Skip to main content

Table 2 Patient characteristics in the development and validation datasets

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)  
  1. Unless otherwise noted, data are reported as N (percentage); continuous variables are mean ± standard deviation
  2. GFR glomerular filtration rate
  3. #P values were derived from paired-sample t test