From: Improving precision of glomerular filtration rate estimating model by ensemble learning
Characteristic | Development (N = 1002) | External validation (N = 417) | P value# |
---|---|---|---|
Age (years) | 55.7 ± 15.0 | 51.3 ± 16.0 | < 0.001 |
Male proportion | 570 (56.9) | 262 (62.8) | 0.044 |
Diabetes | 500 (49.9) | 97 (23.2) | < 0.001 |
Body mass index (kg/m2) | 24.0 ± 3.7 | 22.9 ± 3.6 | < 0.001 |
Weight (kg) | 63.7 ± 12.3 | 61.5 ± 11.8 | 0.002 |
Height (cm) | 162.5 ± 8.3 | 163.6 ± 7.6 | 0.020 |
Body-surface area (m2) | 1.7 ± 0.2 | 1.7 ± 0.2 | 0.107 |
Serum creatinine (mg/dl) | 1.7 ± 1.8 | 2.7 ± 2.5 | < 0.001 |
Measured GFR | |||
Mean (ml/min/1.73 m2) | 70.0 ± 29.6 | 53.4 ± 26.5 | < 0.001 |
< 15 (ml/min/1.73 m2) | 10 (1.0) | 9 (2.2) | < 0.001 |
≥ 15 and < 30 (ml/min/1.73 m2) | 99 (9.9) | 94 (22.5) | |
≥ 30 and < 60 (ml/min/1.73 m2) | 275 (27.4) | 149 (35.7) | |
≥ 60 and < 90 (ml/min/1.73 m2) | 345 (34.4) | 123 (29.5) | |
≥ 90 (ml/min/1.73 m2) | 273 (27.2) | 42 (10.1) |