From: Machine learning-based prediction models for accidental hypothermia patients
Variables | Development cohort | Validation cohort |
---|---|---|
(N = 288) | (N = 244) | |
Vital signs | ||
Body temperature | 30.7 (28.3–32.6) | 31 (28–32.7) |
Heart rate | 65 (50–82) | 63 (45–84) |
SBP | 116 (93–139) | 113 (87–136) |
GCS | 8 (5–11) | 8 (4–11) |
13–15 | 105 (36.5%) | 103 (42.2%) |
9–12 | 96 (33.3%) | 68 (27.9%) |
3–8 | 87 (30.2%) | 73 (29.9%) |
Cardiac arrest | 5 (1.7%) | 16 (6.6%) |
Blood gas assessment | ||
pH | 7.32 (7.26–7.36) | 7.31 (7.23–7.37) |
PaCO2 | 42.1 (32.8–47.8) | 43.8 (37.3–50.4) |
PaO2 | 115.2 (90.1–156) | 115.6 (76.3–183.8) |
HCO3 | 21 (15.6–25.4) | 21.6 (16.7–25.3) |
Base Excess | − 4.3 (− 10.2–0.1) | − 4.4 (− 9.6–0.2) |
Lactate | 2.6 (1.4–5.1) | 3.2 (1.6–6.6) |
Blood test results | ||
WBC | 82.1 (53.3–127.3) | 83 (51.3–120.8) |
Hgb | 11.7 (10–13.4) | 12 (10.3–13.5) |
Hct | 35.3 (30–40.3) | 36.4 (32–40.7) |
PLT | 17.1 (12.2–22.8) | 19.4 (13.5–24.5) |
Glu | 127.5 (88.8–178) | 141.7 (101–195) |
Na | 139 (135–143) | 140 (137–143) |
K | 4.2 (3.6–4.7) | 4 (3.5–4.6) |
Cl | 103 (99–107) | 103 (100–107) |
Ca | 8.8 (8.4–9.3) | 8.8 (8.3–9.2) |
Cr | 1.1 (0.6–2) | 0.9 (0.6–1.6) |
BUN | 38 (20.4–60) | 28.2 (17–51.7) |
TP | 6.5 (5.8–7) | 6.4 (5.7–7.2) |
Alb | 3.4 (2.9–3.9) | 3.5 (3–4) |
T-bil | 0.6 (0.5–1.1) | 0.6 (0.4–0.9) |
CK | 503 (142.3–1388) | 418.5 (129–1281.5) |
CRP | 1.8 (0.4–6.2) | 1.1 (0.1–4) |
Score | ||
SOFA | 4 [3–6] | 4 [2–7] |
5A score | 4 [3–5] | 4 [2–5] |