Skip to main content

Table 2 Respiratory parameters of critically ill ventilated subjects categorised by 1-year mortality

From: Explainable machine learning to predict long-term mortality in critically ill ventilated patients: a retrospective study in central Taiwan

 

All

Survivor

Non-survivor

p value

N = 6994

N = 4589

N = 2405

Day 1

 FiO2 (%)

47.1 ± 13.6

45.5 ± 12.2

50.2 ± 15.5

< 0.01

 PEEP

5.9 ± 2.3

5.7 ± 2.2

6.3 ± 2.4

< 0.01

 VT/PBW

8.7 ± 2.1

8.7 ± 2.0

8.8 ± 2.2

0.03

 Ppeak

22.8 ± 5.0

22.2 ± 4.8

23.9 ± 5.2

< 0.01

Day 2

 FiO2 (%)

41.6 ± 8.9

41.1 ± 8.1

42.6 ± 10.1

< 0.01

 PEEP

6.1 ± 2.5

5.8 ± 2.4

6.7 ± 2.7

< 0.01

 VT/PBW

41.6 ± 8.9

41.1 ± 8.1

42.6 ± 10.1

< 0.01

 Ppeak

22.4 ± 5.2

21.7 ± 4.9

23.8 ± 5.4

< 0.01

Day 3

 FiO2 (%)

40.4 ± 8.4

40.1 ± 7.8

41.0 ± 9.3

< 0.01

 PEEP

6.1 ± 2.4

5.7 ± 2.2

6.6 ± 2.7

< 0.01

 VT/PBW

8.7 ± 2.3

8.6 ± 2.2

8.8 ± 2.4

< 0.01

 Ppeak

22.1 ± 5.3

21.4 ± 5.0

23.5 ± 5.6

< 0.01

Day 7

 FiO2 (%)

39.3 ± 8.4

39.0 ± 7.5

39.7 ± 9.8

< 0.01

 PEEP

5.8 ± 2.0

5.5 ± 1.6

6.3 ± 2.4

< 0.01

 VT/PBW

8.7 ± 2.4

8.6 ± 2.3

8.8 ± 2.5

< 0.01

 Ppeak

20.9 ± 5.3

20.2 ± 4.8

22.4 ± 6.0

< 0.01

  1. Data were presented as mean ± standard deviation
  2. PEEP positive end-expiratory pressure, VT tidal volume, PBW predicted body weight, Ppeak peak pressure