Skip to main content

Table 1 Demographic characteristics and textual characteristics for the main corpus and corpus with headache attack descriptions

From: Using natural language processing to automatically classify written self-reported narratives by patients with migraine or cluster headache

 

Corpus with full texts

Corpus with headache attack descriptions only

All patients

Migraine

Cluster headache

All patients

Migraine

Cluster headache

Number

121

81

40

112

74

38

Mean age in years (SD)

45 (13)

43.1 (12)

48.9 (14.2)

45 (13)

42 (12)

50 (13.6)

Number of females (percentage)

72 (60%)

64 (80%)

8 (20%)

68 (60.7%)

61 (82.4%)

7 (18.4%)

Tokens per text: median (Q1-Q3)

476 (218–765)

474 (227–745)

508 (198–794)

156 (80–242)

152 (84–242)

156 (71–223)

Types per text: median (Q1-Q3)

231 (130–321)

224 (131–317)

236 (126–341)

94 (60–131)

89 (61–133)

96 (55–122)

Sentences per text: median (Q1-Q3)

23 (10–42)

23 (11–41)

22 (8–40)

7 (3–12)

8 (4–12)

5 (2–11)

  1. Legend: Q1 Lower quartile, Q3 Upper quartile, SD Standard deviation