef.) .057 −0.65 to 4.25
 Model 2 0.64 (coef.) .57 −1.60 to 2.88
 Model 3 −1.13 (coef.) .32 −3.34 to 1.08
Intubation
 Model 1 1.3 .17 0.89–1.9
 Model 2 0.95 .81 0.63–1.43
 Model 3 0.70 .11 0.46–1.09
Mortality
 Model 1 1.16 .53 0.73–1.82
 Model 2 1.01 .98 0.62–1.63
 Model 3 0.75 .27 0.44–1.25

*Model 1: OSA without adjustment. **Model 2: Model 1 after adjustment for age, sex, and BMI. ***Model 3: Model 1 after adjustment for age, sex, BMI, and comorbid diseases (hypertension, diabetes mellitus, coronary artery disease, chronic obstructive pulmonary disease, cerebrovascular diseases, congestive heart failure, cancer, and chronic kidney disease). The Nagelkerke’s R2 (%) for the linear regression of LOS is 8.4%, ICU admission (12%), intubation (12.6%), and mortality (18.2%). All values are for model 3. BMI = body mass index, CI = confidence interval, coef. = coefficient, COPD = chronic obstructive pulmonary disease, ICU = intensive care unit, LOS = length of hospital stay, OSA = obstructive sleep apnea.