Table 4 Comparison of patient characteristics between GLASS training and testing cohorts

From: A deep learning model to predict glioma recurrence using integrated genomic and clinical data

 

Training (70)

Testing (16)

p-value

Recurrence outcome [n]

Late

29

7

1.0

Early

41

9

Tumor grade [n]

Grade 2

4

1

0.896

Grade 3

7

1

Grade 4

59

14

Histology [n]a

Astrocytoma

8

2

0.151

Glioblastoma

58

13

Oligodendroglioma

0

1

Astrocytoma wildtype

4

0

IDH & 1p19q codeletion status [n]

IDH-mutant, non-codeleted

8

2

0.107

IDH-wildtype

62

13

IDH-mutant, codeleted

0

1

Vital status [n]

Deceased

65

14

0.61

Alive

5

2

Days to recurrence

Median

319.5

334.5

0.833

IQR

387.5

311.8

Age [yr]

Median

55.0

48.0

0.117

IQR

18.0

11.3

  1. Chi-square tests of independence were used for all categorical variables, unless expected cell counts were <5 in a 2 × 2 contingency table, in which case we applied Fisher’s exact test. The Mann–Whitney U test was used for age and days to recurrence. All statistical tests were two-sided (significance α = 0.05).
  2. Bracketed numbers next to Training/Testing indicate the number of included patients.
  3. aHistology represents the reassigned labels, as described in Methods and Fig. 2.
Back to article page