Table 2 Summaries of clinical characteristics in the training, testing and external testing cohort.

From: A computerized diagnostic model for automatically evaluating placenta accrete spectrum disorders based on the combined MR radiomics-clinical signatures

Characteristics

Training

Validating

Testing

Normal (n = 248)

PAS disorders (n = 110)

P value

Normal (n = 107)

PAS disorders (n = 47)

P value

Normal (n = 13)

PAS disorders (n = 15)

P value

Age, years (mean ± SD)

33.0 ± 4.6

33.7 ± 4.3

0.180

33.0 ± 4.5

33.7 ± 5.0

0.378

32.7 ± 3.9

36.4 ± 3.3

0.015

Gravida (mean ± SD)

3.5 ± 2.1

4.1 ± 1.9

0.100

3.6 ± 2.0

3.5 ± 1.8

0.145

2.1 ± 1.2

2.7 ± 2.0

0.656

Para (mean ± SD)

1.8 ± 0.8

1.8 ± 0.6

0.407

1.8 ± 0.8

1.7 ± 0.7

0.570

0.7 ± 0.6

0.8 ± 0.8

0.713

Placental position

  

 < 0.001

  

 < 0.001

  

0.004

Normal

164

21

 

76

7

 

15

2

 

Low lying placenta

19

4

 

5

2

 

0

0

 

Marginal placenta previa

3

3

 

1

1

 

0

1

 

Partial placenta previa

38

41

 

15

21

 

0

0

 

Complete placenta previa

12

37

 

4

15

 

2

4

 

Pernicious placenta previa

12

4

 

6

1

 

0

6

 
  1. P value of all characteristics are calculated by one of independent-samples t-test, Mann–Whitney U-test or chi-squared test based on their distribution.
Back to article page