Table 3 Characteristics of the 500 bootstrap subsets (500 entries each) created according to the AIS grade distributions present in the Sygen cohort including only complete cases for the variables of interest, and a balanced cohort, where all 4 grades are present in equal proportions
From: Studying missingness in spinal cord injury data: challenges and impact of data imputation
Outcome at week 52 | Sygen complete cases (subsets) | Balanced (subsets) | |
|---|---|---|---|
Number of patients | n | 500 | 500 |
Number of male | mean (SD) | 396.8 (8.6) | 385.5 (9.2) |
Age [years] | mean (SD) | 32.0 (13.3) | 34.2 (14.0) |
LEMS at week 01 | mean (SD) | 2.7 (7.0) | 8.5 (12.1) |
median [95% CI] | 0 [0–0] | 0 [0–0] | |
LEMS at week 26 | mean (SD) | 11.9 (18.8) | 25.6 (21.5) |
median [95% CI] | 0 [0–0] | 34 [33–34] | |
NA, n | 24.9 (5.2) | 22.8 (4.6) | |
LEMS at week 52 | mean (SD) | 12.6 (19.3) | 26.2 (21.7) |
median [95% CI] | 0 [0–0] | 35 [35–36] | |
Level of injury | cervical, mean (SD) | 372.3 (9.8) | 412.7 (8.4) |
thoracic, mean (SD) | 128.7 (9.8) | 87.3 (8.4) | |
AIS grade | A, n (%) | 325 (65.0) | 125 (25.0) |
B, n (%) | 55 (11.0) | 125 (25.0) | |
C, n (%) | 100 (20.0) | 125 (25.0) | |
D, n (%) | 20 (4.0) | 125 (25.0) |