Machine Learning Algorithms Identify Pathogen-Specific Biomarkers of Clinical and Metabolomic Characteristics in Septic Patients with Bacterial Infections
Table 1
Characteristics of the patients in our study.
Clinical variable
Control
Gram-positive
Gram-negative
No.
%
No.
%
No.
%
29
—
67
67
33
33
Age (years)
<50
4
13.79
23
34.33
8
24.24
50-60
8
27.59
17
25.37
8
24.24
60-70
7
24.14
12
17.91
8
24.24
70-80
4
13.79
7
10.45
4
12.12
≥80
6
20.69
8
11.94
5
15.15
Sex
Male
12
41.38
41
61.19
17
51.52
Female
17
58.62
26
38.81
16
48.48
Race
Black
21
72.41
45
67.16
21
63.64
White
7
24.14
17
25.37
11
33.33
Other
1
3.45
5
7.46
1
3.03
Pathogen
S. aureus
N/A
27
N/A
S. pneumoniae
N/A
28
N/A
E. coli
N/A
N/A
17
APACHE II
Temperature (°C)
MAP (mmHg)
Heart rate
Respiratory rate
Serum sodium (mM)
Serum potassium (mM)
Serum creatinine (mg/dl)
Blood lactate (mg/dl)
Hematocrit
White cell count
Platelet count
Data are presented as . MAP: mean arterial pressure; N/A: not available.
