Skip to main content

Table 2 Multivariate Logistic regression using backward elimination strategy

From: Radiomic assessment as a method for predicting tumor mutation burden (TMB) of bladder cancer patients: a feasibility study

Radiomic Features Beta value OR 95%CI OR P value AUCa
log-sigma-1-0-mm-3D glcm Imc1 −1.24 0.29 0.10–0.82 0.019 0.637
log-sigma-2-5-mm-3D glcm MaximumProbability 1.14 3.13 1.34–7.33 0.009 0.638
wavelet-LHL glcm MCC −1.02 0.36 0.16–0.82 0.015 0.690
wavelet-LHH glszm ZoneEntropy 1.56 4.74 1.70–13.20 0.003 0.661
wavelet-HLH glszm SizeZoneNonUniformityNormalized 1.23 3.43 1.45–8.13 0.005 0.696
wavelet-HHL glcm MCC −0.80 0.45 0.18–1.12 0.086 0.644
  1. OR Odds ratio, CI confidence interval
  2. a Area under the receiver operator characteristic curve