Table 1. Characteristics of critically ill patients in training and validation cohorts.
| Training cohort | Validation cohort | P | |
|---|---|---|---|
| (n = 4895) | (n = 5048) | ||
| Demographic parameters | |||
| Age, y | 59.7 ± 17.7 | 60.8 ± 17.4 | 0.002 |
| Gender, n (%) | 0.224 | ||
| Female | 2022 (41.3%) | 2146 (42.5%) | |
| Male | 2873 (58.7%) | 2902 (57.5%) | |
| Ethnicity, n (%) | < 0.001 | ||
| White | 3416 (69.8%) | 3814 (75.6%) | |
| Black | 280 (5.7%) | 366 (7.3%) | |
| Others | 1199 (24.5%) | 868 (17.2%) | |
| Laboratory parameters | |||
| Gluavg (mmol/l), median (IQR) | 6.4 (5.8–7.2) | 6.3 (5.7–7.0) | < 0.001 |
| GluSD (mmol/l), median (IQR) | 1.1 (0.7–1.8) | 1.0 (0.7–1.6) | < 0.001 |
| Hyperglycemia rate, n (%) | 696 (14.2%) | 536 (10.6%) | < 0.001 |
| Hypoglycemia rate, n (%) | 321 (6.6%) | 303 (6.0%) | 0.254 |
| Clinical parameters | |||
| Mechanical ventilation rate, n (%) | 2028 (41.4%) | 1897 (37.6%) | < 0.001 |
| Length of hospital stay, d, median (IQR) | 4.0 (3.0–5.0) | 4.0 (3.0–5.0) | < 0.001 |
| Readmission rate, n (%) | 776 (15.9%) | 635 (12.6%) | < 0.001 |
| Hospital mortality, n (%) | 649 (13.3%) | 468 (9.3%) | < 0.001 |
| 30-day mortality, n (%) | 611 (12.5%) | 489 (9.7%) | < 0.001 |
| 9-month mortality, n (%) | 914 (18.7%) | 803 (15.9%) | < 0.001 |
| Scoring systems | |||
| GCS, median (IQR) | 15.0 (8.0–15.0) | 15.0 (8.0–15.0) | 0.024 |
| SOFA, median (IQR) | 4.0 (2.0–6.0) | 3.0 (1.0–5.0) | < 0.001 |
| SAPS II, median (IQR) | 31.0 (22.0–45.0) | 29.0 (21.0–43.0) | < 0.001 |
| Elixhauser score, median (IQR) | 0.0 (-1.0–4.0) | 0.0 (-1.0–6.0) | 0.096 |
NOTE. Normal distributed data presented as mean ± SD (P < 0.05; independent Student’s t-test); non-normal distributed data presented as median (IQR) (P < 0.05; non-parametric Wilcoxon test); categorical variables presented as counts (n) or percentages (%).
Gluavg = average of glucose levels, GluSD = standard deviation of glucose levels.