Skip to main content

Table 2 Univariate and multivariable logistic regression analyses for selecting clinical and radiological characteristics

From: Endoscopic ultrasonography-based intratumoral and peritumoral machine learning ultrasomics model for predicting the pathological grading of pancreatic neuroendocrine tumors

Variable

Univariate analysis

Multivariate analysis

OR (95% CI)

P-value

OR(95% CI)

P-value

Age

1.000(0.991, 1.009)

0.987

  

Maximum diameter

1.013(1.006, 1.020)

0.002**

0.725(0.584,0.900)

0.016*

Shape

0.656(0.528,0.815)

0.002**

1.010(1.003,1.017)

0.018*

Margin

0.700(0.495,0.990)

0.091

  

Echo

1.281(0.921, 1.781)

0.214

  

uniformity

0.860(0.680,1.088)

0.288

  

Calcification

0.696(0.305,1.587)

0.456

  

Cystic areas

1.164(0.645, 2.102)

0.668

  

Location

1.109(0.996,1.236)

0.115

  

Gender

1.057(0.828,1.350)

0.704

  
  1. OR Odds ratio, CI Confidence interval,* means P-value < 0.05, ** means P-value < 0.01
Back to article page

BMC Medical Imaging

ISSN: 1471-2342

Contact us