Skip to main content

Table 2 Multivariable Cox regression analysis in 398 patients admitted with SARS-CoV-2 in a West London population, during March 1–April 23, 2020

From: Comparison of deep learning with regression analysis in creating predictive models for SARS-CoV-2 outcomes

Variable

Hazard ratio

Lower 95% CI

Upper 95% CI

p value

Age

1.05

1.03

1.07

< 0.005

Sex (F)

0.6

0.36

1

0.05

Cardiac failure

2.92

1.52

5.62

< 0.005

Cerebrovascular event

2.36

1.28

4.36

0.01

Chronic kidney disease

2.32

1.31

4.1

< 0.005

Chronic liver disease

3.52

1.2

10.35

0.02

Chronic respiratory disease

0.9

0.53

1.53

0.7

Diabetes

1.41

0.86

2.3

0.17

Hypertension

1.02

0.64

1.63

0.93

Ischaemic heart disease

2.09

1.29

3.4

< 0.005

Obesity

2.74

0.97

7.7

0.06

NOD

1.01

0.97

1.05

0.65

Abdominal pain

0.29

0.08

1.02

0.05

Collapse

4.21

2.4

7.41

< 0.005

Confusion

6.03

3.5

10.41

< 0.005

Cough

1.88

1.1

3.2

0.02

Diarrhoea/vomiting

1.32

0.68

2.54

0.41

Dyspnoea

3.49

1.93

6.32

< 0.005

Fever

1.88

1.13

3.13

0.02

Myalgia

1.43

0.69

2.94

0.33

Olfactory change

0.87

0.31

2.47

0.79

  1. NOD Number of days of symptoms prior to hospital admission