Table 1 Patient characteristics in the development and test datasets.

From: Augmented prediction of vertebral collapse after osteoporotic vertebral compression fractures through parameter-efficient fine-tuning of biomedical foundation models

 

Overall (n = 245)

p-value

Development dataset

(n = 200, 81.6%)

Test dataset

(n = 45, 18.4%)

VC, n (%)

102 (51.0)

18 (40.0)

0.243

Age, mean ± SD (years)

72.6 ± 9.56

73.7 ± 8.56

0.460

Female, n (%)

166 (83.0)

31 (68.9)

0.052

T-score of BMD, mean ± SD (Lumbar)

-3.08 ± 1.04

-3.52 ± 1.16

0.013*

Lumbar Fracture, n (%)

134 (67.0)

29 (64.4)

0.878

History of medication for osteoporosis, n (%)

 Before OVCF Dx

42 (21.0)

8 (17.8)

0.780

 After OVCF Dx

153 (76.5)

36 (80.0)

0.758

  1. p-values less than 0.05 are considered statistically significant. VC Vertebral collapse, SD standard deviation, BMD bone mineral density, OVCF osteoporotic vertebral compression fracture, dx diagnosis
  2. *Indicates a statistically significant difference.
Back to article page