Table 1 Baseline demographic and clinical characteristics in training and external validation sets

From: An end-to-end deep learning pipeline for hematoma expansion prediction in spontaneous intracerebral hemorrhage based on non-contrast computed tomography

Clinical characteristics

Training set (n = 1103)

External validation set 1 (n = 513)

External validation set 2 (n = 404)

p-value

Sex, n(%)

0.407a

Male

783 (71.0%)

371 (72.3%)

276 (68.3%)

 

Female

320 (29.0%)

142 (27.7%)

128 (31.7%)

 

Age (years, Mean ± SD)

60.08 ± 13.36

59.91 ± 13.69

60.75 ± 13.98

0.611b

Hematoma expansion, n(%)

0.621a

Yes

218 (19.8%)

112 (21.8%)

81 (20.0%)

 

No

885 (80.2%)

401 (78.2%)

323(80.0%)

 

Baseline volume [mL, Median (IQR)]

20.36 (21.95)

19.75 (21.65)

20.06 (21.53)

0.820c

Follow-up volume [mL, Median (IQR)]

22.70 (26.15)

22.59 (26.95)

22.84 (27.15)

0.800c

  1. Continuous variables are presented as mean ± SD or median (interquartile range), categorical variables are presented as frequencies (n) and percentages (%); aAnalyzed by chi-square test; bAnalyzed by one-way ANOVA test; cAnalyzed by Kruskal-Wallis test.
Back to article page