Skip to main content

Table 1 Clinical baseline characteristic of patients in the training cohort, validation cohort, and test cohort

From: Development of a deep learning radiomics model combining lumbar CT, multi-sequence MRI, and clinical data to predict high-risk cage subsidence after lumbar fusion: a retrospective multicenter study

Characteristic

Training cohort, (n = 214)

Validation cohort, (n = 61)

Test cohort, (n = 30)

p

Sex, no (%)

   

0.993

 Female

114 (53.27)

29 (47.54)

14 (46.67)

 

 Male

100 (46.73)

32 (52.46)

16 (53.33)

 

Age (years)

   

0.004*

 Mean (range)

64.39 ± 9.11

60.00 ± 9.98

64.90 ± 8.13

 

Follow-up

   

0.816

 Mean (range)

9.82 ± 3.19

9.87 ± 3.00

9.17 ± 2.20

 

BMI

   

0.687

 Mean (range)

26.65 ± 3.86

26.46 ± 4.00

27.21 ± 4.27

 

Diagnosis, No (%)

   

 < 0.001*

 Lumbar spinal stenosis

113 (52.80)

15 (24.59)

9 (30.00)

 

 Spondylolisthesis

58 (27.10)

16 (26.23)

11 (36.67)

 

 Lumbar disc herniation

43 (20.09)

30 (49.18)

10 (33.33)

 

Segment

   

0.035*

 1

131 (61.21)

46 (75.41)

24 (80.00)

 

 2

69 (32.24)

15 (24.59)

6 (20.00)

 

 3

14 (6.54)

   

Osteoporosis, no (%)

   

0.363

 Yes

108 (50.47)

36 (59.02)

12 (40.00)

 

 No

106 (49.53)

25 (40.98)

18 (60.00)

 
  1. *Indicates statistical significance at p <0.05