Skip to main content

Table 4 Results of feature variable analysis in LR model

From: Machine learning for predicting the risk stratification of 1–5 cm gastric gastrointestinal stromal tumors based on CT

CT features

β

OR

OR (95%CI)

P value

LD

0.064

1.066

1.034–1.099

0.000

SD

   

0.550

Contour

   

0.288

Necrosis

   

0.658

Surface ulceration

   

0.404

Intratumoral angiogenesis

   

0.248

  1. LD, long diameter; SD, short diameter; OR, odds ratio; CI, confidence interval
  2. P values written in bold indicate significant difference