Table 2 Input variables and their descriptive statistics in eICU at 72-h
From: Novel criteria to classify ARDS severity using a machine learning approach
Mild | Moderate | Severe | All | |
|---|---|---|---|---|
A. ARDS patients | 872 (37.49%) | 1025 (44.07%) | 429 (18.44%) | 2326 (100%) |
B. Descriptive feature—means and 95% CI | ||||
Age | 64.77 [63.78, 65.76] | 62.73 [61.83, 63.64] | 59.97 [58.67, 61.28] | 62.99 [62.39, 63.59] |
PEEP | 5.95 [5.80, 6.09] | 7.16 [6.99, 7.34] | 10.09 [9.72, 10.46] | 7.25 [7.12, 7.38] |
FiO2 | 0.40 [0.39, 0.41] | 0.50 [0.49, 0.51] | 0.81 [0.79, 0.83] | 0.52 [0.51, 0.53] |
PaO2 | 98.89 [97.17, 100.62] | 80.52 [79.25, 81.78] | 74.81 [72.83, 76.79] | 86.36 [85.34, 87.37] |
PaCO2 | 39.93 [39.33, 40.53] | 42.38 [41.72, 43.04] | 44.23 [43.13, 45.33] | 41.80 [41.38, 42.23] |