Table 2 Characteristics of the study participants.

From: Deep learning to identify stroke within 4.5 h using DWI and FLAIR in a prospective multicenter study

 

Internal dataset

External dataset

Training set

Internal test set

p

External test set 1

External test set 2

p

(n = 487)

(n = 123)

(n = 468)

(n = 1151)

Age (years)

68 (58–74)

69 (60–76)

0.230

67 (58–76)

70 (61–77)

0.005

Male (number)

321 (65.9)

84.0 (68.3)

0.670

281 (60.0)

679 (59.0)

0.738

NIHSS score on admission

3 (1–6)

3 (1–6)

0.549

3 (1–6)1

5 (2–12)

< 0.001

Time from stroke to MRI (minutes)

408 (144–1094)

393 (174–892)

0.722

272 (122.5–850)

248 (145–880)

0.243

  1. Data are indicated in median (interquartile range) for continuous variables and number (%) for categorical variables. Continuous variables were compared using Mann–Whitney U test. Categorical variables were compared using Fisher’s exact test.
  2. 1NIHSS score on admission is unavailable for one patient.
  3. MRI, magnetic resonance imaging; NIHSS, National Institutes of Health Stroke Scale.
Back to article page