Table 2 Encounter characteristics of the training, validation, and testing cohorts
Characteristics | Training cohort (N = 303) | Validation cohort (N = 101) | Testing cohort (N = 104) | p-value train versus Test* | p-value validation versus test* | p-value train + validation versus test* |
|---|---|---|---|---|---|---|
Number of unique patients N (%) | 288 (95.0) | 96 (95.0) | 97 (93.3) | |||
Primary outcome (N, (%)) | ||||||
Mortality | 43 (14.2) | 6 (5.9) | 11 (10.6) | 0.18 | 0.12 | < 0.0001 |
Demographics | ||||||
Age in years Mean (std) | 56.6 (16.6) | 56.6 (15.6) | 53.4 (14.2) | 0.012 | 0.028 | 0.009 |
Female N (%) | 147 (48.5) | 50 (49.5) | 56 (53.8) | 0.18 | 0.27 | 0.18 |
Race/ethnicity (N, (%)) | 0.63 | 0.95 | 0.76 | |||
Black | 137 (45.2) | 51 (50.5) | 49 (47.1) | |||
Hispanic | 36 (11.9) | 13 (12.9) | 16 (15.4) | |||
Other, non- hispanic | 112 (37.0) | 30 (29.7) | 32 (30.7) | |||
White | 18 (5.9) | 7 (6.9) | 7 (6.7) | |||
Mean (std) of the number of laboratory measurements per encounter | ||||||
636 (786) | 510 (663) | 531 (972) | 0.078 | 0.228 | 0.090 | |
Mean (std) vital signs measurements per encounter | ||||||
999 (1540) | 765 (1344) | 802 (1971) | 0.026 | 0.12 | 0.030 | |
Comorbidities | 0.81 | 0.69 | 0.81 | |||
Mean (std) comorbidities per encounter | 1.0 (1.1) | 1.0 (1.1) | 0.9 (0.9) | |||
Hypertension N (%) | 128 (42.2) | 43 (42.6) | 37 (35.6) | |||
Diabetes N (%) | 89 (29.4) | 32 (31.7) | 30 (28.8) | |||
Heart disease N (%) | 12 (3.9) | 1 (1.0) | 2 (1.9) | |||
COPD N (%) | 3 (1.0) | 0 (0.0) | 1 (1.0) | |||
Stroke N (%) | 1 (0.3) | 0 (0.0) | 0 (0.0) | |||
Cerebrovascular disease N (%) | 0 (0.0) | 2 (2.0) | 0 (0.0) | |||
Cancer N (%) | 4 (1.3) | 2 (2.0) | 1 (1.0) | |||
Respiratory problems N (%) | 44 (14.5) | 12 (11.9) | 15 (14.4) | |||
Chronic kidney disease N (%) | 28 (9.2) | 11 (10.9) | 6 (5.7) | |||
Tuberculosis N (%) | 3 (1.0) | 1 (1.0) | 3 (2.9) | |||